1. How to present data or results in Thesis?
Dr.Leeberk Raja MBBS.,MD
Consultant, Division of Community Health
Bangalore Baptist Hospital

2. Tables and charts
The kind of figure one uses depend on the type of information you want to convey and type of variable
Tables : better for presenting data
Charts: better for presenting the message

3. Types of Variables Nominal Categorical Ordinal Variables Discrete
Numerical
Discrete
Continuous

4. Nominal Individual observation which is usually a word
Variables that are mutually exclusive
No order
When categorized into two, its known as dichotomized or binary variable
Eg. Gender, Religion

5. Ordinal Rank ordered but not equal distance between variable points
The difference between moderate and severe or not necessarily the difference between mild and moderate
We can not say severe is as twice as that of mild
No arithmetic operations can be done Eg
I agree, strongly agree, very strongly agree
Mild, moderate, severe

6. Numerical- discrete
A natural order exists among possible values. Both ordering and magnitude are important
Parity, number of TB is cases in a year

7. Numerical – Continuous data
Data represents measurable quantities but not restricted to taking on certain specified values
Eg: Serum Cholesterol, height, weight
Fractional values are possible
Arithmetic applications possible
Can be transformed into discrete/ordinal/binary variable by grouping them to meaningful categories

8. Dependent and independent variables
Independent variable : (predictor) is a variable that is thought to influence another variable ( dependent)
Dependent variable: (outcome variable) is a variable that is dependent on an independent variable
Smoking and Lung cancer
When we draw a graph, dependent variable is on Y axis and independent on X-axis

9. Organizing data
When data are collected in original form, they are called raw data
When the raw data is organized into a frequency distribution, the frequency will be the number of values in a specific class of the distribution
Frequency distribution: number of times characteristic of a variable is observed in the sample
Presented in one way table or charts or graphs

10. Presenting the frequency distribution Categorical data – nominal, ordinal or grouped
Pie chart
Bar chart
Pareto diagram
Summary table

11. Continuous data Presentation
Tables (grouped)
Histogram
Polygon
Scatter plot

12. Ungrouped frequency distribution
Ungrouped frequency distribution – can be used for discrete data when the range of values in the data set is not large.
Examples – number of miles patients have to travel from home to health services

13. Table – Frequency table (ungrouped)

14. Grouped frequency distributions
Grouped frequency distributions can be used when the range of values in the continuous/discrete data set is very large. The data must be grouped into classes that are more than one unit width
Examples – weight, height, age group

15. Birth weights of babies born in an Hospital
Weight in Kg
Frequency 10 30 50
100
200
400
150

16. Guidelines for constructing a Frequency distribution
The classes must be mutually exclusive
The classes must be continuous
The classes must be equal in width

17. Two way tables for combination of variables
SES
Nutritional status (1000)
Normal
No (%)
Grade I
Grade II
Grade III
Total
Low
75 (25%)
100 (33%)
50 (17%)
300
Middle
200 (50%)
100 (25%)
75 (17%)
25 (8%)
400
High
175 (58%)
95 (25%)
30 (10%)
20 (7%)
200
100
1000

18. Guidelines for Tables
Present information in rows and columns ( orderly arranged)
Organize data in meaningful way
Clearly label rows and columns (no abbreviations)
Note units clearly
Show percents – round to nearest whole numbers
Show total numbers
Table no. and title
Identify the source of data

19. Graphs/Charts
Frequency distribution: Nominal/categorical data – Pie and bar charts Continuous data – Histogram, frequency polygon Comparing variables: Nominal/categorical – grouped or clustered bar stacked/component bar Continuous data – Polygon , scatter plot , line graph

20. Bar Chart Graphical way to organize data
Easier to read than tables, but give less details
The most informative graphs are relatively simple and self explanatory
The x-axis gives the independent variable and y-axis depicts the values of the dependent variable
Use few bars ( maximum of 6)

21. Bar charts
Simple bar charts: To display frequency distribution of nominal of ordinal variable Clustered (grouped) bar charts: Results of a cross tabulation ( eg : SES Vs nutritional status) can be well presented by clustered bars, but as there will be unequal number of people in each category, it is difficult to compare length across the categories Stacked or component bar chart: To represent the proportion of people in each category ( SES Vs nutritional status). Stack bars in a clustered one top of the other.

22. Distribution of study population by religion ( n=200)
Simple bar chart
Distribution of study population by religion ( n=200)
Bar length shows frequency or %
Equal bar widths
Zero point
Religion

23. Grouped bar chart
Menigococcal disease by quarter, Bangalore ( ) (n=535)
Number of cases
Quarter

24. Stacked or component bar chart
Menigococcal disease by quarter, Bangalore ( ) (n=535)
Proportion of cases
Quarter

25. Pie charts
Pie charts are used to represent the distribution of categorical variable .
Rules for pie charts:
Use pie charts for data that add up to some meaningful total
Never ever use three dimensional pie charts
Avoid forcing comparisons across more than one pie chart
Bar charts are better than pie charts

26. Distribution of study population by religion (n=200)
Shows breakdown of total quantity in categories
Useful for showing relative differences
Proportion should add upto 100%
Used for small number of Categories. Best for 6 or less. Max 10.
Angle size = 360/percent= 360/10=36 degree

27. Histogram
Displays data by using vertical bars of various heights to represent frequencies
Frequency distribution of continuous data
Area of each column represents number of cases
No spaces between columns
No scale breaks
Equal class intervals

28. Histogram

29. Comparison

30. Frequency polygon
Graph that displays data by using line that connect points plotted for frequencies at the midpoint of classes
The frequencies represent the heights of midpoints

31. Frequency polygon

32. Frequency polygon

33. Box and Whiskers plot
A boxplot splits the data set into quartiles. The body of the boxplot consists of a "box" (hence, the name), which goes from the first quartile (Q1) to the third quartile (Q3).
Within the box, a vertical line is drawn at the Q2, the median of the data set. Two horizontal lines, called whiskers, extend from the front and back of the box. The front whisker goes from Q1 to the smallest non-outlier in the data set, and the back whisker goes from Q3 to the largest non-outlier

34. If the data set includes one or more outliers, they are plotted separately as points on the chart. In the boxplot below, two outliers follow the second whisker

35. Scatter plot
A scatterplot is a graphic tool used to display the relationship between two quantitative variables
A scatterplot consists of an X axis (the horizontal axis), a Y axis (the vertical axis), and a series of dots. Each dot on the scatterplot represents one observation from a data set. Variables have to be on continuous scale.

36. Scatter plot
Slope refers to the direction of change in variable Y when variable X gets bigger. If variable Y also gets bigger, the slope is positive; but if variable Y gets smaller, the slope is negative.
Strength refers to the degree of "scatter" in the plot. If the dots are widely spread, the relationship between variables is weak. If the dots are concentrated around a line, the relationship is strong

37. Types of Scatterplots

38. How to present?
Association between age at onset of drinking and relapse
Row total
If p value is Write as <0.05

39. t-tests One sample ‘t’ test ‘t’ test for two independent samples
‘t’ test for two paired test

40. Comparison of two independent means (student’s t-test/unpaired t-test)
This test is used when we wish to compare two means
Independent Variable
One nominal Variable with two levels
E.g: boy/girl, smokers/non-smoking mothers
Dependent Variable
Continuous variable
E.g: marks obtained by the students in the exam, birth weight of children

41. How to present?

42. Paired ‘t’ test
Same individuals are studied more than once in different circumstances
E.g: Measurement made on the same people before and after intervention
Outcome variable should be continuous
The difference between pre-post measurements should be normally distributed.

43. How to present?

44. Examples
Objectives
To determine the prevalence of erectile dysfunction (ED) among patients with Diabetes Mellitus visiting the out patient and primary care facilities of a teaching hospital in Bangalore.
To assess the determinants of ED in the same population

45. Descriptive statistics
Age distribution ( mean, SD, range) – Categories (Tables, bar chart)
Sex distribution (pie chart
Occupation (Tables, bar chart)
No.years with DM
Peripheral neuropathy

46. Factors Contributing ED
Age Vs ED (Chi square, student ‘t’ test)
Sex Vs ED
Duration Vs ED
Peripheral neuropathy Vs ED

47. Questions?

48. Thank you!