4exercise Of Causal Inference

Exercise of causal inference Liyan Guo Department of Epidemiology

Question1. In a large case-control study of pancreatic cancer,17% of the patients were found to be diabetic at the time of diagnosis, compared to 4% of a well-matched control group (matched by age, sex, ethnic group, and several other characteristics) that was examined for diabetes at the same time as the cases were diagnosed. It was concluded that the diabetes played a causal role in the pancreatic cancer. This conclusion: • A. Is correct • B. May be incorrect because there is on control or comparison group • C. May be incorrect because of failure to establish the time sequence between onset of the diabetes and diagnosis of pancreatic cancer • D. May be incorrect because of less complete ascertainment of diabetes in the pancreatic cancer cases • E. May be incorrect because of more complete ascertainment of pancreatic cancer in non-diabetic persons

Question2. All of the following are important criteria when making causal inferences except: • A. Consistency with existing knowledge • B. Dose-response relationship • C. Consistency of association in several studies • D. Strength of association • E. Predictive value

Question3. Several studies have found that approximately 85% of cases of lung cancer are due to cigarette smoking. This measure is an example of: • A. An incidence rate • B. An attributable risk • C. A relative risk • D. A prevalence risk • E. A proportionate mortality ratio

• Questions 4 and 5 refer to the following information: • The results of a 10-year cohort study of smoking and coronary heart disease (CHD) are shown below: Outcome After 10 YRS At Beginning of Study 2,000 Healthy smokers 4,000 Healthy nonsmokers

CHD Developed 65

CHD Did Not Developed 1,935

20

3,980

• 4. The incidence of CHD in smokers that can be attributed to smoking is: • 5. The proportion of the total incidence of CHD in smokers that is attributable to smoking is:

• The incidence of a disease that is attributable to the exposure in the exposed group can be calculated as follows: Incidence in exposed group - Incidence in nonexposed group (How much of the risk of the disease is due to exposure?) • The attributable risk as proportion of the total incidence in the exposed group that is attributable to exposure can be calculated as follows: (Incidence in exposed group - Incidence in nonexposed group) Incidence in exposed group (What proportion of the risk of the disease in exposed persons is due to exposure?)

• Questions 6 and 7 refer to the following information: • In a cohort study of smoking and lung cancer, the incidence of lung cancer among smokers was found to be 9/1000 and the incidence among nonsmokers was 1/1000. From another source we know that 45% of the total population were smokers. • 6. The incidence of lung cancer attributable to smoking in the total population is: • 7. The proportion of the risk in the total population that is attributable to smoking is:

Formula for Attributable Risk for the Total PopulationPopulation Attributable Risk (PAR)

• Incidence in total population-Incidence in nonexposed group • OR • (Incidence in smokers) (%Smokers in population) +(Incidence in nonsmokers) (%Nonsmokers in population)

• Formula for the attributable risk for the total population

p (r − 1) PAR% = p (r − 1) + 1 Where p is the proportion of the population with the characteristic or exposure and r is the relative risk (or odds ratio). OR (Incidence in total population - Incidence in nonexposed group) Incidence in total population