Tables

Frequency distribution table

As a first step in exploring the data, frequency distributions of variables are commonly summarised in tables. Frequency distribution tables can be used for both categorical and numerical variables. Continuous variables should only be used with class intervals. Frequency distributions can show either the actual number of observations which fall within a given class (absolute frequency), the ratio of the absolute frequency to the total number of observations (relative frequency), or the percentage of observations (percentage frequency). A table is a data set organised in rows and columns. The simplest table includes two columns. The first column lists the categories in which data are grouped. The second column shows the number of events or individuals falling in each category (absolute frequency). A third column may show the percentage of the total that each category represents (percentage frequency).

Table 1. Number of cases of disease X by age groups, among residents of sample-city, 2009

Age groups (years)	Number of cases	Percentage (%)
0-9	422	8,3
10-19	783	15,5
20-29	565	11,2
30-39	904	17,9
40-49	237	4,7
50-59	676	13,4
60-69	898	17,7
70-79	239	4,7
80 or more	120	2,4
Unknown	220	4,2
Total	5064	100,0

Some guiding text on how to create a good table:

• The title should be concise and include the "what (or who), when and where" content of the table (i.e. description by person, place and time). The title should be preceded by a table number (e.g. Table II).
• Each row and column should be clearly and concisely labelled. Units of measurements should be indicated (e.g. years, meters, cases/1000, etc.). Categories should be mutually exclusive.
• The total of lines and columns should always be mentioned as well as missing or unknown information or any exclusion (as a special line or in footnotes).
• All of the abbreviations or codes should be explained in footnote (e.g. OR = odds ratio).
• The source of data should be mentioned in a footnote unless these are original data.
• Lines to separate columns are not needed. They are easily replaced by proper alignment and justification of columns. Horizontal lines should be reduced to the strict minimum.
• Any table, together with its title and its attached footnote should be self-explanatory. No additional text should be needed to understand the table.
• The above table shows case count with percentage of total according to one variable (age groups). Data could be segregated across a second or several other variables. This can be illustrated as follows:

Table 2. Number of cases of disease X by age groups, sex and X/Y characteristic, among residents of sample-city, 2009

ge groups (years)	Gender	Number of cases
X characteristic	Y characteristic	Total
0-9	Male
	Female
	Total
Oct/19	Male
	Female
	Total
20-29	Male
	Female
	Total
(...)

Cumulative frequency distribution table

The cumulative frequency (CF) is the running total of the frequencies; the CF that corresponds to a given value is the sum of all the frequencies up to and including that given value. A cumulative frequency distribution table has added columns that give the cumulative frequency and the cumulative percentage of the results as well. For more information, see also frequency polygons.

Table 3. Number and cumulative frequency of cases of disease X by age groups, among residents of sample-city, 2009

Age groups (years)	Number of cases	Percentage (%)	Cumulative frequency	Cumulative percentage (%)
0-9	422	8.3	422	8.3
10-19	783	15.5	1205	23.8
20-29	565	11.2	1770	35.0
30-39	904	17.9	2674	52.9
40-49	237	4.7	2911	57.6
50-59	676	13.4	3587	71.0
60-69	898	17.7	4485	88.7
70-79	239	4.7	4724	93.4
80 or more	120	2.4	4844	95.8
Unknown	220	4.2	5064	100.0
Total	5064	100.0	5064	100.0

Contingency table

Contingency tables (also known as cross tabulation or cross tab) are used to present and analyse the relation between two or more categorical variables in a matrix format. Cohort studies and case control studies are classical methods used by epidemiologists to identify association between an exposure and a disease. The crude results of such studies are frequently presented as 2-by-2 contingency tables. They can be illustrated as follows.

Table 4. General structure of a contingency table

	Disease present	Disease absent	Total
Exposed	a	b	a+b
Unexposed	c	d	c+d
Total	a+c	b+d

Cohort studies

Table 5. Cases of disease X according to consumption of food X, among customers of restaurant Y, 29 February 2009

Consumption of food X	Total	Cases	Risk %	Risk Ratio (RR)
Yes	100	40	40	2
No	50	10	20	Reference group
Total	150	50	33,3

Case-control study

Table 6. Cases of disease X and controls according to consumption of food X, among customers of restaurant Y, 29 February 2009

Consumption of food X	Cases	Controls	Odds Ratio (OR)
Yes	80	30	9,3
No	20	70	Reference group
Total	100	100

Dummy table

Although epidemiologists cannot analyse data before they are collected, they usually prepare their analysis by designing dummy tables (empty shells) which will later figure in the results. This is an important part of any plan of analysis. It allows making sure that the responses to be obtained will fit with the study design, the hypothesis tested and the way questions are asked.

Table 7. Dummy table for food specific attack rates (AR) in a cohort study - cases of gastroenteritis according to consumption of specific food items and beverages, among customers of restaurant X, date

Food item	Have eaten (exposed)				Did not eat (not exposed)
	Case	Total	AR (risk%)		Case	Total	AR (risk%)	Risk ratio	95%CI
Potato salad
Fruit salad
Tiramisu
Roasted chicken
Milk
Beer
(...)

Table 8. Dummy table for food specific attack rates in a case-control study - cases of gastroen

Food item	Cases exposed				Controls exposed
	n	N	(%)		n	N	(%)	Odds ratio	(95% CI)
Potato salad
Fruit salad
Tiramisu
Roasted chicken
Milk
Beer
(...)

FEM PAGE CONTRIBUTORS 2007

Editors

Agnes Hajdu

Original Author

Alain Moren

Contributors

Marion Muehlen

Lisa Lazareck

Agnes Hajdu