The Third factor- Effect Modification
An Example of Stratified Analysis
Salmonella after wedding dinner Disease seems to be associated with both chicken and rice But many had both chicken and rice
Exposure Cases Controls Odds ratio 95% ci
Rice 37 / 50 21 / 50 3,9 (1,7 - 9,2)
Chicken 40 / 50 20 / 50 6,0 (2,8 - 12,7)
Cake 32 / 50 27 / 50 1,5 (0,7 - 3,4)
Juice 16 / 50 20 / 50 0,7 (0,3 - 1,6
Confounding
Is rice a confounder for the chicken salmonellosis association?
Stratify: Make one 2x2 table for rice-eaters and one for non-rice-eaters (e.g. in Episheet)
Chicken Salmonellosis
Rice
No confounding
Because:
OR for chicken alone = ORmh for chicken ”controlled for rice”
Exposure Cases Controls Odds ratio 95% ci
Rice-eaters: Chicken 36 / 37 18 / 21 6,0 (0,6 - 62)
Non-rice-eaters: Chicken 4 / 13 2 / 29 6,0 (0,9 - 38)
Chicken "controlled for rice" 40 / 50 20 / 50 6,0 (1,4 - 26)
Confounding
Is chicken a confounder for the rice salmonellosis association?
Stratify: Make one 2x2 table for chicken-eaters and one for non-chicken-eaters (e.g. in Episheet)
Rice Salmonellosis
Chicken
Confounding
Because:
OR for rice alone = ORmh for rice ”controlled for chicken”
Exposure Cases Controls Odds ratio 95% ci
Chicken-eaters: rice 36 / 40 18 / 20 1,0 (0,17 - 1,0)
Non-chicken-eaters: rice 1 / 10 3 / 20 1,0 (0,09 - 11)
Rice "controlled for chicken" 37 / 50 21 / 50 1,0 (0,24 - 4,2)
Not 3,9
Conclusion
Chicken is associated with salmonellosis Rice is not associated with salmonellosis
confounding by chicken because many chicken-eaters also had rice
rice only appeared to be associated with salmonellosis
Stratification was needed to find confounding Compare crude OR to adjusted OR (ORmh) If > 10-20% difference confounding!
Exercises
Exercise 1
Confounding: exerciseHypothetical case control study
Drinker
Non-drinker
100 200
Lung cancer No lung cancer
50 50
50 150
50 1503.0
50 50OR
Q> Calculate the crude OR
Confounding: example
DrinkerNon-drinker
75 25
Lung cancer
No lung
cancer45 15
30 10
45 101.0
15 30sOR
DrinkerNon-drinker
25 175
Lung cancer
No lung
cancer5 35
20 140
5 1401.0
35 20n sOR
Smokers Non-smokers
Q> Calculate the OR for smokers Q> Calculate the OR for non-smokers
Confounding: exampleInterpretation
Drinking Lung cancerX
Smoking
• Drinking is not associated with lung caner • Smoking is a confounder
Exercises
Exercise 2
Effect modification: example
Drinker
Non-drinker
100 200
Lung cancer No lung cancer
50 50
50 150
50 1503.0
50 50OR
Q> Calculate the crude OR
Effect modification: example
DrinkerNon-drinker
60 25
Lung cancer
No lung
cancer45 15
15 10
45 102.0
15 15sOR
DrinkerNon-drinker
40 175
Lung cancer
No lung
cancer5 35
35 140
5 1400.57
35 35n sOR
Smokers Non-smokers
Q> Calculate the OR for smokers Q> Calculate the OR for non-smokers
Effect modification: exampleInterpretation
Drinking Lung cancer
Smoking
• Drinking is associated with lung cancer • Smoking is an effect modifier
Exercises
Exercise 3
Exercises
Exercise 3
The following table shows the relative risk (RR) of cigarette smoking and developing oral cancer, grouped by whether having alcohol beverage drinking habit or not. Condition
(A-D) Having alcohol
habit group Not having
alcohol habit group
Combined both having and not having alcohol
habit groups A 4.0 2.0 1.0 B 4.0 4.0 1.0 C 4.0 2.0 2.8 D 4.0 4.0 4.0
a. Which condition in the table 1 that alcohol beverage drinking is most likely to be a confounder but not a modifier? b. Which condition in the table 1 that alcohol beverage drinking is most likely to be a confounder and also a modifier? c. Which condition in the table 1 that alcohol beverage drinking is mostly likely to be a modifier but not a confounder? d. Which condition in the table 1 that alcohol beverage drinking is mostly likely neither to be a modifier nor a confounder?
BACD