‫بسم الله الرحمن الرحيم‬

Shendi University
Faculty of Medicine
community medicine department
Semester 7

Proposal Framework

Research Methods

Dr:- Ebtisam khalaf Alla

1
 Proposal framework
1. Personal information 6. Research methods
2. Title 1.Study design
3. Introduction 2.Study setting(area)
4. Justification 3. Study Population (definition
4.sampling :
5. Objectives(general &specific )
sample size ,sample size technique
6. Research methods
5.Study variables :
7. Work plan 6.Methods of data collection
8. Budget 7.Tools of data collection
9. References 8. Data collection technique
10. annex 9..Data management :
10.Ethical consideration ethical
technical approval, participant
consent
11 . Reference management
(manual ,electronic

2
 Data management
• During the planning phase the investigator
should decide, at least in broad outlines, how
the information will be proposes, to collect
and analyzed , to meet its objectives
• Data management is the way of research data
is prepared for analysis , it consists of creating
a database, and enters the data and outlines
how the data is analyzed

3
 Data management
• Data analysis: consists of data editing and
how the researcher reviews the recorded data
for
– Validity
– accuracy
– consistency
– Completeness
– data summarization

4
So data management reflect on
Process of , review, analyze, detect, modify, or remove
“dirty” data to make your dataset “clean.”Organizing
the Data
Analysis the data (statistic analysis)
(to show significance or insignificance of the results)
Displaying data ( data presentation : tables and
figures )

5
Data management could be( process of dataset):-
A. Manual
• Hand tallying and hand sorting
(Hand tallying is the most primitive method. A tally sheet is
prepared in the form of a skeleton table, and a tally mark is
made in the requisite cell for each individual)
b. Electronic
• By an appropriate computer program
As Statistical Package for the Social Sciences “SPSS” analytic
software ,
For the analysis & presentation of data
6
 Data statistic analysis

• Descriptive statistics summarize and organize

characteristics of a data set.
• A data set is a collection of responses or observations from
a sample or entire population.
• In quantitative research, after collecting data, the first step
of statistical analysis is to describe characteristics of the
responses, such as the average of one variable (e.g., age), or
the relation between two variables (e.g., age and outcome).
• inferential statistics, (the 2ed )step which help you decide
whether your data confirms your hypothesis and whether it
is generalizable to a larger population.

7
 Descriptive statistics
There are 3 main types of descriptive statistics:
• The distribution concerns the frequency of
each value(Incidence , prevalence and
percentage)
• The central tendency concerns the averages
of the values.
• The variability or dispersion concerns how
spread out the values are.

8
 Inferential statistics
• After finishing the descriptive statistics, we
move to the analytical part (called also
inferential statistics)
• Basic skills in analytical statistics include
choosing the proper statistical test that is
suitable for the data.
• It helps to answer the research question and
reach a conclusion regarding the null hypothesis
(reject or fail to reject the null hypothesis)
9
Revision

10
 Normal distribution…cont

• Normal distribution is a theoretical mathematical formula

• Normal distribution characteristic:-
1. Bell shaped
2. Symmetrical around the mean
3. Mean =median =mode
4. Mean ± 1sd= 68 % of observation
Mean ± 2sd =95% of observation
Mean ± 3sd = 99.7% of observation

(Sd= stander deviation ; Square root of the variance)

(confidence limit : 68% , 95%, 99.7% )
11
Central Limit Theorem (CLT)

The Central Limit Theorem states that : regardless

of the shape of the population distribution, the
sampling distribution of the sample mean will
approach a normal distribution as the sample size
increases, given that the sample size is sufficiently
large.
 Mean ± 1sd= 68 % of observation
Mean ± 2sd =95% of observation
Mean ± 3sd = 99.7% of observation
(confidence limit : 68% , 95%, 99.7

About 68% of the area lies within 1

standard deviation of the mean

68%

About 95% of the area lies within 2

standard deviations

About 99.7% of the area lies within 3 standard

deviations of the mean

13
Inference statistic :-
1. Estimation : An estimate is a numerical value
which is used to estimate the corresponding
population parameter.
• Point estimation
• Interval estimation(confidence interval)

2. Test of hypothesis (test of significances)

There are Two Methods for testing hypotheses :
(1) The Traditional Method. (t-test, z-test)
(2) The P- value Method 14
• These concepts( HT & CL) are essential for
understanding the precision and reliability of
estimates derived from sample data, as well as
for making informed decisions based on
statistical inference.
 Parametric tests
 Non parametric tests
 Regression analysis
• Parametric Tests
– T – tests
– Analysis of variance (ANOVA)
• Non parametric tests
– Mann-Whitney U Test
– Kruskal-Wallis Test
– Chi-Square Test
Each of these tests has its own assumptions, conditions, and
interpretation methods, and their selection depends on the
nature of the data and the research question being
investigated.
• Regression analysis
– Simple linear regression models
– Multiple regression
– Assumptions & limitations
– Correlation
 Choosing the Right Statistical Test
• Statistical tests are used in hypothesis testing. They can be
used to determine whether a predictor variable has a
statistically significant relationship with an outcome variable.
• Estimate the difference between two or more groups.
• Statistical tests assume a null hypothesis of no relationship
or no difference between groups. Then they determine
whether the observed data fall outside of the range of values
predicted by the null hypothesis.
• If you already know what types of variables you’re dealing
with, you can use the flowchart to choose the right statistical
test for your data.

18
• There are multiple flowcharts to guide us to
the suitable test
• Example flowchart 1
guide for choosing the most common statistical t
ests.pdf

19
Example 2

20
Example 3

21
• There are multiple flowcharts to guide us to
the suitable test. They are of variable degrees
of complexity and the number of tests
presented.
• Here, a simplified guide is presented based on
5 steps to guide us to the most common
statistical tests.

22
Choosing the proper statistical test, the five steps (5
questions):
Q1: Bivariate Vs Multivariable
– Bivariate analysis: studying the relationship between two
variables without considering any other variables e.g Age
and height
– Multivariable (regression methods): studying the effect of
multiple variables on an outcome variable. Regression is
also used for prediction e.g. The effect of smoking, sex,
coffee consumption on blood pressure

23
Q2 Difference Vs Correlation
If we are doing bivariate analysis, we need to
ask if we are studying a difference or a
correlation.
e.g.
- The difference between males and females
regarding coffee consumption.
- The association between age and weight

24
Q3: Independent data Vs Paired data
- Independent (unpaired) data: The values come
from two or more different groups, and values
in each group are not connected.
- There is no relationship between the subjects
in each sample. Also, knowing the values of
the observations in one group tells us nothing
about the observations in the other group.

25
Dependent (Paired) data: the measured values
are connected as:
When a variable is measured twice or more on
the same individual.
• Pre-test/post-test samples (a variable is measured
before and after an intervention).
• Cross-over trials.
• Matched samples.

26
Q4: Type of outcome and normality of
distribution
It is important before doing some statistical
tests to determine if a numerical variable is
normally distributed or not.

27
Q5 Number of groups /conditions
Are we comparing two groups (diseased, not
diseased), or three groups (normal,
osteopenia, osteoporosis)?

28
• Choosing the proper statistical test, the five
steps ( 5 questions):
• The five questions are arranged together in
the following guide to direct us to the suitable
test.
• guide for choosing the most common statistica
l tests.pdf

29
30