You are on page 1of 28

Research Methodology

Introduction to Statistical Analysis and Decision Making


Overview

1. Definitions of key terms, Analysis , Variables, and Data


types
2. Using Statistical Software Packages (A case of SPSS)
3. Data Coding, Data Entry, Data Cleaning, and Processing
4. Descriptive Data Analysis and Interpretation of Results
5. Hypotheses Testing and Interpretation of Results

04/12/24 BIT 1205 2


Steps in data processing

04/12/24 BIT 1205 3


Data Editing

• Editing is the process of scrutunizing the completed research instruments to


identify and minimise as far as possible, errors, incompleteness, incosistencies,
and gaps in the data obtained from the respondents.

• Sometimes even the best researchers can;


• Forget to ask a question
• Forget to record a response
• Wrongly classify a response
• Write only half of the response

04/12/24 BIT 1205 4


Data editing

• Example 1:
A questionnaire meant to be answered by adults over the age of
30 years has also been answered by some persons under the age
of 30 years

• Example 2:
A respondent gives her birthday as 1865 or claims to have a car
insurance but says she doesn‘t own a car

04/12/24 BIT 1205 5


Data Consistency and Completeness

The data obtained from a questionnaire must be logically consistent,


especially when questions are related.
Circumstances permitting, the data editor may have to insert data if
answers to questions have been omitted by the respondent, but which can
be answered based on the other data obtained.
(example: respondent does not answer a question asking if his
organization has a website, but somewhere later answers that the
organization has three websites).
 Sometimes respondents give answers to (open-ended) questions in other questions. In such cases, data
must be shifted around the questions.

04/12/24 BIT 1205 6


Some Observations while Editing

• Editing of data should be done wih a coloured pencil and the original
data must not be erased in case it is required for future reference.
• Data editing should be conducted systematically on the basis of
procedures made by professionals.
• Data editing has drawbacks, such as, the editor does not possess the
required level of intelligence, experience and objectivity.

04/12/24 BIT 1205 7


Data Coding

• Data coding means translating the raw data into values suitable for
computer entry and statistical analysis.

• For computer analysis, each category of a variable can be coded


with a letter, group of letters or word, or be given a number.

• For example, the answer ‘yes’ may be coded as ‘Y’ or 1; ‘no’ as


‘N’ or 2 and ‘no response’ or ‘unknown’ as ‘U’ or 9.

04/12/24 BIT 1205 8


Data Coding

• Common responses should have the same code in each question,


as this minimizes mistakes by coders.

• For example:
• Yes (or positive response) code - Y or 1
• No (or negative response) code - N or 2
• Don’t know code - D or 8
• No response/unknown code - U or 9

04/12/24 BIT 1205 9


Data Coding open-ended qtns

• The coding of open-ended questions requires a process called content


analysis.
• This involves selecting several interview schedules
/questionnaires randomly from the total completed interview schedules or
questionnaires received.
• Select an open-ended question from one of these schedules or questionnaire
and write down the response on a sheet of paper.
• Look through all the selected schedules or questionnaires and write down the
responses of that same open-ended question on a separate sheets.

04/12/24 BIT 1205 10


Data Coding open-ended qtns

• Now, one by one, examine the responses of that same exact open-ended question to
ascertain the similarities and differences.
• If two or more responses are similar in meaning though not necessarily in language,
try to combine them under one category.
• Give a name to the category that is descriptive of the responses . Remember, when
you code the data you code categories, not responses per se.
• A response should not be placed within two categories, every response should be
placed within one of the categories.

04/12/24 BIT 1205 11


Data Entry

During data entry, the information relating to each subject in the


study is keyed into the computer in the form of the relevant code.
Verification
During data entry, mistakes will creep in. The computer can print
out the data exactly as it has been entered, so the printout can be
checked visually for obvious errors, (blanks that should not be
there, alphabetic codes where numbers are expected, obviously
wrong codes).

04/12/24 BIT 1205 12


Data Analysis

Analysis of data is a process of inspecting, cleaning, transforming/processing, and


modeling data with the goal of highlighting useful information, suggesting conclusions,
and supporting decision making.

The process of transforming raw data into useful information with an aim of suggesting
conclusions and supporting decision making.

 In data analysis, a framework of analysis (Analysis plan)needs to be developed. It includes ;


 Which variables you are planning to be analyzed
 How should they be analyzed
 Which variables need to be analyzed together to draw conclusions..

04/12/24 BIT 1205 13


variables

In scientific research, a researcher cannot be able to do very much unless


he/she has identified variables in his study; because it is the variables that one
has to study to ascertain relationships between them and draw conclusions.

A variable is a property or characteristic of some event, object, or person that


can take on different values or amounts (as opposed to constants which do not
vary).

It can also be defined as any entity that can take on different values. OK, so
what does that mean?
An attribute is a specific value on a variable. For instance, the variable sex or
gender has two attributes: male and female
04/12/24 BIT 1205 14
variables
Anything that can vary can be considered a variable. For instance, age can
be considered a variable because age can take different values for different
people or for the same person at different times.

Similarly, country can be considered a variable because a person's country


can be assigned a value.

Variables aren't always 'quantitative' or numerical. The variable 'gender'


consists of two text values: 'male' and 'female'. We can, if it is useful, assign
quantitative values instead of (or in place of) the text values, but we don't
have to assign numbers for something to be a variable
04/12/24 BIT 1205 15
Types of Variables: Independent vs. dependent variable
• Two most used variables in scientific research;

• Independent Variable (I.V)


• Dependent variable (D.V)

• Independent variable: Is a variable manipulated or changed by the


researcher/experimenter to examine its effect upon the dependent
variable.
 The direct and indirect control has to do with whether the researcher changes the values
or the changes in the values naturally occur and cannot be manipulated (e.g. age,
gender).
04/12/24 BIT 1205 16
Types of Variables: Independent vs. dependent variable

Dependent variable: A dependent variable is the variable we look at to see


what effect changing (or looking at different levels of) the independent
variable had.

Dependent variable is what is affected by the independent variable


It is called dependent because it "depends" on the independent variable.
 In a scientific experiment, you cannot have a dependent variable without an
independent variable.
In summary, the independent variable is typically the variable being
manipulated or changed and the dependent variable is the observed result
of the independent variable being.

04/12/24 BIT 1205 17


Examples

• If your study involves assessing the effect/impact of teaching methods on student


performance.

• The independent variable is teaching methods


• Then the dependent variable is Student performance

• Why? Because changing or manipulating the teaching methods used in class is


going to affect (positively or negatively) the performance of students in a give class.

04/12/24 BIT 1205 18


Other types of Variables

• Control variable

• Extraneous variable

• Moderator variable

04/12/24 BIT 1205 19


Control Variable

• A Control variable is anything else that could influence the dependent variable.

• The influence of which needs to be removed or controlled.

• See example on the next slide…

04/12/24 BIT 1205 20


More examples

• If you were measuring the impact of full sunlight on the growth


rate of plants.

• Independent – sunlight,
• dependent- growth rate

• A control variable in this case could be Water (because it can


also cause an impact on the growth of plants).

• Therefore, to make it constant, the amount of water given to


each plant should be the same.

04/12/24 BIT 1205 21


Extraneous Variable
• Extraneous variable. A variable that has an unpredictable impact/ influence on the
(relationship between the) independent and dependent variables.

• Unlike a control variable which can be eliminated or controlled, an extraneous


variable is one that we cannot control or manipulate.

• Extraneous variables are undesirable because they add error to an experiment.

04/12/24 BIT 1205 22


Example
• For example, let’s say that an educational psychologist has developed a new learning strategy
and is interested in examining the effectiveness of this strategy.

• The experimenter randomly assigns students to two groups. All of the students study text
materials on a biology topic for thirty minutes.

• One group uses the new strategy for studying and the other uses a strategy of their choice. Then
all students complete a test over the materials.

• One obvious extraneous variable in this case would be pre-knowledge of the biology topic that
was studied.

04/12/24 BIT 1205 23


Example cont..d
• It would be better, of course, if all students came in with the exact same pre-knowledge, but
because we cannot control or find out which students have pre-knowledge about this same
topic, pre-knowledge turns out to be the extraneous variable in this experiment.

• This variable will most likely influence student scores, regardless of which strategy they use.

• Because of this extraneous variable (and surely others like one group being more intelligent
than the other) there will be some spread within each of the groups.

04/12/24 BIT 1205 24


Moderator Variable
• Moderator Variable: In statistics, moderation occurs when the relationship
between two variables (i.e. I.V & D.V) depends on a third variable.

• The third variable is referred to as the moderator variable or simply the moderator.

• Examining the relationship between Gender and ice cream consumption, you need to
include temperature since it moderates that relationship, else your conclusions will be
inaccurate.

04/12/24 BIT 1205 25


Summary on types of variables
Type of Variable Definition Other terms
Dependent A variable measured to see whether a change of the Outcome Variable
independent variable had an effect Results variable
Criterion
Independent A variable manipulated to examine its impact on a Treatment variable
dependent variable Factor variable
Predictor Variable
Control A variable related to the dependent variable, the influence Restricting Variable
of which needs to be removed

Extraneous A variable that has an unpredictable impact on the Threatening Variable


dependent or independent variable but is not part of the
experiment
Moderator A variable that makes the relationship between two Interacting Variable
variables (I.V & D.V) to depend on a third variable.

04/12/24 BIT 1205 26


Continuous vs. Discrete Variables

• Continuous
• A variable that can take on any of a range of values, including fractions. e.g. height
can be 45.0 inches, 65.334 inches, 70.005 inches, weight, temperature etc.
• can assume an infinite number of values
• Discrete (or Categorical)
• their values vary but, they are constrained to a certain limit or boundary. e.g.
gender, number of goals scored in a football match, number of bedrooms in a house
etc..
• describe a finite set of conditions and take values from a finite, usually small, set of
states.

04/12/24 BIT 1205 27


Data Types

• Numerical data
• Characters and Strings

(personal reading)

04/12/24 BIT 1205 28

You might also like