Bahan Ajar Statistika

BAHAN AJAR
STATISTIKA
JURUSAN PENDIDIKAN DAN SASTRA INGGRIS

FAKULTAS BAHASA DAN SENI
UNIVERSITAS NEGERI SEMARANG
2021
HALAMAN PENGESAHAN
Pada hari ini Kamis tanggal 19 bulan Agustus tahun 2021 Bahan Ajar Mata Kuliah
Statistika Program Studi Pendidikan Bahasa Inggris telah diverifikasi oleh Ketua
Jurusan Pendidikan dan Sastra Inggris.
Semarang, 19 Agustus 2021
Ketua Jurusan/ Ketua Prodi Ketua Tim Penulis
Widhiyanto, S.Pd., M.Pd., Ph.D Arif Suryo Priyatmojo, S.Pd., M.Pd

NIP. 197309052005011001 NIP. 198306102010121002
PRAKATA
Bahan ajar ini mengenalkan mahasiswa Pendidikan Bahasa Inggris tentang
pengetahuan Statistika, ketrampilan dan proses data yang diawali dengan teori
statistika sampai ketrampilan menganalisa data dari sebuah kegiatan penelitian.
DESKRIPSI MATA KULIAH
CP Lulusan
Attitude:
- Able to internalize values, norms and academic etiquette;
- Able to express responsibility toward his independent works;
General skills:
- Able to implement logical, critical, systematic and innovative thinking in the
context of developing or implementing knowledge and technology in accordance
to humanities based on the expertise.
- Able to show independent, qualified and measurable work;
- Able to make correct decision in the context of problem solving in their expertise
based on the analysis of information and data.
Specific skill (1)

- Able to apply ICT to support successful learning process
- Able to do research related to English language learning & teaching
Specific skill (2)

Able to apply the concept of academic integrity in general, plagiarism in specific
that includes types of plagiarism, penalty and effort to avoid plagiarism and to
master theoretical concept of other filed of studies in general as well as formulate
procedural problem-solving related to the concept.
Knowledge
- Able to do research related to English language learning & teaching
- Master theoretical concept of other field of studies in general as well as
formulating procedural problem-solving related to the concepts.
CP Mata Kuliah
CLO 1
Able to demonstrate responsibility by integrating norms, values, and academic
etiquette.
CLO 2
Able to make correct decisions in the context of problem solving in their expertise
based on the analysis of information and data.
CLO 3
Able to apply ICT in the learning process
CLO 4
Able to do research related to English language learning and teaching
CLO 5
Master theoretical concept of English language learning and teaching as well as
other field of studies
DAFTAR ISI
Week 1&2 Statistics and statistical thinking

Week 3&4 Quantitative & Qualitative Paradigm
Week 5 Types of Data
Week 6&7 Describing Data Set
Week 8 Mid Test
Week 9&10 Microsoft Office Excel
Week 11&12 Central Tendency
Week 13,14,15 SPPS
Week 16 Final Test
UNITS
A HANDBOOK OF STATISTICS Statistics and Statistical Thinking
1 STATISTICS AND STATISTICAL

THINKING
Statistics is the science of data. It involves collecting, classifying, summarizing, organizing,
analyzing, and interpreting numerical information. Statistics is used in several different
disciplines (both scientific and non-scientific) to make decisions and draw conclusions
based on data.
For instance:
• In the pharmaceutical industry, it is impossible to test a potential drug on every

single person that may require it. But, what drug companies can do, is consult a
statistician who can help them draw a sample of individuals and administer the
drug to them. The statistician can then analyze the effects of the drug on the
sample and generalize their findings to the population. If the drug fails to alleviate
any negative symptoms from their sample, then perhaps the drug isn’t ready to be
rolled out to the population.
• In business, managers must often decide whom to offer their company’s products
to. For instance, a credit card company must assess how risky a potential customer
is. In the world of credit, risk is often measured by the measuring the chance that a
person will be negligent in paying their credit card bill. This clearly is a tricky task
since we have limited information about this individual’s propensity to not pay their
bills. To measure risk, managers often recruit statisticians to build statistical models
that predict the chances a person will default on paying their bill. The manager
can then apply the model to potential customers to determine their risk and that
information can be used to decide whether or not to offer them a financial product.
As a more concrete example, suppose that an individual, Dave, needs to lose weight for
his upcoming high school reunion. Dave decided that the best way for him to do this was
through dieting or adopting an exercise routine. A health counselor that Dave has hired to
assist him, gave him four options:
1. The Atkins Diet

2. The South Beach Diet
3. A diet where you severely reduce your caloric intake
4. Boot Camp, which is an extremely vigorous, daily, exercise regimen.
Download free eBooks at bookboon.com

7
Dave, who understands that using data in making decisions can provide additional insight,
decides to analyze some historical trends that his counselor gave him on individuals (similar
in build to Dave) that have used the different diets. The counselor provided the weights for
different individuals who went on these diets over an eight week period.
Weight
Diet 1 2 3 4 5 6 7 8
Atkins 310 310 304 300 290 285 280 284
South Beach 310 312 308 304 300 295 290 289
Reduced Calorie 310 307 306 303 301 299 297 295
Boot Camp 310 308 305 303 297 294 290 287
Average Weight Loss on Various Diets across Eight Weeks (initial weight listed in week 1)
Based on these numbers, which diet should Dave adopt?
What if Dave’s goal is to lose the most weight? The Atkins1 diet would seem like a reasonable
choice as he would have lost the most weight at the end of the eight week period. However,
the high protein nature of the diet might not appeal to Dave. Also, Atkins seems to have
some ebb and flow in the weight loss (see week 7 to week 8). What if Dave wanted to lose
the weight in a steadier fashion? Then perhaps boot camp might be the diet of choice since
the data shows an even, steady decline in weight loss. This example demonstrates that Dave
can make an educated decision that is congruent with his own personal weight loss goals.
There are two types of statistics that are often referred to when making a statistical decision
or working on a statistical problem.
Definitions
Descriptive Statistics: Descriptive statistics utilize numerical and graphical methods to look
for patterns in a data set, to summarize the information revealed in a data set, and to present
the information in a convenient form that individuals can use to make decisions. The main
goal of descriptive statistics is to describe a data set. Thus, the class of descriptive statistics
includes both numerical measures (e.g. the mean or the median) and graphical displays of
data (e.g. pie charts or bar graphs).
Inferential Statistics: Inferential statistics utilizes sample data to make estimates, decisions,
predictions, or other generalizations about a larger set of data. Some examples of inferential
statistics might be a z statistics or a t-statistics, both of which we will encounter in later
sections of this book.

8
1.1 DESCRIPTIVE STATISTICS

Dave can use some basic descriptive statistics to better understand his diet and where there
might be opportunity to change some of his dietary habits. The table below displays the
caloric contents of the foods that Dave has eaten this past week.
Sunday Monday Tuesday Wednesday
Breakfast 4 Coffees Protein Plate Skip Fruit
Calories 200 175 0 200
Lunch Pizza and Wings Salad Super Burrito Salad
Calories 1200 375 750 375
Dinner Leftovers Frozen Dinner Frozen Dinner Frozen Dinner
Calories 1000 275 300 300
Snack 3 Beers 3 Beers 3 Beers 3 Beers
Calories 300 300 300 300
Caloric Intake Log for Sunday–Wednesday
What information can be gleaned from the above caloric intake log? The simplest thing
to do is to look at the total calories consumed for each day. These totals are shown below.
Sunday Monday Tuesday Wednesday
Breakfast 4 Coffees Protein Plate Skip Fruit
Calories 200 175 0 200
Lunch Pizza and Wings Salad Super Burrito Salad
Calories 1200 375 750 375
Dinner Leftovers Frozen Dinner Frozen Dinner Frozen Dinner
Calories 1000 275 300 300
Snack 3 Beers 3 Beers 3 Beers 3 Beers
Calories 300 300 300 300
Daily Total 2700 1125 1350 1175
Caloric Intake Log (with totals) for Sunday–Wednesday

9
What new information does providing the totals add?
• The heaviest calorie day was by far on Sunday.

• Enjoying the three beers per night is consuming approximately 20% of Dave’s
calories on each day (except Sunday).
• Dave tends to have higher calorie lunches on the days that he skipped breakfast
(or just had coffee).
The third point is an interesting take away from the above analysis. When Dave skips
breakfast, his lunches are significantly higher in caloric content than on the days that he
eats a breakfast. What Dave can take away from this is quite clear – he should start each
day by eating a healthy breakfast as this will most likely lead to eating less total calories
during the day.
1.2 INFERENTIAL STATISTICS

The main goal of inferential statistics is to make a conclusion about a population based
off of a sample of data from that population. One of the most commonly used inferential
techniques is hypothesis testing. The statistical details of hypothesis testing will be covered in
a later chapter but hypothesis testing can be discussed here to illustrate inferential statistical
decision making.
Key Definitions
Experimental Unit: An object upon which data is collected.
Population: A set of units that is of interest to study.
Variable: A characteristic or property of an individual experimental unit.
Sample: A subset of the units of a population.
What is a statistical hypothesis? It is an educated guess about the relationship between

two (or more) variables. As an example, consider a question that would be important to
the CEO of a running shoe company: Does a person have a better chance of finishing a
marathon if they are wearing the shoe brand of the CEO’s company than if they are wearing
a competitor’s brand? The CEO’s hypothesis would be that runners wearing his company’s
shoes would have a better chance at completing the race since his shoes are superior. Once
the hypothesis is formed, the mechanics of running the test are executed. The first step is
defining the variables in your problem. When forming a statistical hypothesis, the variables
of interest are either dependent or independent variables.

10
Definition
Dependent Variable: The variable which represents the effect that is being tested
Independent Variable: The variable that represents the inputs to the dependent variable,
or the variable that can be manipulated to see if they are the cause.
In this example, the dependent variable is whether an individual was able to complete a
marathon. The independent variable is which brand of shoes they were wearing, the CEO’s
brand or a different brand. These variables would operationalized by adopting a measure
for the dependent variable (did the person complete the marathon) and adopting a measure
for the kind of sneaker they were wearing (if they were wearing the CEO’s brand when
they ran the race).
After the variables are operationalized and the data collected, select a statistical test to evaluate
their data. In this example, the CEO might compare the proportion of people who finished
the marathon wearing the CEO’s shoes against the proportion who finished the marathon
wearing a different brand. If the CEO’s hypothesis is correct (that wearing his shoes helps
to complete marathons) then one would expect that the completion rate would be higher
for those wearing the CEO’s brand and statistical testing would support this.
Since it is not realistic to collect data on every runner in the race, a more efficient option
is to take a sample of runners and collect your dependent and independent measurements
on them. Then conduct your inferential test on the sample and (assuming the test has been
conducted properly) generalize your conclusions to the entire population of marathon runners.
While descriptive and inferential problems have several commonalities, there are some
differences worth highlighting. The key steps for each type of problem are summarized below:
Elements of a Descriptive Statistical Problem
1) Define the population (or sample) of interest

2) Select the variables that are going to be investigated
3) Select the tables, graphs, or numerical summary tools.
4) Identify patterns in the data.

11
Elements of an Inferential Statistical Problem
1) define the population of interest

2) Select the variables that are going to be investigated
3) Select a sample of the population units
4) Run the statistical test on the sample.
5) Generalize the result to your population and draw conclusions.
1.3 TYPES OF DATA

There are two main types of data used in statistical research: qualitative data and quantitative
data. Qualitative data are measurements that cannot be measured on a natural numerical
scale. They can only be classified into one or more groups of categories. For instance, brands
of shoes cannot be classified on a numerical scale, we can only group them into aggregate
categories such as Nike, Adidas, or K-Swiss. Another example of a qualitative variable is an
individual’s gender. They are either male or female and there is no ordering or measuring on
a numerical scale. You are one or the other. Graphs are very useful in studying qualitative
data and the next chapter will introduce graphical techniques that are useful in studying
such data.
Quantitative data are measurements that can be recorded on a naturally occurring scale.
Thus, things like the time it takes to run a mile or the amount in dollars that a salesman
has earned this year are both examples of quantitative variables.
1.4 CHAPTER 1 PROBLEMS

1) Discuss the difference between descriptive and inferential statistics.
2) Give an example of a research question that would use an inferential statistical solution.
3) Identify the independent and dependent variable in the following research question:
A production manager is interested in knowing if employees are effective if they
work a shorter work week. To answer this question he proposes the following
research question: Do more widgets get made if employees work 4 days a week
or 5 days a week?
4) What is the difference between a population and a sample?
5) Write about a time where you used descriptive statistics to help make a decision
in your daily life.

12
bs_bs_banner
European Journal of Education, Vol. 48, No. 2, 2013
Comparison of Quantitative and Qualitative

Research Traditions: epistemological, theoretical,
and methodological differences
Kaya Yilmaz
Introduction
Educational researchers in every discipline need to be cognisant of alternative
research traditions to make decisions about which method to use when embarking
on a research study. There are two major approaches to research that can be used
in the study of the social and the individual world. These are quantitative and
qualitative research. Although there are books on research methods that discuss the
differences between alternative approaches, it is rare to find an article that exam-
ines the design issues at the intersection of the quantitative and qualitative divide
based on eminent research literature. The purpose of this article is to explain the
major differences between the two research paradigms by comparing them in
terms of their epistemological, theoretical, and methodological underpinnings.
Since quantitative research has well-established strategies and methods but quali-
tative research is still growing and becoming more differentiated in methodological
approaches, greater consideration will be given to the latter.
Definition of the Terms

What is quantitative research? It can be defined as research that explains phenom-
ena according to numerical data which are analysed by means of mathematically-
based methods, especially statistics. From a broader perspective, it can be defined
as a type of empirical research into a social phenomenon or human problem,
testing a theory consisting of variables which are measured with numbers and
analysed with statistics in order to determine if the theory explains or predicts
phenomena of interest (Creswell, 1994; Gay & Airasian, 2000). What is qualitative
research? Although it is deemed ‘difficult to define’ because of its multifaceted
nature underpinned by different paradigms (Hitchcock & Hughes, 1995, p. 26), a
working definition has been provided by some researchers. Strauss and Corbin
(1998) offer this definition: ‘By the term “qualitative research” we mean any type
of research that produces findings not arrived at by statistical procedures or other
means of quantification’ (pp. 10–11). But this definition is simplistic since it
focuses on procedures and techniques used to collect and analyse data, ignoring
other aspects of research design. It also tends to define the term from a quantitative
perspective rather than focus on its characteristics. Gay and Airasian (2000, p. 627)
define qualitative research as ‘the collection of extensive data on many variables
over an extended period of time, in a naturalistic setting, in order to gain insights
not possible using other types of research’. But this definition also suffers from an
identical problem, since it uses a quantitative concept to define a qualitative term
(Qualitative research is based on the epistemological assumption that social phe-
nomena are so complex and interwoven that they cannot be reduced to isolated
variables, so it is not appropriate to use the term variable when defining qualitative
© 2013 John Wiley & Sons Ltd

312 European Journal of Education, Part II
research). Hence, qualitative research needs to be comprehensively defined to do

justice to its key characteristics. Drawing on the research literature (Creswell,
2007, p. 37; Denzin & Lincoln, 1998, 2005, p. 3; Miles & Huberman, 1994,
pp. 6–7; Patton, 2002, pp. 39–41), I define it as an emergent, inductive, interpretive
and naturalistic approach to the study of people, cases, phenomena, social situa-
tions and processes in their natural settings in order to reveal in descriptive terms
the meanings that people attach to their experiences of the world.
It should be noted that qualitative research is not based on a single method-
ology and does not belong to a single discipline (Denzin & Lincoln, 2005). It
‘draws on philosophical ideas in phenomenology, symbolic interactionism, herme-
neutics and other traditions to support the attention on “quality” rather than
“quantity”.’ (Brewer, 2003, p. 239). Therefore, the term is used as ‘an overarching
category, covering a wide range of approaches and methods found within different
research disciplines’ (Snape & Spencer, 2003, p. 3). There is a wide variety of
theoretical paradigms, methodologies, research strategies and methods in qualita-
tive research traditions, ranging from descriptive study, case study, field research,
ethnography, participant observation, biographical method, life history, oral
history, narrative inquiry to phenomenological research, ethno-methodology, sym-
bolic interactionist study, grounded theory and action research.
Differences between the Two Research Paradigms

When the characteristics of quantitative or qualitative research are discussed, the
four essential elements of the research process must be addressed. They are
epistemology, theoretical perspectives, methodology, and methods (Crotty, 1998).
Denzin and Lincoln (1998) suggested that four basic issues structure the design of
a research study: (a) Which paradigm or worldview will inform the study design?
(b) Who or what will be studied? (c) Which research strategies will be used? and (d)
Which research methods or tools will be used to collect and analyse data? This
article takes into account these components when explaining the differences
between quantitative and qualitative research approaches.
Quantitative and qualitative research designs differ in terms of their epistemo-
logical, theoretical and methodological underpinnings. Quantitative research is
informed by objectivist epistemology and thus seeks to develop explanatory univer-
sal laws in social behaviours by statistically measuring what it assumes to be a static
reality. It emphasises the measurement and analysis of causal relationships between
isolated variables within a framework which is value-free, logical, reductionistic, and
deterministic, based on a priori theories. A quantitative approach endorses the view
that psychological and social phenomena have an objective reality that is independ-
ent of the subjects being studied, i.e. the knower or the researcher and the known or
subjects are viewed as relatively separate and independent. Hence, reality should be
studied objectively by the researchers who should put a distance between themselves
and what is being studied. On the other hand, qualitative research is based on a
constructivist epistemology and explores what it assumes to be a socially con-
structed dynamic reality through a framework which is value-laden, flexible, descrip-
tive, holistic, and context sensitive; i.e. an in-depth description of the phenomenon
from the perspectives of the people involved. It tries to understand how social
experience is created and given meaning. From a qualitative perspective, reality or
knowledge are socially and psychologically constructed. The qualitative paradigm
views the relationship between the knower and the known as inextricably connected.

Kaya Yilmaz 313
Therefore, the researcher is supposed to develop a close, empathic relationship with

the subjects being studied (Bergman, 2008; Bryman, 1988; Cohen, Manion &
Marrison, 2007; Creswell, 2007; Denzin & Lincoln, 1998; Gelo, Braakmann &
Benetka, 2008; Patton, 2002).The epistemological, theoretical, and methodological
differences between quantitative and qualitative research designs, together with
their underlying assumptions, purposes, approaches and the researcher’s roles are
summarised in Table I.
Quantitative methods require the researcher to use a pre-constructed stand-
ardised instrument or pre-determined response categories into which the partici-
pants’ varying perspectives and experiences are expected to fit. They generally
demand randomly selected large representative samples in order for researchers to
generalise their findings from the sample, i.e. from where the logic and power of
probability sampling derive their purpose, generalisation. The major advantage
of this method is that it allows one to measure the responses of a number of
participants to a limited set of questions, thereby facilitating comparison and
statistical aggregation of the data. The results of closed-ended questionnaires help
the researchers to identify a general pattern of participants’ reactions to a treat-
ment or programme. Quantitative methods and procedures allow the researchers
to obtain a broad and generalisable set of findings and present them succinctly and
parsimoniously. But, because they require a deductive approach and predeter-
mined sets of standardised responses based on theory, they fail to provide insight
into the participants’ individual or personal experiences. They do not let the
respondents describe their feelings, thoughts, frames of reference, and experiences
with their own words. Quantitative researchers are supposed to play a neutral role
in the research process. Hence, the meaning participants ascribe to the phenom-
enon studied is largely ignored in quantitative studies (Patton, 2002).
Unlike quantitative studies which are concerned with outcomes, generalisation,
prediction, and cause-effect relationships through deductive reasoning, qualitative
studies are concerned with process, context, interpretation, meaning or under-
standing through inductive reasoning. The aim is to describe and understand the
phenomenon studied by capturing and communicating participants’ experiences
in their own words via observation and interview. What is emphasised is the
examination of the context that influences people’s actions or interactions and the
meaning that people ascribe to their experiences. People can elucidate how they
make sense of the world around them and their experiences through interviews
with open-ended questions. That is why qualitative research requires an in-depth
study of people’s lives or the issues in their natural settings without resorting to
standardised, pre-determined categories of analysis. Open-ended responses let the
researcher understand and present the world as it is seen and experienced by the
participants without predetermining those standpoints. Direct quotations docu-
ment the participants’ depth of feelings, experiences, thoughts about what is
happening, and meaning at a personal level. Hence, qualitative findings are far
longer, more detailed and variable in content than quantitative ones. Purposeful
sampling plays a key role. Irrespective of the kind of unit of analysis, the main aim
of purposeful sampling in qualitative research is to select and study a small number
of people or unique cases whose study produces a wealth of detailed information
and an in-depth understanding of the people, programmes, cases, and situations
studied. But, this sampling procedure limits the possibility of generalising research
findings to other settings or situations, i.e. it does not provide parsimonious

TABLE I. Comparison of Quantitative (Positivist) and Qualitative (Naturalist) Modes of Inquiry
Quantitative Mode Qualitative mode
Assumptions Assumptions
• Reality is single, tangible, and fragmentable. Social facts have an objective • Realities are multiple, constructed, and holistic. Reality is socially
reality. constructed.
• Knower and known are independent, a dualism. • Knower and known are interactive, inseparable.
• Primacy of method • Primacy of subject matter
• Variables can be identified and relationships measured • Variables are complex, interwoven, and difficult to measure.
• Inquiry is objective, value-free. • Inquiry is subjective, value-bound.
Purposes Purposes
• Generalisability (Time and context free generalisations through • Contextualisation (Only time and context bound working hypotheses
nomothetic or generalised statements) through idiographic statements)
• Prediction • Interpretation
• Causal explanations • Understanding actors’ perspectives
Approach Approach
• Begins with hypotheses and theories • Ends with hypotheses or grounded theory
• Manipulation and control • Emergence and portrayal
• Uses formal, structured instruments • Researcher as the instrument
• Experimentation and intervention • Naturalistic or nonintervention
• Deductive • Inductive
• Component analysis • Searches for patterns
• Seeks consensus, the norm • Seeks pluralism, complexity
• Reduces data to numerical indices • Makes minor use of numerical indices
• Abstract language in write-up • Descriptive write-up

Researcher Role Researcher Role
• Detachment and impartiality • Personal involvement and partiality
• Objective portrayal • Empathic understanding
• Etic (outsider’s point of view) • Emic (insider’s point of view)
Source: Adapted from Glesne & Peshkin (1992); Lincoln & Guba (1985).
Kaya Yilmaz 315
information about the research topic studied (Denzin & Lincoln, 1998; Patton,
2002; Wolcott, 1994).
Methods of data collection and analysis are also different in the two
approaches. Quantitative research uses questionnaires, surveys and systematic
measurements involving numbers. Quantitative researchers use mathematical
models and statistics to analyse the data and report their findings in impersonal,
third-person prose by using numbers. In contrast, qualitative research uses par-
ticipants’ observation, in-depth interviews, document analysis, and focus groups.
The data are usually in textual, sometimes graphical or pictorial form. Qualitative
researchers disseminate their findings in a first-person narrative with a combina-
tion of etic (outsider or the researcher’s) and emic (insider or the participants’)
perspectives (Denzin & Lincoln, 1998; Miles & Huberman 1994). Since qualita-
tive findings are highly context and case dependent, researchers are expected to
keep findings in context and report any personal and professional information that
may have an impact on data collection, analysis, and interpretations. Bracketing
their points of view and biases, the researchers must avoid making any judgement
about whether the situation in which they are involved and participants are
engaged is good or bad, appropriate or inappropriate. In addition, researchers
should make their orientation, predispositions, and biases explicit. Lastly, qualita-
tive research reports must provide the reader with sufficient quotations from
participants (Patton, 2002).
There are some situations or questions that qualitative research methods illus-
trate better than quantitative ones or vice versa. For instance, qualitative methods
are especially effective to study a highly individualised programme in which learn-
ers who have different abilities, needs, goals, and interests proceed at their own
pace. In this case, quantitative methods can provide parsimonious statistical data
through mean achievement scores and hours of instruction. But, in order to
understand the meaning of the programme for individual participants, their points
of view and experiences should be illustrated with their own words via such
qualitative methods and techniques as case studies and interviews which provide
the detailed, descriptive data needed to deepen our understanding of individual
variation. On the other hand, some situations require quantitative research design
to be effectively addressed. For example, quantitative methods are more helpful
when conducting research on a broader scale or studying a large number of people,
cases, and situations since they are cost-effective and statistical data can provide a
succinct and parsimonious summary of major patterns (Patton, 2002).
More Elaboration on Qualitative Research

The quantitative research paradigm has been practised for a long time, so its
defining characteristics are well known. But that is not the case for qualitative
research design. Hence, more elaboration is needed to illustrate its distinctive
features. The post-positivist, post-structural, constructionist, and critical para-
digms lay the bases for the ontological, epistemological, and methodological underpin-
nings of qualitative research design. The qualitative inquiry is identified with a
relativist ontology (the notion of multiple realities is accepted), a subjectivist
epistemology (the idea that understandings are created through interaction
between the knower and the unknown or subject), and a naturalistic (subjects are
studied in their natural settings) set of methodological procedures (Denzin &
Lincoln, 1998, p. 27). Creswell (2007) adds two more philosophical assumptions

to qualitative research.These are axiological (the idea that no research endeavour is

value-free in that researchers brings their values to what is researched) and rhe-
torical (the language of research is subjective in the form of first person account)
assumptions (p. 17). Philosophical assumptions of qualitative research are given in
Table II.
TABLE II. Basic Set of Beliefs or Philosophical Assumptions about

Characteristics of Qualitative Research
Assumptions Questions Characteristics Implications for Practice
(Examples)
Ontological What is the Reality is subjective and Researcher uses quotes and
nature of multiple, as seen by themes in words of
reality? participants in the study participants and provides
evidence of different
perspectives
Epistemological What is the Researcher attempts to lessen Researcher collaborates,
relationship distance between himself or spends time in field with
between the herself and that being participants, and becomes
researcher researched an ‘insider’
and that
being
researched?
Axiological What is the role Researcher acknowledges that Researcher openly discusses
of values? research is value laden and values that shape the
that biases are present narrative and includes his
or her own interpretation
in conjunction with the
interpretations of
participants
Rhetorical What is the Researcher writes in a Researcher uses an engaging
language of literary, informal style using style of narrative, may use
research? the personal voice and uses first-person pronoun, and
qualitative terms and employs the language of
limited definitions qualitative research
Methodological What is the Researcher uses inductive Researcher works with
process of logic, studies the topic particulars (details) before
research? within its context, and uses generalisations, describes
an emerging design in detail the context of the
study, and continually
revises questions from
experiences in the field
Source: Adapted from Creswell (2007).
Even though the qualitative research tradition is coloured by diversity of different

and sometimes conflicting philosophical assumptions, theoretical lens, and prac-
tical considerations, the essence of its design as commonly agreed by researchers
can be summarised as follows:
• Qualitative research design assumes that knowledge is not independent of the
knower, but socially constructed and that reality is neither static nor fixed. Since
there are multiple realities that different cultural groups construct on the basis
of their world views or value systems, there are multiple interpretations or
perspectives on any event or situation. So, understanding the phenomenon

Kaya Yilmaz 317
under investigation from the perspectives of the participants involved is

essential.
• It is holistic, flexible or emergent. It looks at the larger picture or process,
searching for an understanding of the whole over time.
• It seeks answers to ‘what’, ‘how’ and ‘why’ questions in terms of quality rather
than quantity, amount, intensity, or frequency.
• It postulates that events, cases, processes, situations, individuals and their
behaviours are unique, context-dependent and largely non-generalisable.
Hence, what is needed is not reductionism but ‘thick description’ of purpose-
fully selected small samples or cases.
• It stipulates that people are intentional and creative in their actions, actively
construct their social world, and make meanings in and through their activities.
People interpret events, contexts and situations, and act on the basis of those
events.
• It looks at relationships within a system or culture or face-to-face interactions
among people in a given social setting. It emphasises the importance of under-
standing a given social setting rather than making predictions about that setting.
• It assumes that events, processes, situations and behaviours change over time
and are affected by context.
• It requires researchers to stay in the setting over a substantial period and urges
them to develop a model of what occurred in the social setting.
• It requires the researcher to become the research instrument. Hence, the
researcher must be able to observe behaviour and interview people face-to-
face. The researcher should establish close contact with the research partici-
pants when collecting data which need to be detailed, rich, complex, and
extensive.
• It demands time in analysis that is equal to the time in the field, calling for
ongoing analyses of the data. The bottom-up approach to data analysis with
open coding strategies should be practised to allow themes and patterns to
emerge from data.
• It involves informed consent decisions and is responsive to ethical concerns.
• It incorporates room for description of the role of the researcher as well as
description of the researcher’s own biases and ideological preference (Cohen,
Manion, & Marrison, 2007, p. 21; Creswell, 2009, pp. 175–176, 195; Denzin &
Lincoln, 1998, p. 42; Snape & Spencer, 2003, p. 5).
Issues Related to Criteria for Evaluating Research: Reliability and

Validity
Because quantitative and qualitative researchers differ in terms of their approach to
defining the concepts of reliability and validity (or determining the criteria for
evaluating the quality of a research study), the definition and meaning of these
terms for both research designs are explained in separate sections.
Reliability and Validity in Quantitative Research

Reliability means consistency or the degree to which a research instrument meas-
ures a given variable consistently every time it is used under the same condition
with the same subjects. It is important to note that reliability applies to data not to
measurement instruments. From different perspectives or approaches, researchers
can evaluate the extent to which their instruments provide reliable data. Types of

reliability can be briefly explained as follows (Huck, 2000; Keppel, 1991;Trochim,

2005):
Test-retest reliability refers to the extent that the same test administered by the
researcher to a single group of subjects on two different occasions gives highly
positively correlated results. Two sets of scores from the same test should be
correlated for the researcher to claim they are consistent (i.e. assessment of the
stability of the instrument over time). Parallel forms reliability demonstrates
whether two forms of the same instrument administered to the same group of
people to measure the same characteristic such as intelligence give highly posi-
tively correlated results. The researcher examines whether there is a consistency
between the scores obtained for any examinee across the two settings (i.e. the
degree of equivalence across forms). Internal consistency reliability indicates
whether measuring instruments possess internal consistency or the results of the
instrument administered to a group of people on one occasion correlate very
positively. There should be consistency across the parts of a measuring instru-
ment or subsets of questions. To judge that the full instrument possesses high
internal consistency reliability, the researcher determines the extent to which
parts of a test hang together and measure the same thing. Inter-rater (Inter-
observer) reliability refers to the process whereby the researcher gathers data by
asking raters to evaluate a set of objects, pictures etc., and then quantifies the
degree of consistency among the raters. To that end, the researcher computes an
index of interrater reliability.
Validity refers to the accuracy of research data. A researcher’s data can be said
to be valid if the results of the study measurement process are accurate. That is, a
measurement instrument is valid to the degree that it measures what it is supposed
to measure. There are different types of validity. Internal validity refers to whether
there is a causal relationship between the treatment and the outcome. External
validity reflects the degree to which one can generalise research results or the
effects of the treatment beyond the present conditions of testing; that is, other
settings, programmes, persons, places, times, cases, or approaches. Construct valid-
ity refers to the degree to which conclusions can be made from the operationali-
sations of a study to the theoretical constructs on which operationalisations are
based. In other words, the treatment or the programme should reflect the construct
on which they are based. For instance, if the study examined the effects of
simulation or role playing on students’ ability to empaphise with historical agents,
the treatment (simulation) should accurately reflect the construct of simulation,
and the measured outcome (historical outcome) should reflect the construct of
historical empathy. Conclusion validity indicates whether there is a relationship
between the independent variable and the dependent variable or outcome (Huck,
2000; Keppel, 1991).
Reliability and Validity in Qualitative Research

Rather than using quantitative researchers’ jargons, qualitative researchers prefer
to use their own terms to communicate what is meant by reliability, validity, and
objectivity in quantitative language. Some researchers have even argued that deter-
mining the quality of qualitative studies via quantitative concepts or measures such
as reliability and validity is not only irrelevant but also misleading (Creswell, 2009,
p. 190; Davies & Dodd, 2002, p. 280; Steinke, 2004, p. 186; Stenbacka, 2001,
p. 551). Since qualitative research is focused on meaning and interpretation in

Kaya Yilmaz 319
cases which are unique and context-bound, ‘traditional thinking about generaliz-
ability falls short . . . and reliability in the traditional sense of replicability is
pointless’ (Denzin & Lincoln, 1998, p. 51). It is believed that because ontological,
epistemological, and theoretical assumptions of qualitative research are so funda-
mentally different from those of quantitative research, it should be judged on its
own terms. Hence, it is proposed that rather than the concepts of validity and
reliability, an alternative set of criteria based on qualitative concepts need to be
used to judge the trustworthiness of a qualitative research which needs its own
criteria for evaluation (Gibbs, 2007; Lincoln & Guba, 1985; Wolcott, 1994).
The concept of validity in quantitative study corresponds to the concept of
credibility, trustworthiness, and authenticity in qualitative study which means that the
study findings are accurate or true not only from the standpoint of the researcher
but also from that of the participants and the readers of the study (Creswell &
Miller, 2000). The concept of reliability in quantitative study is comparable, but
not identical, with the concept of dependability and auditability in qualitative study,
which means that the process of the study is consistent over time and across
different researchers and different methods or projects (Gibbs, 2007; Miles &
Huberman, 1994). To judge the quality or (a) credibility and (b) dependability of
a qualitative study, the following questions compiled from various studies can be
asked (Miles & Huberman, 1994, pp. 278–279):
Credibility (instead of validity) questions:
• How context-rich and detailed are the basic descriptions?
• Does the account ‘ring true’, make sense, seem convincing or plausible, enable
a ‘vicarious presence’ for the reader?
• Is the account rendered comprehensive, respecting the configuration and tem-
poral arrangement of elements in the local context?
• Did triangulation among complementary methods and data sources generally
lead to converging conclusions? If not, is there a coherent explanation for this?
• Are the presented data linked to the categories of prior or emergent theory if
used?
• Are the findings internally coherent and concepts systematically related?
• Were guiding principles used for confirmation of propositions made explicit?
• Are areas of uncertainty identified?
• Was negative case or evidence sought for? Found? What happened then?
• Have rival explanations been actively considered? What happened to them?
• Were the conclusions considered to be accurate by the participants involved in
the study? If not, is there a coherent explanation for this?
Dependability (instead of reliability) questions:
• Are research questions clearly defined and the features of the study design
congruent with them?
• Are basic paradigms and analytic constructs clearly specified?
• Are the researcher’s role and status within the site explicitly described?
• If multiple field-researchers are involved, do they have comparable data collec-
tion protocols?
• Do multiple observers’ accounts converge, in instances, settings, or times when
they might be expected to?
• Were data connected across the full range of appropriate settings, times,
respondents suggested by the research questions?

• Were coding checks made and did they show adequate agreements?
• Were data quality checks for bias, deceit, informant knowledgeability etc.
made?
• Do findings show meaningful parallelism across data sources (informants,
contexts, and times)?
• Were any forms of peer or colleague review employed?
Lincoln and Guba are commonly acknowledged to have made a great contribution
to the criteria debate in qualitative research by developing parallel criteria to the
concepts of validity and reliability (Spencer et al., 2003). Their alternative criteria
are constantly cited in the research literature and still considered to be the yard-
stick or the ‘gold standard’ (Spencer et al., 2003; Whittemore, Chase & Mandle,
2001).To assess the rigour of qualitative research, Lincoln and Guba (1985) resort
to the concepts of credibility, transferability, dependabilty, and confirmability to
express the quantitative concepts of internal validity, external validity (generalis-
ability), reliability, and objectivity respectively. Credibility means that the partici-
pants involved in the study find the results of the study true or credible.
Transferability is achieved if the findings of a qualitative study are transferable to
other similar settings.Thick description of the setting, context, people, actions, and
events studied is needed to ensure transferability or external validity in quantitative
terms. The study has dependability (reliability) if the process of selecting, justifying
and applying research strategies, procedures and methods is clearly explained and
its effectiveness evaluated by the researcher and confirmed by an auditor, which is
called ‘audit trail’. The study enjoys confirmability when its findings are based on
the analysis of the collected data and examined via an auditing process, i.e. the
auditor confirms that the study findings are grounded in the data and inferences
based on the data are logical and have clarity, high utility or explanatory power
(Table III).
TABLE III. Criteria for Judging the Quality of a Research Study: Quantitative
vs. Qualitative Terms
Aspect Quantitative terms Qualitative terms
Truth value Internal validity Credibility

Applicability External validity or generalizability Transferability
Consistency Reliability Dependability
Neutrality Objectivity Confirmability
Source: Adapted from Lincoln and Guba (1985).
Incorporated to these concepts by Guba and Lincoln (1989) in their discussion of

the issues related to validity and reliability are fairness (the various perspectives of
all participants should be given equal consideration), educative authenticity (the
study enables the participants to educate themselves by raising their conscious-
ness), catalytic authenticity (the study encourages activity and decision making),
and empowerment (the study promotes the participants’ ability to make choices
about their professional activity).
In short, terms such as credibility, trustworthiness, authenticity, neutrality
or confirmability, dependability, applicability or transferability and the like are
those that qualitative researchers use most in their discussion of the concepts of

Kaya Yilmaz 321
reliability and validity1. Patton (2002) argues that judging ‘quality’ constitutes the
foundation for perceptions of credibility. Issues related to quality and credibility
correspond to the audience and intended inquiry purposes. Therefore, the criteria
for judging quality and credibility depend on the philosophical underpinnings,
theoretical orientations, and purposes of a particular qualitative research. Taking
this crucial point into account, Patton (2002, pp. 542–544) suggests alternative
sets of five criteria for judging the quality or credibility of a qualitative inquiry: (1)
traditional scientific research criteria, (2) social construction and constructivist
criteria, (3) artistic and evocative criteria, (4) critical change criteria, and (5)
evaluation standards and principles (Table IV).
The credibility of a qualitative study is affected by the extent to which system-
atic data collection procedures, multiple data sources, triangulation, thick and rich
description, external reviews or member checking, external audits, and other
techniques for producing trustworthy data are used. According to Patton (2002),
three distinct but related inquiry elements determine the credibility of a qualitative
research:
(1) rigourous methods to do fieldwork that yield high-quality data that
are systematically analysed with attention to issues of credibility; (2) the
credibility of the researcher, which is dependent on training, experience,
track, record, status, representation of self; and (3) philosophical beliefs in the
value of qualitative inquiry, i.e. an appreciation of naturalistic inquiry, quali-
tative methods, inductive analysis, purposeful sampling, and holistic thinking
(pp. 552–553).
For a qualitative study to be credible and trustworthy, the data must first and
foremost be sufficiently descriptive and include a great deal of pure description of
people, activities, interactions, and settings so that the reader or reviewer can
understand what occurred and how it occurred. The basic criterion to judge the
credibility of data is the extent to which they allow the reader to enter the situation
or setting under study. In other words, rich and detailed or thick description of the
setting and participants is a must.The researcher must provide an accurate picture
of the empirical social world as it exits to those under investigation, rather than as
he or she imagines it to be. The descriptions must be factual, accurate, detailed
but without being overburdened with irrelevant information or trivia. In addition,
researchers should overtly reveal the biases they bring to the study and discuss
how their background such as gender, ethnicity, disciplinary orientation and ideo-
logical viewpoint affected the interpretation of the findings. Since the nature of
qualitative inquiry is fundamentally people-oriented, qualitative researchers must
get close enough to the people and situation being studied in order to capture
what actually takes place and what people actually say; i.e. develop an in-depth
understanding of the phenomenon under investigation. To that end, they should
spend prolonged time in the setting with the participants without dismissing the
negative or discrepant cases observed in the setting. Member checking (the partici-
pants check and evaluate the final research report to determine if its descriptions
and themes accurately reflect their viewpoints), peer debriefing (involving another
researcher in reviewing the study report to see if it fits or resonates with the
experience of both the participants and the audience rather than the researcher),
and external auditor (an independent researcher who, unlike the peer debriefer, is
not familiar with the researcher, reviews the study project to evaluate its accuracy)

TABLE IV. Criteria for Judging the Quality and Credibility of Qualitative
Inquiry
Traditional Scientific Research Criteria
䊏 Objectivity of the inquirer [attempts to minimise bias]
䊏 Validity of the data
䊏 Systematic rigour of fieldwork procedures
䊏 Triangulation [consistency of findings across methods and data sources]
䊏 Reliability of coding and pattern analysis
䊏 Correspondence of findings to reality
䊏 Generalisability [external validity]
䊏 Strength of evidence supporting causal hypothesis
䊏 Contributions to theory
Construction and Constructivist Criteria
䊏 Subjectivity acknowledged [discusses and takes into account biases]
䊏 Trustworthiness and authenticity
䊏 Triangulation [capturing and respecting multiple perspectives]
䊏 Reflexivity and praxis
䊏 Particularity [doing justice to the integrity of unique cases]
䊏 Enhanced and deepened understanding [Verstehen]
䊏 Contributions to dialogue
Artistic and Evocative Criteria
䊏 Opens the world to us in some way
䊏 Creativity
䊏 Aesthetic quality
䊏 Interpretive vitality
䊏 Flows from self; embedded in lived experience
䊏 Stimulating
䊏 Provocative
䊏 Connects and moves the audience
䊏 Voice distinct and expressive
䊏 Feels true, authentic or real
Critical Change Criteria
䊏 Critical perspective: Increases consciousness about injustice
䊏 Identifies nature and sources of inequalities and injustice
䊏 Represents the perspective of the less powerful
䊏 Makes visible the ways in which those with more power exercise and benefit from this power
䊏 Engages those with less power respectfully and collaboratively
䊏 Builds the capacity of those involved to take action
䊏 Identifies change-making strategies
䊏 Clear historical and values context
Evaluation Standards and Principles
䊏 Utility
䊏 Feasibility
䊏 Propriety
䊏 Accuracy [balance]
䊏 Systematic inquiry
䊏 Evaluator competence
䊏 Integrity/honesty
䊏 Respect for people [fairness]
䊏 Responsibility to the general public welfare [taking into account diversity of interests and
values]
Source: Adapted from Patton (2002).

Kaya Yilmaz 323
should be employed as verification strategies to ensure the accuracy of the

account. Because only one research method is unlikely to adequately address the
problem of rival explanations, employing multiple data collection methods to
study the same setting, issue, or programme increases the credibility of the find-
ings by eliminating or reducing errors linked to a particular method. Thus, trian-
gulation or combination of interviewing, observation, and document analysis
contributes to a rigorous qualitative research study. Five types of triangulation
enhance verification of qualitative analysis, adding depth and breadth to under-
standing of the issue under investigation.These are methods triangulation, sources
triangulation, analyst triangulation, theory/perspective triangulation, and meth-
odological triangulation, all of which together enable the researcher to gain a
broader and deeper understanding of the research issue (Creswell, 2009; Denzin
& Lincoln, 1994; Patton, 2002).
Corbin and Strauss (2008) identify certain research situations and conditions
that affect the quality of a qualitative study. These are methodological consistency,
methodological awareness, clarity about the purpose of the study, having training
in qualitative research tradition, self-awareness about one’s biases and assump-
tions, creativity and openness to new ideas, sensitivity for the research including
the research data and the participants, and a willingness to do research for its own
sake and to work hard (pp. 302–304).
Conclusion
Educational researchers, especially graduate students, need to acquaint them-
selves with different research approaches. Quantitative and qualitative research
approaches represent the two ends of the research continuum. They differ in
terms of their epistemological assumptions, theoretical frameworks, methodo-
logical procedures and research methods. Whereas the former is based on posi-
tivism or objective epistemology, relies on quantitative measures for collecting
and analysing data, and aims to make predictions and generalisations, the latter
is based on constructivism, draws on naturalistic methods for data collection and
analysis, and aims to provide an in-depth understanding of people’s experiences
and the meanings attached to them. Having been viewed not only as competitive
but also incompatible research paradigms for some decades, they are now con-
sidered as alternative strategies for research. Both approaches have their
own strengths and weaknesses in their design and application. Which approach
should be used when planning a research depends on several factors such as
the type of questions asked, the researcher’s training or experinces, and the
audience.
Kaya Yilmaz, Marmara University, Ataturk Faculty of Education, Department of
Elementary Education, Kadikoy, Istanbul, Turkey, kaya.yilmaz@marmara.edu.tr
NOTE
1. However, the term validity is used by some researchers in relation to qualita-
tive research. Schwandt (1997) defines validity as the extent to which the
qualitative account accurately represents the research participants’ views of
social phenomena and is credible to them. Likewise, reliability is defined as
the extent to which the qualitative study provides an ‘understanding’ of a
situation, setting, case, programme, or event that otherwise would be confusing

and enigmatic (Eisner, 1991, p. 58). Lincoln and Guba (1985) use the concept
of dependability to refer to reliability in quantitative studies (p. 300).
REFERENCES
BERGMAN, M. M. (2008) Advances in Mixed Methods Research (Los Angeles,
Sage).
BREWER, J. D. (2003) Qualitative research, in: R. L. MILLER & J. D. BREWER (Eds)
The A-Z of Social Research: a dictionary of key social science research concepts
(pp. 238–241) (Thousand Oaks, Sage).
BRYMAN, A. (1988) Quantity and Quality in Social Research (London, Routledge).
COHEN, L., MANION, L. & MARRISON, K. (2007) Research Methods in Education
(6th edition) (New York, Routledge).
CORBIN, J. & STRAUSS, A. (2008). Basics of Qualitative Research: techniques and
procedures for developing grounded theory (3rd edition) (Thousand Oaks, Sage).
CRESWELL, J. W. (1994) Research Design: qualitative & quantitative approaches
(Thousand Oaks, Sage).
CRESWELL, J.W. (2007) Qualitative Inquiry and Research Design: choosing among five
traditions (2nd edition) (Thousand Oaks, Sage).
CRESWELL, J. W. (2009) Research Design: qualitative, quantitative and mixed
approaches (3rd edition) (Thousand Oaks, Sage).
CRESWELL, J.W. & MILLER, D. (2000) Determining validity in qualitative inquiry,
Theory into Practice, 39, pp. 124–130.
CROTTY, M. (1998) The Foundations of Social Research: meaning and perspective in
the research process (Thousand Oaks, Sage).
DAVIES, D. & DODD, J. (2002) Qualitative research and the question of rigor,
Qualitative Health Research, 12, pp. 279–289.
DENZIN, N. K. & LINCOLN, Y. S. (1994) Introduction: entering the field of
qualitative research, in: N. K. DENZIN & Y. S. LINCOLN (Eds) Handbook
of Qualitative Research (pp. 1–17) (London, Sage).
DENZIN, N. K. & LINCOLN, Y. S. (1998). Strategies of Qualitative Inquiry
(Thousand Oaks, Sage).
DENZIN, N. K. & LINCOLN, Y. S. (2005) Handbook of Qualitative Research (3rd
edition) (Thousand Oaks, Sage).
EISNER, E.W. (1991) The Enlightened Eye: qualitative inquiry and the enhancement of
educational practice (New York, NY, Macmillan Publishing Company).
GAY, L. R. & AIRASIAN, P. (2000) Educational Research: competencies for analysis and
application (6th edition) (Upper Saddle River, Prentice Hall).
GELO, O., BRAAKMANN, D. & BENETKA, G. (2008) Quantitative and qualitative
research: beyond the debate, Integrative Psychological Behavioral Science, 42,
pp. 266–290.
GIBBS, G. R. (2007) Analyzing qualitative data, in: U. FLICK (Ed) The Sage
Qualitative Research Kit (London, Sage).
GLESNE, C. & PESHKIN, A. (1992) Becoming Qualitative Researchers: an introduction
(New York, Longman).
GUBA, E. & LINCOLN, Y. (1989) Fourth Generation Evaluation (Newbury Park,
Sage).
HITCHCOCK, G. & HUGHES, D. (1995) Research and the Teacher: a qualitative
introduction to school-based research (2nd edition) (London, Taylor & Francis).

Kaya Yilmaz 325
HUCK, S. W. (2000) Reading Statistics and Research (3rd edition) (New York,
Longman).
KEPPEL, G. (1991) Design and Analysis: a researchers’ handbook (Upper Saddle
River, Prentice Hall).
LINCOLN, Y. S. & GUBA, E. G. (1985) Naturalistic Inquiry (Newbury Park,
Sage).
MILES, M. & HUBERMAN, M. (1994) Qualitative Data Analysis (2nd ed) (Thou-
sand Oaks, Sage).
PATTON, M. Q. (2002) Qualitative Research & Evaluation Methods (3rd Edition)
(Thousands Oaks, Sage).
SCHWANDT, T. A. (1997) Qualitative Inquiry: A dictionary of terms (Thousand
Oaks, Sage).
SNAPE, D. & SPENCER, L. (2003) The foundations of qualitative research, in:
J. RITCHIE & J. LEWIS (Eds) Qualitative Research Practice: a guide for social
science students and researchers (pp. 1–23) (Thousand Oaks, Sage).
SPENCER, L., RITCHIE, J., LEWIS, J. & DILLON, L. (2003) Quality in Qualitative
Evaluation: a framework for assessing research evidence (London, National Centre
for Social Research, Government Chief Social Researcher’s Office).
STEINKE, I. (2004) Quality criteria in qualitative research, in: U. FLICK, E. V.
KARDORFF & I. STEINKE (Eds) A Companion to Qualitative Research
(pp. 184–190) (Thousand Oaks, Sage).
STENBACKA, C. (2001) Qualitative research requires quality concepts of its own,
Management Decision, 39, pp. 551–555.
STRAUSS, A. L. & CORBIN, J. (1998) Basics of Qualitative Research: techniques and
procedures for developing grounded theory (2nd edition) (Thousand Oaks, Sage).
TROCHIM, W. M. (2005) Research Methods Knowledge Base. www.socialresearch
methods.net/kb
WHITTEMORE, R., CHASE, S. K. & MANDLE, C. L. (2001) Validity in qualitative
research, Qualitative Health Research, 11, pp. 522–537.
WOLCOTT, H. F. (1994) Transforming Qualitative Data: description, analysis,
interpretation (Thousand Oaks, Sage).

M9. Quantitative and Qualitative Data
Quantitative data involves expressing data statistically or numerically, such as counting the
number of crimes each year. Such data is usually expressed in one of three ways:
▪ Numbers (sometimes called raw numbers). For example, the total number of people who live in
poverty.
▪ Percentages: the number per 100 in a population. For example, 30% of British voters regularly
vote Conservative.
▪ Rates: the number per 1000 in a population. For example, if the birth rate in Britain was 1 (it’s
not...) for every 1000 people one baby is born each year.
Research data is often expressed as a rate or percentage because it allows accurate comparisons
between and within groups and societies. For example, comparing unemployment between Britain
and America as a raw number wouldn’t tell us very much, since the population of America is
roughly 5 times larger. Expressing unemployment as a percentage or rate on the other hand
allows us to compare "like with like”.
Strengths Matveev (2002) notes the ability to control the
conditions under which data is collected (such
The ability to express relationships numerically as using standardised questionnaires) makes
can be useful if the researcher doesn’t need to quantitative data more reliable. Where the
explore the reasons for behaviour. If you simply same questions are asked of different groups -
want to know how many murders there are per or the same group at different times - we can
year quantitative data satisfies this purpose. be sure that any differences in their answers
are not down to being asked different
Quantitative data lends itself to statistical questions.
comparisons. This is useful for things like
hypothesis testing or cross-cultural The ability to replicate quantitative research
comparisons (such as crime rates in different also means it is likely to be highly reliable and
countries). where the researcher has no direct, necessary
and personal involvement with the generation
Kruger (2003) of data it makes it less-likely for personal biases
Longitudinal studies, where the same group to intrude into the research process.
may be researched at different times to track
changes in their behaviour, can exploit this Kealey and Protheroe (1996), for example,
comparative feature of quantitative data. suggest the ability to “eliminate or minimize
subjective judgments” is a major contributory
Quantitative methods and data “allow us to factor to increased data reliability.
summarize vast sources of information and
make comparisons across categories and
over time”.
Shortcutstv.com 1
Sociology Research Methods
Limitations
Although the ability to quantify the social world

can be a significant advantage for social
researchers one of the major criticisms of
quantification relates to the validity of the data
collected. This can be exampled in a number of
ways:
1. In order to quantify behaviour people are

frequently placed in artificial, unrealistic,
situations where realism is sacrificed for For this reason there’s little or no opportunity to
control. In their everyday lives, for example, develop the research outside of the original
people rarely encounter situations where parameters decided by the researcher.
they're asked to respond to a list of questions
asked by a stranger. A validity issue here is Although, as a general principle, quantitative
whether a researcher can capture people’s data is usually considered both “highly reliable”
“real beliefs” when they place them in an
artificial situation. Harvey (2002)
“Many apparently quantitative data depend
2. Quantitative methods only capture a critically on the way in which they were
relatively narrow range of data about people's collected, who collected them, where they
behaviour - what Day (1998) calls the: were collected, when they were collected and
from whom they were collected”.
▪ Who?
▪ What?
▪ When? and “more reliable” than qualitative data, this is
▪ Where? not necessarily the case: reliability is not an
automatic quality of any one particular research
3. Following from the above, quantitative data method.
tells us very little about “The Why?” - The
reasons for people’s behaviour. This is partly a In 2014, for example, the status of Official UK
problem of lack of depth: the more complex the Police-Recorded Crime Statistics was
behaviour, the more difficult it is to quantify. downgraded to “unreliable” by the UK Statistics
Authority based on "accumulating evidence that
This leads to a further criticism that quantitative the underlying data on crimes recorded by the
methods focus on relatively superficial aspects police may be unreliable”.
while failing to address the complexities Sorokin (1956), partly tongue-in-cheek, coined
involved in even very simple forms of the term “Quantophrenia” to refer to a
behaviour. As Kruger (2003) argues, it’s “psychological compulsion to grasp for the
“difficult to get the real meaning of an issue by numeric” - a “condition” that leads to the use of
looking at numbers”. quantification for its own sake, regardless of
whether or not it tells us anything useful or
For McCullough (1988) a significant interesting about the behaviour being
methodological limitation is the fact “Issues are quantified.
only measured if they are known prior to the
beginning of the survey” As Eberstadt (2006) puts it, the “victims” of this
condition “obsess over numbers as descriptors,
In other words, in order to quantify behaviour no matter how dubious their basis or
the researcher must decide, in advance of their questionable their provenance”.
research, what is and what is not significant in
relation to the behaviour being studied.
Shortcutstv.com 2
Qualitative data tries to capture the quality of people’s behaviour and such data says something
about how people experience the social world. It can be used to understand the meanings they
give to behaviour.
Boyle (1977), for example, studied the behaviour of a juvenile gang from the viewpoint of its
members while Goffman (1961) tried to understand the experiences of patients in an American
mental institution.
Both were trying to capture and express how people feel about and react to different situations.
Strengths 2. Where the atmosphere is more-relaxed and

less clinical the researcher is more likely to get
Where a research objective is to understand respondents to open-up about their thoughts
the meaning of people’s behaviour, they must and feelings - something that may improve
be allowed the scope to talk freely. Qualitative research validity.
data encourages this because a researcher
doesn't impose their interpretation on a In this respect although qualitative methods
situation (by asking direct, quantifiable, don't have a monopoly on validity (any poorly-
questions for example). designed research can lack validity regardless
of the methods used) but when dealing with the
Qualitative data provides greater depth and complexities of human behaviour it is much
detail about behaviour since, as Day (1998) more likely research methods that dig into this
suggests, they are concerned with discovering complexity will produce highly-valid data: they
“the Why?” - the reasons for such behaviour; will measure what they claim to measure.
because qualitative methods draw-out the
complex reasons for social behaviour it follows Qualitative methods allow researchers greater
they are likely to involve digging more deeply freedom to study people in their “everyday” or
into people’s beliefs and behaviours. “normal” settings and this gives a greater
chance of collecting rich data about what
Qualitative methods avoid the problem of the people “really believe” or how they “really
researcher pre-judging what is and what is not behave”. As Matveev (2002) suggests,
significant data prior to starting their research. qualitative methods produce data that allow the
Where the research objective is to describe or researcher to gain a “more realistic feel of the
draw out people’s opinions and reasons the world that cannot be experienced in the
respondent, rather than the researcher, is numerical data and statistical analysis used in
effectively the driving-force: they lead and the quantitative research”.
researcher follows. Respondents may talk
about things they see as significant and take
the research into directions and places the
researcher had not originally considered.
Many qualitative methods demand the

researcher establish a close relationship with
respondents (which doesn’t mean they have to
like them, only understand them). The
development of a research rapport has a
couple of advantages:
1. Everyone involved in the research is free to

suggest new ideas and directions - the role of
the respondent isn’t limited to answering
questions.
Shortcutstv.com 3
Limitations 1. Which data to keep and which to discard?
Where qualitative research generally focuses 2. Different researchers looking at the same
on the intensive study of relatively small data may arrive at different conclusions based
groups, opportunities to generalise research on the data they choose to use
data may be limited.
Levy (2006), however, argues reliability
For similar reasons it’s difficult to compare evidenced through the ability to replicate
qualitative research across time and space research is not a useful test for qualitative
because researchers are unlikely to be research methods. She suggests the concept of
comparing "like with like". trustworthiness might be a more useful
measure of the internal reliability of qualitative
Qualitative data also tends to be structured in methods: “In qualitative research, as there are
ways that make the research difficult to no numerical measures. It is up to the
replicate - a consequence, Cassell and Symon researcher to provide evidence of reliability by
(1994) argue, of the fact that where research carefully documenting the data collection and
evolves to take account of the input of different analysis process, hence “trustworthiness” is
respondents the original research objectives used to assess how reliable the results are.
may change. Can we trust that the results are a ‘true’
reflection of our subject?”.
In general this means qualitative research
generally produce data with lower levels of Qualitative methods require different skills from
reliability. While all data, quantitative as well as the researcher to those required of a
qualitative, requires interpretation by the quantitative researcher and this means
researcher, qualitative methods - from qualitative data may be harder to collect. In
participant observation to unstructured something like observational research, for
interviews - tend to produce vast amounts of example, the researcher needs to be able to
data across a wide range of issues. This raises convincingly and consistently “play a role”
two potential reliability issues: within the group they are studying - a very
different set of skills to those needed to deliver
a questionnaire or structured interview.
Quantitative and Qualitative
Although we’ve considered quantitative and qualitative data as separate entities, there are
occasions when a researcher may want to combine quantitative and qualitative types of data,
such as collecting quantitative data about educational achievement or the number of people
who visit their doctor each year alongside qualitative data that seeks to explore the satisfaction
levels of pupils or patients.
This technique is called methodological triangulation and is one that can also be used to
improve both research validity - by creating a more-accurate measurement of something - and
reliability by using the strengths of one type of data (the ability to quantify behaviour, for
example) to offset the weaknesses of the other.
Alternatively, quantitative data is sometimes collected before starting qualitative research. A

researcher looking at reasons for school truancy, for example, may firstly carry-out a
quantitative analysis to discover whether or not pupils are actually absent from the classroom. A
quantitative enabling study can be used to establish whether or not there is anything for the
researcher to qualitatively investigate…
Shortcutstv.com 4
A HANDBOOK OF STATISTICS Describing Data Sets
3 DESCRIBING DATA SETS

Populations can be very large and the data that we can collect on populations is even larger
than the population itself because of the number of variables we collect on each population
member. For instance, credit bureaus collect credit data on every credit eligible person in the
United States. An online shopping hub such as Amazon.com, collects data on not just every
purchase you make, but every product that you click on. The ability to amass such large
amounts of data is a great thing for individuals who use data to run their business or study
policy. They have more information with which to base their decisions on. However, it is
impossible for most humans to be able to digest it in its micro form. It is more important
to look at the big picture than it is to look at every element of data that you collect.
Statisticians can help out decision makers by summarizing the data. Data is summarized
using either graphical or numeric techniques. The goal of this chapter is to introduce these
techniques and how they are effective in summarizing large data sets. The techniques shown
in these chapters are not exhaustive, but are a good introduction to the types of things that
you can do to synthesize large data sets. Different techniques apply to different types of data,
so the first thing we must do is define the two types of data that we encounter in our work.
Quantitative and qualitative data/variables (introduced in chapter 1) are the two main types
of data that we often deal with in our work. Qualitative variables are variables that cannot
be measured on a natural numerical scale. They can only be classified into one of a group
of categories. For instance, your gender is a qualitative variable since you can only be male
or females (i.e. one of two groups). Another example might be your degree of satisfaction
at a restaurant (e.g. “Excellent”, “Very Good”, “Fair”, “Poor). A quantitative variable is a
variable that is recorded on a naturally occurring scale. Examples of these might be height,
weight, or GPA. The technique that we choose to summarize the data depends on the type
of data that we have.
3.1 SUMMARIZING QUALITATIVE DATA

The first technique that we will look that summarizes qualitative data is known as a
frequency table. The frequency table provides counts and percentages for qualitative data
by class. A class is one of the categories into which qualitative data can be classified. The
class frequency is the number of observations in the data set falling into a particular class.
Finally, the class relative frequency is the class frequency divided by the total number of
observations in the data set.

18
We can illustrate the frequency table using a simple example of a data set that consists of
three qualitative variables: gender, state, and highest degree earned.
• Gender, needs no explanation, one can be either male or female.

• The variable state is the state (e.g. Virginia, Maryland) that the person lives in.
• Finally, the highest degree earned is the highest degree that a person in our data
set has earned.
Let’s say that this data set is 20 small business owners.
ID Gender State Highest Degree Earned
1 M VA Law
2 M MD Law
3 M IA PhD
4 F ID HS Degree
5 F VA MBA
6 M MD BA
7 M DC MS
8 F CA MBA
9 F CA MBA
10 F MD MS
11 F VA MS
12 M IA MS
13 M AK MBA
14 M AK MBA
15 M AR MBA
16 F AK MBA
17 F DC PhD
18 F MD PhD
19 F MD Law
20 M VA Law
Frequency Table for Highest Degree Earned

19
Class Class Frequency Relative Frequency
BA 1 5.00%
HS Degree 1 5.00%
Law 4 20.00%
MBA 7 35.00%
MS 4 20.00%
PhD 3 15.00%
Grand Total 20 100.00%
The table below the raw data summarizes the data by the variable “Highest Degree Earned”.
The first column shows the different levels that the variable can take. The second and third
columns show the frequency and relative frequency, respectively for each class. For this
data set, the MBA degree is the most represented degree with 7 individuals holding MBA’s.
Finally, the third column shows the relative frequency, or the percentage of people with that
degree. MBA’s have 35%. The frequency table summarizes the data so that we can better
understand the data set without having to look at every record. Most of our small business
owners have MBA’s with some other advanced degree a close second. In fact, 90% of the
small business owners have some sort of advanced degree.
3.2 GRAPHICAL TECHNIQUES FOR DESCRIBING DATA

The data in the example can also be used to illustrate a pie chart. A pie chart is useful for
showing the part to the whole in a data set. The pie chart is a circular chart that divided
into different pieces that represents the proportion of the class level to the whole.
Highest Degree Earned

BA HS Degree Law MBA MS Phd
5%
5%
15%
20%
20%
35%

20
The pie chart provides the same information that the frequency chart provides. The benefit
is for the individuals who prefer seeing this kind of data in a graphical format as opposed
to a table. Clearly the MBA is most highly represented. Even without the labels, it would
be easy to see that the MBA degree is the most represented in our data set as the MBA is
the largest slice of the pie.
Frequency Histogram
The final type of graph that we will look at in this chapter is the frequency histogram. The
histogram pictorially represents the actual frequencies of our different classes. The frequency
histogram for the “Highest Degree Earned” variable is shown below.
Highest Degree Earned

8
7
7
6
5
4 4
4
3
3
2
1 1
1
0
BA HS Degree Law MBA MS Phd
In the frequency histogram, each bar represents the frequency for each class level. The
graph is used to compare the raw frequencies of each level. Again, it is easy to see that
MBA dominates, but the other higher level degrees (Law, MS, and PhD) are almost equal
to each other.
3.3 MEASURES OF CENTRAL TENDENCY

The central tendency of the set of measurements is the tendency of the data to cluster or center
about certain numerical values. Thus, measures of central tendency are applicable to quantitative
data. The three measures we will look at here are the mean, the median and the mode.
The mean, or average, is calculated by summing the measurements and then dividing by the
number of measurements contained in the data set. The calculation can be automated in excel.
=average()

21
For example, if we have the data points 5,3,8,6 in cells A1:A4
=average(A1:A4) = 5.5
The median of a quantitative data set is the middle number when the measurements are
arranged in ascending or descending order. The formula for the median in Excel is
=median()
Continuing in the above example
=median(A1:A4) = 5.5
The mode is the measurement that occurs most frequently in the data. The mode is the
only measure of central tendency that has to be a value in the data set.
=mode()
Since the mean and median are both measures of central tendency, when is one preferable
to the other? The answer lies with the data that you are analyzing. If the dataset is skewed,
the median is less sensitive to extreme values. Take a look at the following salaries of
individuals eating at a diner.

22
The mean salary for the above is ~$15K and the median is ~$14K. The two estimates are quite
close. However, what happens if another customer enters the diner with a salary of $33 MM.
The median stays approximately the same (~$14K) while the mean shoots up to ~$5MM.
Thus, when you have an outlier (an extreme data point) the median is not affected by it
as much as mean will be. The median is a better representation of what the data actually
looks like.
3.4 MEASURES OF VARIABILITY

Variance is a key concept in statistics. The job of most statisticians is to try to understand
what causes variance and how it can be controlled. Variance can be considered the raw
material in which we do statistical analysis for. Some types of variance that can be considered
as beneficial to understanding certain phenomena. For instance, you like to have variance in
an incoming freshman class as it promotes diversity. However, variance can also negatively
impact your process and it is something you want to control for and eliminate. For instance,
you want to minimize variability in a manufacturing process. All products should look
exactly the same.
The job of a statistician is to explain variance through quantitative analysis. Variance will
exist in manufacturing processes due to any number of reasons. Statistical models and
tests will help us to identify what the cause of the variance is. Variance can exist in the
physical and emotional health of individuals. Statistical analysis is geared towards helping
us understand exactly what causes someone to be more depressed than another person, or
why some people get the flu more than others do. Drug makers will want to understand
exactly where these differences lie so that they can target drugs and treatments that will
reduce these differences and help people feel better.

23
There are several methods available to measure variance. The two most common measures
are the variance and the standard deviation. The variance is simply the average squared
distance of each point from the mean. So it is really just a measure of how far the data is
spread out. The standard deviation is a measure of how much, on average each of the values
in the distribution deviates from the center of the distribution.
Say we wish to calculate the variance and the standard deviation for the salaries of the five
people in our diner (the diners without Jay Sugarman). The excel formulas for the variance
and the standard deviation are:
=var.p(12000,13000,13500,16000,20000)
=stdev.p(12000,13000,13500,16000,20000)
360°
thinking .
360°
thinking . 360°
thinking .
Discover the truth at www.deloitte.ca/careers Dis
© Deloitte & Touche LLP and affiliated entities.
Discover the truth at www.deloitte.ca/careers © Deloitte & Touche LLP and affiliated entities.
Deloitte & Touche LLP and affiliated entities.
Discoverfree
Download theeBooks
truth atatbookboon.com
www.deloitte.ca/careers
Click on the ad to read more
24
The variance is 8,240,000 and the standard deviation is $2870.54. A couple of things
worth noting:
• The variance is not given in the units of the data set. That is because the variance
is just a measure of the spread of the data. The variance is unit free.
• The standard deviation is reported in the units of the dataset. Because of this, people
often prefer to talk about the data in terms of the standard deviation.
• The standard deviation is simply the square root of the variance.
• The formulas for the variance and the standard deviation presented above are for the
population variances and standard deviations. If your data comes from a sample use:
=var.s()
=stdev.s()
The standard deviation has several important properties:
1. When the standard deviation is 0, the data set has no spread – all observations are
equal. Otherwise the standard deviation is a positive number.
2. Like the mean, the standard deviation is not resistant to outliers. Therefore, if you
have an outlier in your data set, it will inflate the standard deviation.
3. And, as said before, the standard deviation has the same units of measurements as
the original observations.
3.5 COMBINING THE MEAN AND THE STANDARD DEVIATION

The mean and the standard deviation can be used to gain quite a bit of insight into a data
set. Say for instance that Dave and Jim, his co-worker, are in charge of filling up 2 liter
growlers of beer. Since this is a manual process, it is difficult to get exactly two liters into
a growler. To assess how far each of you is off, you decide to precisely measure the next
100 growlers that you fill up. The mean and the standard deviation are reported below.
Employee Name Mean Standard Deviation
Dave 2.01 liters .05
Jim 1.95 liters .01

25
The data tells us that, on average, Dave’s pours are a bit closer to the mark of two liters
when he fills his beer growler. However, his pours have a higher standard deviation than
does Jim which indicates that his pours fluctuate more than Jim’s does. Jim might pour
less, but he consistently pours about the same amount each time. How could you use this
information? One thought you might have is that from a planning purpose, you know that
Jim is performing more consistently than Dave. You know you are going to get slightly
below the 2 liter goal. You can confidently predict what his next pour will be. On the other
hand, on average Dave gets closer to the mark of 2 liters, but his pours vacillate at a much
higher rate than does Jim.
The Empirical Rule is a powerful rule which combines the mean and standard deviation to
get information about the data from a mound shaped distribution.
Definition
The Empirical Rule: For a mound shaped distribution
• 68% of all data points fall within 1 standard deviation of the mean.
• 95% of all data points fall within 2 standard deviations of the mean.
• 99.7% of all data points fall within 3 standard deviations of the mean.
Put another way, the Empirical Rule tells us that 99.7% of all data points lie within three
standard deviations of the mean. The empirical rule is important for some of the work
that we will do in the chapters on inferential statistics later on. For now though, one way
that the empirical rule is used is to detect outliers. For instance suppose you know that
the average height of all professional basketball players is 6 feet 4 inches with a standard
deviation of 3 inches. A player of interest to you stands 5 foot 3 inches. Is this person an
outlier in professional basketball? The answer is yes. If we know that the distribution of
the height of pro basketball players is mound shaped, then the empirical rule tells us that
99.7% of all player’s heights will be within three standard deviations of the mean, or 9
inches. Our 5 foot 3 inches player is beyond 9 inches below the mean, which indicates he
is an outlier in professional basketball.
The last concept introduced in this chapter is the z-score. If you have a mound shaped
distribution the z-score makes use of the mean and the standard deviation of the data set in
order to specify the relative location of a measurement. It represents the distance between a
given data point and the mean, expressed in standard deviations. The score is also known
as “standardizing” the data point. The excel formula to calculate a z-score is
=standardize(data, mean, standard deviation)

26
Large z-scores tell us that the measurement is larger than almost all other measurements.
Similarly, a small z-score tells us that the measurement is small than all other measurements.
If a score is 0, then the observation lies on the mean. And if we pair the z-score with the
empirical rule from above we know that:
• 68% of the data have a z-score between -1 and 1.

• 95% of the data have a z-score between -2 and 2.
• 99.7% of the data have a z-score between -3 and 3.
Example
Suppose 200 steelworkers are selected and the annual income of each is determined. This
is our sample data set. The mean is $34,000 and the standard deviation is $2,000. Joe’s
annual income is $32,000. What is his sample z-score?
=standardize(32000,34000,2000)
= -1.0
Joe’s income falls one standard deviation below the average of all the steelworkers.
3.6 CHAPTER 3 EXERCISES

3.6.1 SUMMARIZING QUALITATIVE DATA
1) You survey 20 students to see which new cafeteria menu they prefer, Menu A,
Menu B, or Menu C. The results are A, A, B, C, C, C,A,A,B,B,B,C,A,B,A,A,C,
B,A,B,B. Which menu did they prefer? Make a frequency table carefully defining
the class, class frequency and relative frequency. Explain your answer.
2) A PC maker asks 1,000 people whether they’ve updated their software to the latest
version. The survey results are 592 say yes, 198 say no and 210 do not respond.
Generate the relative frequency table based off of the data. Why would you need
to include the non-responders in your table, even though they don’t answer your
question.
3) What is the benefit of showing the relative frequency (the percentages) instead of
the frequency in a table?
4) The pie chart below represent a random sample of 76 people, 22 females and the
remaining are males. How could the pie chart below be improved?

27
Subject: Introduction to Statistics
BS Mathematics Morning/Evening program spring semester 2020
Chapter # 03 Measures of Central Tendency
Measure of Central Tendency: Usually when two or more different data sets are
to be compared it is necessary to condense the data, but for comparison the
condensation of data set into a frequency distribution and visual presentation are
not enough. It is then necessary to summarize the data set in a single value. Such a
value usually somewhere in the center and represent the entire data set and hence it
is called measure of central tendency or averages. Since a measure of central
tendency (i.e. an average) indicates the location or the general position of the
distribution on the X-axis therefore it is also known as a measure of location or
position.
Types of Measure of Central Tendency
1. Arithmetic Mean
2. Geometric Mean
3. Harmonic Mean
4. Mode
5. Median
Arithmetic Mean or Simply Mean: “A value obtained by dividing the sum

of all the observations by the number of observation is called
arithmetic Mean ”
Sum of All observation
Mean 
Number of observation
Numerical Example:
Calculate the arithmetic mean for the following the marks obtained by 9
students are given below:
Using formula of arithmetic mean for ungrouped data:
x i
xi
x i 1
n 45
32
n9 37
46
360 39
x  40 marks 36
9 41
48
36
n
 Numerical Example: x
i 1
i  360
 Calculate the arithmetic mean for the following data given below:
 Using formula of direct method of arithmetic mean for grouped data:

n
fx i i n
x i 1
n
, n f i
 i 1
fi i 1
The weight recorded to the nearest grams of 60 apples picked out at random from a
consignment are given below:
106 107 76 82 109 107 115 93 187 95 123 125

111 92 86 70 126 68 130 129 139 119 115 128
100 186 84 99 113 204 111 141 136 123 90 115
98 110 78 185 162 178 140 152 173 146 158 194
148 90 107 181 131 75 184 104 110 80 118 82
Weight (grams) Frequency
65----84 09
85----104 10
105----124 17
125----144 10
145----164 05
165----184 04
185----204 05
Solution:
Weight (grams) Midpoints ( xi ) Frequency
( fi ) f i xi
65----84 (65  84) 2  74.5 09 9  74.5=670.5
85----104 94.5 10 945.0
105----124 114.5 17 1946.5
125----144 134.5 10 1345.0
145----164 154.5 05 772.5
165----184 174.5 04 698.0
185----204 194.5 05 972.5
n n
f
i 1
i  60 fx
i 1
i i  7350.0
fx i i
7350.0
x i 1
n
  122.5 grams
60
f
i 1
i
 Using formula of short cut method of arithmetic mean for grouped data:
n
fD n n f

i i
x  A ,
i 1
i
n
f
i 1
i
i 1
Where Di  X i  A and A is the provisional or assumed mean

Weight (grams) Midpoints ( xi ) Frequency Di  X i  A
( fi ) A  114.5 f i Di
65----84 (65  84) 2  74.5 09 -40 -360
85----104 94.5 10 -20 -200
105----124 114.5 17 0 0
125----144 134.5 10 20 200
145----164 154.5 05 40 200
165----184 174.5 04 60 240
185----204 194.5 05 80 400
n n
i 1
f i  60  f D =480
i 1
i i
fD i i
480
x  A i 1
n
 114.5   122.5 grams
60
f
i 1
i
 Using formula of step deviation method of arithmetic mean for grouped data:
n
 fu i i
xi  A
x  A i 1
n
 h , ui  , where h is the width of the class interval:
h
f
i 1
i
Xi  A
Weight (grams) Frequency ui 
Midpoints ( xi ) h f i ui
( fi ) A  114.5 , h=20
65----84 (65  84) 2  74.5 09 -2 -18
85----104 94.5 10 -1 -10
105----124 114.5 17 0 0
125----144 134.5 10 1 10
145----164 154.5 05 2 10
165----184 174.5 04 3 12
185----204 194.5 05 4 20
n n
f
i 1
i  60  fu
i 1
i i =24
 fu i i
24
x  A i 1
n
 h  114.5   20  114.5  08  122.5 grams (Answer).
60
f
i 1
i
Chapter 03 Measures of Central Tendency
 Geometric Mean: “The nth root of the product of “n” positive values is called
geometric mean”
Geometric Mean  n product of " n " positive values
The following are the formulae of geometric mean:
 Numerical example of geometric Mean for both grouped and ungrouped

data:
 Calculate the geometric mean for the following the marks obtained by 9
xi 45 32 37 46 39 36 41 48 36
 Using formula of geometric mean for ungrouped data:
n9
xi log xi
 n 
45 log 45 =1.65321   log xi 
32 1.50515 G.M  anti  log  i 1 
 n 
37  
1.56820  
46 1.66276
 14.38700 
39 1.59106 G.M  anti  log  
 9 
36 1.55630 G.M  anti  log 1.59856 
41 1.61278
48 G.M  39.68 (Answer).
1.62124
36 1.55630
n
 log x =14.38700
i 1
i
 Given the following frequency distribution of weights of 60 apples, calculate the

geometric mean for grouped data.
Weights 65--84 85--104 105--124 125--144 145--164 165--184 185--204

(grams)
Frequency 09 10 17 10 05 04 05
 n 
  f i log xi 
G.M  anti  log  i 1 n 
 
  fi 
 i 1 

( fi ) log xi f i log xi  n
65----84 (65  84) 2  74.5 09 1.8722 16.8498   f i log xi
G.M  anti  log  i 1 n
85----104 10 1.9754 19.7540 
  fi
94.5  i 1
105----124 17 2.0589 35.0013
 124.2483 
125----144 114.5 10 2.1287 21.2870  anti  log  
 60 
145----164 134.5 05 2.1889 10.9445
165----184 154.5 04 2.2418 8.9672  anti  log  2.0708 
185----204 174.5 05 2.2889 11.4445

G.M  117.7
194.5 grams
n n (An
f
i 1
i  60  f log x
i i = swer).
i 1
124.2483
 Harmonic Mean: “The reciprocal of the Arithmetic mean of the

reciprocal of the values is called Harmonic mean”
 Sum of reciprocal of the values 

Harmonic Mean  reciprocal of  
 The number of values 
The following are formulae of harmonic mean:
 Numerical example of harmonic Mean for both grouped and ungrouped

data:
 Calculate the harmonic mean for the following the marks obtained by 9
xi 45 32 37 46 39 36 41 48 36
 Using formula of harmonic mean for ungrouped data:
n9
xi 1 xi n
H .M 
45 0.02222
n
1
  
i 1  xi 
32 0.03125
37 0.02702 9
H .M 
46 0.02173 0.22862
39 0.02564
H .M  39.36663 (Answer).
36 0.02777
41 0.02439
48 0.02083
36 0.02777
n
1
x
i 1
=0.22862
i
 Given the following frequency distribution of weights of 60 apples, calculate the

harmonic mean for grouped data.
Weights 65--84 85--104 105--124 125--144 145--164 165--184 185--204

(grams)
Frequency 09 10 17 10 05 04 05
f i
H .M  i 1
n
 fi 
 x
i 1  i 

( fi ) f i xi
65----84 (65  84) 2  74.5 09 0.12081
85----104 94.5 10 0.10582
105----124 114.5 17 0.14847
125----144 134.5 10 0.07435
145----164 154.5 05 0.03236
165----184 174.5 04 0.02292
185----204 194.5 05 0.02571
n n
fi

i 1
fi  60 x =0.53044
i 1 i
f i
60
H .M  i 1
  113.11 grams (Answer).
n
 fi  0.53044
  
i 1  xi 
 Median: “when the observation are arranged in ascending or descending order,

then a value, that divides a distribution into equal parts, is called median”
 Numerical example of median for both grouped and ungrouped data:
 Calculate the median for the following the marks obtained by 9 students are
given below:
xi 45 32 37 46 39 36 41 48 36
Arrange the data in
ascending order
32, 36, 36, 37, 39, 41, 45, 46, 48. n  9 “n” is odd
th
 n 1
Median  Size of   observation
 2 
th
 9 1 
Median  Size of   observation
 2 
Median  Size of 5thobservation
Median  39 (Answer).
 Calculate the median for the following the marks obtained by 10 students
are given below:
xi 45 32 37 46 39 36 41 48 36 50
Arrange the data in ascending order
32, 36, 36, 37, 39, 41, 45, 46, 48, 50. n  10 “n” is even
 n th  n th 

Size of      1   observation
Median   2   2  
2
 10 th  10 th 

Median   2   2  
2
Median 
Size of 5 th
 6th  observation
2
39  41
Median   40 (Answer).
2
 The number of values above the median balances (equals) the number of
values below the median i.e. 50% of the data falls above and below the
median.
 Numerical examples: The following distribution relates to the number of
assistants in 50 retail establishments.
No.of 0 1 2 3 4 5 6 7 8 9
assistant
f 3 4 6 7 10 6 5 5 3 1
No. of assistants fi Cumulative frequency ( c. f )

0 3 3
1 4 7
2 6 13
3 7 20
4 10 30
5 6 36
6 5 41
7 5 46
8 3 49
9 1 50
n
f
i 1
i =50
n
n   f i  50 “n” is even
i 1
 n th  n th 

 2   2  
Median 
2
 50   50  
th th
 2   2  
Median 
2
Median 
Size of 25 th
 26 th  observation
2
44
Median  4 (Answer).
2
 Numerical example: Find the median, for the distribution of examination marks
given below:
Marks 30--39 40--49 50--59 60--69 70--79 80--89 90--99

Number of 08 87 190 304 211 85 20
students
h n  n
Median  l   C  here n   f i
f 2  i 1
Class boundaries Midpoints  xi  Frequency  fi  Cumulative frequency  c. f 
29.5---39.5 34.5 8 8
39.5---49.5 44.5 87 95
49.5---59.5 54.5 190 285
59.5---69.5 64.5 304 589
69.5---79.5 74.5 211 800
79.5---89.5 84.5 85 885
89.5---99.5 94.5 20 905
n
f
i 1
i =905
n 905
= =452.5th student which corresponds to marks in the class 59.5---69.5
2 2
Therefore
h n  10  905  10
Median  l    C   59.5    285   59.5   452.5  285 
f 2  304  2  304
1675
Median  59.5  , Median  59.5  5.5 , Median  65 marks (Answer).
304
 Quartiles: “ wh en th e obs er v a t i o n ar e ar r a n g e d in in c r ea s i n g
or d er th e n th e va l u e s , th at di v i d e th e wh ol e dat a in t o fou r (4)
eq u a l par t s , ar e ca l l e d qu a r t i l e s ”
These values are denoted by Q1, Q2 and Q3. It is to be noted that 25% of the data falls
below Q1, 50% of the data falls below Q2 and 75% of the data falls below Q3.
 Deciles: “ wh en th e obs e r v a t i o n ar e ar r a n g e d in in cr e as i n g or de r
th e n th e va l u es , th a t di v i d e th e wh ol e dat a in t o te n (10 ) eq u al
pa r t s , ar e ca l l e d qu a r t i l e s ”
These values are denoted by D1, D2,…,D9. It is to be noted that 10% of the data falls
below D1, 20% of the data falls below D2,…, and 90% of the data falls below D9.
 Percentiles: “wh en th e ob s e r v a t i on ar e ar r an ge d in in c r e as i n g
or d er th e n th e va l u es , th a t di v i d e th e wh o l e dat a in t o hu n d r e d
(1 00) eq u a l par t s , ar e ca l l e d qu ar t i l e s ”
These values are denoted by P1, P2,…,P99. It is to be noted that 1% of the data falls
below P1, 2% of the data falls below P2,…, and 99% of the data falls below P99.
Median  Q2  D5  P50 are same and are equal to median.
 Calculate quartiles for ungrouped data.
 Calculate the quartiles for the following the marks obtained by 9 students
are given below:
xi 45 32 37 46 39 36 41 48 36
Arranged the observation in ascending order
32, 36, 36, 37, 39, 41, 45, 46, 48.
If “n” is odd then we use the below formula:

th
 jn  
Q j  Marks obtained by    1 student , generalized formula of quartiles
 4  
where j=1, 2, 3.
th
 n  
Put j=1, n=9, Q1  Marks obtained by    1 student
 4  
th
 9  
Q1  Marks obtained by    1 student
 4  
Q1  Marks obtained by 2.25  1 student

th
Q1  Marks obtained by 2  1 student
th
Q1  Marks obtained by 3thstudent
Q1  36 (Answer).
Calculate Q2 and Q3 from above distribution?
 Calculate quartiles for discrete grouped data.

th
 3n  
 4  

0 3 3
1 4 7
2 6 13
3 7 20
4 10 30
5 6 36
6 5 41
7 5 46
8 3 49
9 1 50
n
f
i 1
i =50
th
 3  50  
 4  
th
 150  
 4  
Q3  Marks obtained by 38 thstudent
Q3  6 (Answer).
 Calculate Decile for ungrouped data.
 Calculate the Decile for the following the marks obtained by 9 students are
given below:
xi 45 32 37 46 39 36 41 48 36

32, 36, 36, 37, 39, 41, 45, 46, 48.

th
 jn  
D j  Marks obtained by    1 student , generalized formula of quartiles
 10  
where j=1, 2, 3, 4, 5, 6, 7, 8, 9.
th
 4n  
Put j=4, n=9, D4  Marks obtained by    1 student
 10  
th
 4  9  
D4  Marks obtained by    1 student
 10  
D4  Marks obtained by 3.6  1 student

th
D4  Marks obtained by 3  1 student

th
D4  Marks obtained by 4 thstudent
D4  37 (Answer).
Calculate D3 , D7 and D9 from above distribution?
 Calculate decile for discrete grouped data.

th
 6n  
 10  

0 3 3
1 4 7
2 6 13
3 7 20
4 10 30
5 6 36
6 5 41
7 5 46
8 3 49
9 1 50
n
f
i 1
i =50
th
 6  50  
 10  
th
 300  
 10  
D6  Marks obtained by 31thstudent
Q3  5 (Answer).
 Calculate percentile for ungrouped data.
 Calculate the percentile for the following the marks obtained by 9 students
are given below:
xi 45 32 37 46 39 36 41
48 36
32, 36, 36, 37, 39, 41, 45, 46, 48.

th
 jn  
Pj  Marks obtained by    1 student , generalized formula of quartiles
 100  
where j=1, 2, …, 99.
th
 68n  
Put j=68, n=9, P68  Marks obtained by    1 student
 100  
th
 68  9  
P68  Marks obtained by    1 student
 100  
P68  Marks obtained by 6.12  1 student

th
P68  Marks obtained by 6  1 student

th
P68  Marks obtained by 7 thstudent
D4  45 (Answer).
Calculate P9 , P55 , P80 and P95 from above distribution?
 Calculate percentile for discrete grouped data.

th
 49n  
 100  
0 3 3
1 4 7
2 6 13
3 7 20
4 10 30
5 6 36
6 5 41
7 5 46
8 3 49
9 1 50
n
f
i 1
i =50
th
 49  50  
 100  
th
 2450  
 100  
P49  Marks obtained by 24 thstudent
Q3  4 (Answer).
 Numerical example of Quartile, Decile and Percentile for continuous grouped
data:
29.5---39.5 34.5 8 8
39.5---49.5 44.5 87 95
49.5---59.5 54.5 190 285
59.5---69.5 64.5 304 589
69.5---79.5 74.5 211 800
79.5---89.5 84.5 85 885
89.5---99.5 94.5 20 905
n
f i 1
i =905
Calculate the 3rd quartile

h  3n 
Q2  l   C 
f  4 
3n 3  905
= = 678.75
4 4
10
Q2  69.5   678.75  589 
211
897.5
Q2  69.5 
211
Q2  73.7535 (Answer)
Calculate the 4th and 8th decile

h  4n 
D4  l   C 
f  10 
4n 4  905
= =362
10 10
10
D4  59.5  362  285 
304
770
D4  59.5 
304
D4  62.0328 (Answer)
h  8n 
D8  l  C 
f  10 
8n 8  905
= =724
10 10
10
D8  69.5   724  589 
211
1350
D8  69.5 
211
D8  75.8981 (Answer)
Calculate the 18th and 76th Percentile

h  18n 
P18  l   C 
f  100 
18  905
= 162.9
100
10
P18  49.5  162.5  95 
190
675
P18  49.5   53.05 (Answer).
190
h  76n 
P76  l   C 
f  100 
76  905
=687.8
100
10
P76  69.5   687.8  589 
211
988
P76  69.5  = 74.182 (Answer).
211
Calculate Q2 , D5 , D8 , P25 , P50 and P88 ?
Main Objects of Average
The main object (purpose) of the average is to give a bird’s eye view
(summary) of the statistical data. The average removes all the unnecessary
details of the data and gives a concise (to the point or short) picture of the
huge data under investigation.
 Average is also of great use for the purpose of comparison (i.e. the
comparison of two or more groups in which the units of the variables are
same) and for the further analysis of the data.
 Averages are very useful for computing various other statistical measures
such as dispersion, skewness, kurtosis etc.
 Requisites (desirable qualities) of a Good Average: An average will be
considered as good if:
 It is mathematically defined.
 It utilizes all the values given in the data.
 It is not much affected by the extreme values.
 It can be calculated in almost all cases.
 It can be used in further statistical analysis of the data.
 It should avoid to give misleading results.
 Uses of Averages in Different Situations

 A.M is an appropriate average for all the situations where there are no
extreme values in the data.
 G.M is an appropriate average for calculating average percent increase in
sales, population, production, etc. It is one of the best averages for the
construction of index numbers.
 H.M is an appropriate average for calculating the average rate of increase
of profits of a firm or finding average speed of a journey or the average
price at which articles are sold.
 Mode is an appropriate average in case of qualitative data e.g. the opinion
of an average person; he is probably referring to the most frequently
expressed opinion which is the modal opinion.
 Median is an appropriate average in a highly skewed distribution e.g. in
the distribution of wages, incomes etc.
Mode in case of Ungrouped Data: “A value that occurs most frequently in a data is
called mode”
OR
“if two or more values occur the same number of times but most frequently than the
other values, the there is more than one whole”
“If two or more VAlues occur the SAme number of times but most frequently thAn
the other vAlues, then there is more thAn one mode”
 The data having one mode is called uni-modal distribution.

 The data having two modes is called bi-modal distribution.
 The data having more than two modes is called multi-modal distribution.
Mode in case of Discrete Grouped Data: “A value which has the largest frequency
in a set of data is called mode”
Mode in case of Continuous Grouped Data: In case of continuous grouped data,

mode would lie in the class that carries the highest frequency. This class is called
the modal class. The formula used to compute the value of mode, is given below:
 Numerical examples of Mode for ungrouped and grouped data

 Calculate Mode for ungrouped data
xi : 2, 3, 8, 4, 6, 3, 2, 5, 3.
Mode = 3 (Answer).
 Calculate Mode in discrete grouped data
No. of assistants fi
0 3
1 4
2 6
3 7
4 10
5 6
6 5
7 5
8 3
9 1
n
f
i 1
i =50
Mode = 4
 Mode in case of Continuous grouped data:

29.5---39.5 34.5 8 8
39.5---49.5 44.5 87 95
49.5---59.5 54.5 190 285
59.5---69.5 64.5 304 589
69.5---79.5 74.5 211 800
79.5---89.5 84.5 85 885
89.5---99.5 94.5 20 905
n
f
i 1
i =905
f m  f1 304  190
Mode  l   h  59.5   10
 f m  f1    f m  f 2   304  190   304  211 
114
Mode  59.5   10  Mode  59.5  5.05072
114  93
Mode = 4 (Answer)
Q: What is a measure of location? What is the purpose served by it? What

are its desirable qualities?
Measure of location: A central value that represents the whole data is
called an average. Since average is a value usually somewhere in the center
and represents the entire data set therefore it is called measure of central
tendency. Measure of central tendency indicates the location or the general
position of the data on the X-axis therefore it is also known as a measure of
location or position
Purpose:
 It removes all the unnecessary details of the data and gives a concise
picture of the huge data.
 It is used for the purpose of comparison.
 It is very useful in computing other statistical measures such as
dispersion, skewness and kurtosis etc.
Desirable qualities of a good average: An average will be considered as

good if:
 It is mathematically defined.
 It utilizes all the observations given in a data.
 It is not much affected by the extreme values.
 It is capable of further algebraic treatment.
 It is not affected by fluctuations of sampling.

Bahan Ajar Statistika

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Bahan Ajar Statistika

Uploaded by

Copyright:

Available Formats

BAHAN AJAR

JURUSAN PENDIDIKAN DAN SASTRA INGGRIS

Semarang, 19 Agustus 2021

Ketua Jurusan/ Ketua Prodi Ketua Tim Penulis

Widhiyanto, S.Pd., M.Pd., Ph.D Arif Suryo Priyatmojo, S.Pd., M.Pd

Specific skill (1)

Specific skill (2)

Week 1&2 Statistics and statistical thinking

1 STATISTICS AND STATISTICAL

• In the pharmaceutical industry, it is impossible to test a potential drug on every

1. The Atkins Diet

Download free eBooks at bookboon.com

Atkins 310 310 304 300 290 285 280 284

Based on these numbers, which diet should Dave adopt?

Download free eBooks at bookboon.com

1.1 DESCRIPTIVE STATISTICS

Sunday Monday Tuesday Wednesday

Breakfast 4 Coffees Protein Plate Skip Fruit

Calories 200 175 0 200

Lunch Pizza and Wings Salad Super Burrito Salad

Calories 1200 375 750 375

Dinner Leftovers Frozen Dinner Frozen Dinner Frozen Dinner

Calories 1000 275 300 300

Snack 3 Beers 3 Beers 3 Beers 3 Beers

Calories 300 300 300 300

Caloric Intake Log for Sunday–Wednesday

Sunday Monday Tuesday Wednesday

Breakfast 4 Coffees Protein Plate Skip Fruit

Calories 200 175 0 200

Lunch Pizza and Wings Salad Super Burrito Salad

Calories 1200 375 750 375

Dinner Leftovers Frozen Dinner Frozen Dinner Frozen Dinner

Calories 1000 275 300 300

Snack 3 Beers 3 Beers 3 Beers 3 Beers

Calories 300 300 300 300

Daily Total 2700 1125 1350 1175

Caloric Intake Log (with totals) for Sunday–Wednesday

Download free eBooks at bookboon.com

What new information does providing the totals add?

• The heaviest calorie day was by far on Sunday.

1.2 INFERENTIAL STATISTICS

Experimental Unit: An object upon which data is collected.

Population: A set of units that is of interest to study.

Variable: A characteristic or property of an individual experimental unit.

Sample: A subset of the units of a population.

What is a statistical hypothesis? It is an educated guess about the relationship between

Download free eBooks at bookboon.com

Elements of a Descriptive Statistical Problem

1) Define the population (or sample) of interest

Download free eBooks at bookboon.com

Elements of an Inferential Statistical Problem

1) define the population of interest

1.3 TYPES OF DATA

1.4 CHAPTER 1 PROBLEMS

Download free eBooks at bookboon.com

European Journal of Education, Vol. 48, No. 2, 2013

Comparison of Quantitative and Qualitative

Definition of the Terms

© 2013 John Wiley & Sons Ltd

research). Hence, qualitative research needs to be comprehensively defined to do

Differences between the Two Research Paradigms

© 2013 John Wiley & Sons Ltd

Therefore, the researcher is supposed to develop a close, empathic relationship with

© 2013 John Wiley & Sons Ltd

1 STATISTICS AND STATISTICAL