I.M.R.A.D.

By Dr. Bonifacio P. Bairan

VPAA
 What does IMRAD stand for?
• INTRODUCTION
• (Related Literatures and Studies)

• METHODOLOGY
• RESULT
• DISCUSSION
 When did IMRAD start?
The IMRAD structure has come to dominate academic writing in the
sciences, most notably in empirical biomedicine. 

In a study of four of the major English language biomedical journals,

Sollaci & Pereira (2004) report that “The IMRAD structure, in those
journals, began to be used in the 1940s. In the 1970s, it reached 80%
and, in the 1980s, was the only pattern adopted in original papers.”

Sources:

•Luciana B. Sollaci & Mauricio G. Pereira. 

“The introduction, methods, results, and discussion (IMRAD) structure: a fi
fty-year survey”
. J Med Libr Assoc. 2004 July; 92(3): 364–371. Retrieved 2010-08-19.

•Day, RA (1989). "The Origins of the Scientific Paper: The IMRAD Format“.

 How about the other disciplines?
Even though the IMRAD structure originates in the empirical
sciences, it now appears in academic journals in many disciplines. 

For example:

The American Psychological Association (APA style). The APA

publication manual is widely used by journals in
the social, educational and behavioral sciences.

Source:

•American Psychological Association (2010). Publication Manual

of the American Psychological Association (6th ed.).
 CHAPTER I: INTRODUCTION
Background

•What is the study all about?

– Context

•What are the researches known about the study?

– Related studies & literatures

•Why is further study needed?

– The rationale of the study (E.g. for continuity, for replication, or for further
studies, etc.)

•What is the purpose of the study?

– To compare variables X1 and X2, etc.
– To correlate between variable X and Y
– To predict variable Y from X
Theoretical Framework

•Your theoretical framework is the

foundation of your research paradigm.

•It introduces and describes the theory that

explains why the research problem under
study exists.
Research Paradigm

•Your research paradigm is based on your theoretical

framework.

•The Figure should show either:

– To compare variables X1 and X2, etc. (No DV)
– To correlate between variable X and Y
– To predict variable Y from X

(Note: The “Figure” of the study should be the same as the

“Purpose” of the study as mentioned in the “Background”.)
Example of “Research Paradigm”:
Research Problem

•1. What is the profile of the respondents in terms of:

 
•1.1. gender
•1.2. age group
•1.3. civil status
•1.5. total number of years of relevant work experience
•1.6. household income
•1.4. employment status, and
•1.7. highest educational attainment?

•2. Is there a significant relationship between X and Y?

 
•3. Does the profile of the respondents influence the effect of X on Y? (Optional)
 
•4. What are the applications of the study based on the implications of the findings?
Hypothesis
 CHAPTER II: REVIEW OF RELATED
LITERATURES AND STUDIES
• What was done? Or, what is the study all about?

• How was it done? Or, how was the problem

studied?

• What was found? Or, what are the findings?

• What are the significance, meaning and

implication of the findings? Or, what do the
findings mean in light or purpose (and context) of
your study?
 CHAPTER III: METHODOLOGY
Respondents

•Who are your respondents?

•What are your inclusion and exclusion criteria?

•What is the type of sampling method used?

• Sample size

– Note: Unlike other sample size formulas (e.g., Slovin’s etc),

when you have a large population (e.g., 250,000 > ) at 5.0%
margin of error, the calculated sample size only changes
marginally (i.e., the sample size remains constant from the
time it first changes).

• Krejcie, R.V. and Morgan, D.W. (1970).

Determining Sample Size for Research
Activities.
Recommended sample size without using a Table or a formula from
research experts and statisticians:

For descriptive studies:

–Fraenkel and Walden (2011) recommend 100 individuals, while Mertler and
Charles (2010) recommended 10% and 20% of the population

For correlational research designs:

–Fraenkel and Wallen recommend a sample size of 50 individuals, and

–Mertler and Charles recommend that a minimum of 30 individuals are

needed.

For experimental and causal comparative research:

–Fraenkel & Wallen recommend 30 individuals per group, and

–Mertler and Charles recommend 15 per group.

Instrument

Validity and reliability of questionnaire.

Use Kappa Value.

Cohen's kappa coefficient is a statistic which measures

inter-rater agreement for qualitative (categorical) items.
It is generally thought to be a more robust measure than
simple percent agreement calculation, since κ takes into
account the agreement occurring by chance.
• Cohen's kappa measures the agreement between two
raters who each classify N (notation for population
size) items into C mutually exclusive categories. The
first mention of a kappa-like statistic is attributed to
Galton (1892). (See Smeeton [1985]).

• To evaluate percent agreement, the method involves

counting the number of times the two experts agreed
and dividing by the total number of observations.
Calculate percent agreement according to the
following formula:
• How to create a customized researcher-made
questionnaire?

– 1st step: Establish your criteria (i.e., a principle or

standard by which something may be judged or
decided).

– 2nd step: Customize the number of

criteria/questions/descriptors, i.e., data points: unit of
information per variable: E.g.: 10 criteria or 5 criteria
with sub-criteria.

– 3rd step: Decide on what type of rating scale to use.

• For example:

• 1. Dichotomous Scales

• A dichotomous scale is a two-point scale which presents

options that are absolutely opposite each other. This type of
response scale does not give the respondent an opportunity
to be neutral on his answer in a question. Examples:

• Yes- No
• True - False
• Fair - Unfair
• Agree – Disagree
• 2. Rating Scales

• Three-point, five-point, and seven-point scales are all included in

the umbrella term “rating scale”. A rating scale provides more
than two options, in which the respondent can answer in
neutrality over a question being asked.

• Examples:

• 2.1. Three-point Scales

• Good - Fair – Poor
• Agree – Undecided - Disagree
• Extremely- Moderately - Not at all
• Too much - About right - Too little
• 2.2. Five-point Scales (e.g. Likert Scale)

• Strongly Agree – Agree – Undecided / Neutral -

Disagree - Strongly Disagree

• Always – Often – Sometimes – Seldom – Never

• Extremely – Very - Moderately – Slightly - Not at all

• Excellent - Above Average – Average - Below Average

- Very Poor
• 2.3. Seven-point Scales

• Exceptional – Excellent – Very Good –

Good – Fair – Poor – Very Poor

• Very satisfied - Moderately satisfied -

Slightly satisfied – Neutral - Slightly
dissatisfied - Moderately Dissatisfied- Very
dissatisfied
• 3. Semantic Differential Scales

• A semantic differential scale is only used in

specialist surveys in order to gather data
and interpret based on the connotative
meaning of the respondent’s answer.

• It uses a pair of clearly opposite words,

and can either be marked or unmarked.
• 3.1 Marked Semantic Differential
• 3.2. Unmarked Semantic Differential Scale
Procedures

•Questionnaire administration
•Data gathering
•Data processing
•Data Analysis
• Questionnaire administration
 
• Explain / describe the step by step process of your questionnaire
administration:

• Who administered your questionnaires?

• Who and how many respondents were in your study?

• When, where, and for how long were the questionnaires given?

• What were the inclusion and exclusion criteria? Why?

• Where applicable, what were the environment and condition of the

respondents when the questionnaires were administered?

• As appropriate, what were the guidelines (or protocol) you followed in

questionnaire administration?
• Data gathering
 
• Provide enough information about the procedure that another researcher
could reproduce its essential details. Hence, explain / describe the step by step
process of data gathering:

• Who collected your questionnaires?

• When and for how long were the questionnaires retrieved?

• What was the response rate or attrition of the respondents?

• Was there a follow up? If yes/none, why?

• Where applicable, what were the environment and condition of the

respondents when the questionnaires were gathered?

• As appropriate, what were the guidelines (or protocol) you followed in data
gathering?
• Data processing

• Data processing will be done through data

coding.

• The codes are going to be finalized as the

respondents completed the questionnaires
and after they were submitted to the
researcher for data entry.
Note: Very very very very very very
important!!!!
Summate (add together or add up) on the top of
each unit of scale all the choices/answers of
your respondents for coding purposes.
Data Analysis

•Frequency Distribution
•Percentage
•Mean Score
•Standard Deviation

Note: The statistician will put or add in this

section what statistical treatment will be
applied in the study.
• Frequency Distribution
 
• Frequency distribution was used in the study to indicate the
number of cases at each score.

• The scores of the demographic profile of the respondents

were grouped in categories defined by step intervals, each of
which was a set of contiguous (i.e., together in sequence)
possible scores.

• A variable with values that indicate the order of the cases was
divided into a number of categories. The number of cases
tabulated in any category was the frequency.
• Percentage
 
• In order to obtain a measure of the relative
frequency of the respondents’ demographic
profile in a nominal scale and so as to
determine the relationship of their categories
with each other, percentages are used.
• Mean Score
 
• The mean score is used to determine if the
average score (or mean value) of the
respondents’ set of data is equal to the
sum of all the values in the data set
(divided by the total number of values).
• Standard Deviation
 
• Standard deviation is used to quantify the
amount of variation or dispersion of a set
of data values.

• A standard deviation indicates how much

the values of the respondents’ data differ
from the mean on average.
 CHAPTER IV: RESULT
• Descriptive and Inferential Statistics. Per the accepted practice in
the academe, the statistician will do this part.

• Marilyn J. Lister (1993) “The results section, therefore, may be the

shortest section of your paper.” She added: “. . . do not discuss the
results as you present them.” The data (figures, illustrations, tables,
etc.) will be organized according to the procedures and data analysis
subsections.

• The results will state the effect being evaluated (comparison,

correlation, prediction), whether or not the hypothesis is statistically
significant, (null, non-directional, directional) the critical statistic used
(critical / tabular value), the degrees of freedom, the value obtained
(calculated value) for the statistic, and the level of significance (alpha
0.05 or 0.01) achieved.
•  
• (Note: Interpretation or discussion of findings is NOT done in the
result section! A simple result of the calculation will be shown via a
tables, figures or descriptions.)
 CHAPTER V: DISCUSSION

• Write the discussion succinctly and in the same

order in which you presented your procedures and
results so that the readers will not be sidetrack.

• Close your paper with a brief conclusion on your

findings and the implications of your results.

• Do not create a summary for this section as in an

abstract and do not draw conclusions unless they
are part of the study.
• The sequence in writing the Discussion section is as follows:
 
• result/s of the computation the test statistic

• conclusion whether the null hypothesis is accepted or rejected

 
• implication of the conclusion:

– if H0 is accepted; H0 cannot be generalized (because X has “zero

effect” with Y: not possible); whereas,
 
– if H1 is accepted; H1 can be generalized (because X has “an
effect” with Y: possible).
 
• integrate the findings with previous researches and theories.
 BIBLIOGRAPHY
• Use APA citation research guide.

• Go to:

• http://www.citefast.com/.

• http://www.bibme.org/

• http://www.citationmachine.net
 APENDICES
• This is the section or table of additional
matter at the end of a book or document.

• For example:

– Questionnaires

– Other required research documents for

addendum, supplement, postscript, or attachment
purposes.
 Thank you!
“We are what we make ourselves to be!”
– Dr. B. P. Bairan, VPAA