Two-by-Two Table: Cornerstone in Epidemiological Research
Two-by-Two Table: Cornerstone in Epidemiological Research
Cornerstone in epidemiological
research
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
‘Every epidemiologic study can be
summarized in a two-by-two table.’
- H. Ory
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Two-by-two Table
• Cornerstone of all
epidemiological research
• Often the first thing one draws
up when starting to investigate
some data
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Two-by-two Table
ill not ill
Exposed a b a+b
Not
c d c+d
exposed
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
The legend
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
The legend
ill not ill
not
exposed c d c+d Total number not exposed
a + c b + d Total
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Example: New Year’s Dinner Outbreak
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Food item Ill Not Ill
Eaten Not Eaten Eaten Not Eaten
Cheesecake 4 1 1 9
Eat
cheesecake 4 1 a+1
4 b=5
Total
15
a+1
4 c=5 b1 ++ d9 = 10
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Number of people who are ill
Attack Rate (AR) =
Number of population at risk
Eat
cheesecake 4 1 4+1= 5
Total = 15
4 + 1 = 5 1 + 9 = 10
5 4 1
AR = AR exposed = AR not exposed =
15 5 10
= 0.33 = 0.1
= 0.8
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Using Denominator
Infection by S.Typhimurium
Attack Rate by age group, Jura, May-June 1997
Age group Number of
(years) Cases
<1 2
1–5 36
6 – 14 22
15 – 64 29
> 65 9
Total 98
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Using Denominator
Infection by S.Typhimurium,
Attack Rate by age group, Jura, may-June 1997
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Use of Two-By-Two Table in
Measures of Association
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
ill not ill
a+b
Cohort studies
Exposed 4 1 4+1=5
c+d
Not exposed 1 9 1 + 9 = 10
Relative Risk = the risk in the exposed group divided by the risk in the unexposed group
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
case control
Case control studies
a+b
Exposed
Open well
30 25 30 + 25 = 55 When true size of the exposed
and unexposed groups is
c+d unknown
Not exposed
Open well 32 60 32 + 60 = 92 e.g., cholera cases and control and
exposure to shallow well N’Djamena,
a+c b+d Chad, July 2001
30+32 = 62 25+60 = 85
ad
Odds Ratio (OR) = bc
30 x 60
= 25 x 32
OR = 1 no association 1800
OR > 1 there is association = 800
= 2.25
Odds Ratio = the odds for cases divided by odds for control
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
References
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation
Two-by-Two Table
SEARO – CSR Training on Outbreak Investigation