STATISTICS EPIDEMIOLOGY SOLUTION

STATISTICS EPIDEMIOLOGY SOLUTION Q&A Use the space assigned after each question for your answer. All the questions must be answered, justified and show your calculations for full credit. 1. Which of the following is a case-control study? [ONE POINT] a. Study of past mortality or morbidity trends to permit estimates of the occurrence of disease in the future b. Analysis of previous research in different places and under different circumstances to permit the establishment of hypotheses based on cumulative knowledge of all known factors c. Study of the incidence of cancer in men who have quit smoking d. Obtaining histories and other information from a group of known cases and from a comparison group to determine the relative frequency of a characteristic or exposure under study e. Both a and c this is case control study because we are dealing with known cases which makes the study a case controlled study. 2. A random sample of middle age sedentary males was selected from four census tracts, and each man was examined for coronary artery disease. All those having the disease were excluded from the study. All others were randomly assigned to either an exercise group, which followed for a two-year program of systematic exercise, or to a control group, which had no exercise program. Both groups were observed semiannually for any difference in incidence of coronary heart disease. ● What type of study (study design) you would assign to this information? Why? [ONE POINT] The study design suitable for this information is randomized controlled trial because we can estimate relative risk, incidence and we can also measure any impact 3. Several studies have found that approximately 92% of cases of lung cancer are due to cigarette smoking. This measure is an example of: [ONE POINT] a. An incidence rate b. A relative risk c. A prevalence risk d. An attributable risk e. A proportionate mortality ratio this is attributable risk because it shows the difference in percent of people exposed to smoking and who don’t exposed to smoking 4. Researchers select 100 patients with colon cancer and 300 patients without colon cancer. Of the 100 patients with colon cancer, 15 smoke cigars while 40 of the 300 patients without colon cancer smoke cigars. a. Calculate a measure of association between colon cancer and cigar smoking. Show your work. [ONE POINT] Odds of exposure(case) = 15/85 = 0.18 Odds of exposure(control) = 40/360 = 0.11 Odds of ratio = 0.18/0.11 = 1.64 b. Interpret the measure of association you calculated. [ONE POINT] the odds of ratio is 1.64 which means we more chances of exposure among cases than the control group. 5. Complete the Table 1 (Table below) by calculating the polio incidence rates, disease- specific mortality rates, and case-fatality for each of the past five years. Interpret the data and the trend over time. [THREE POINTS] Table 1. Incidence, mortality and case fatality. # New Midyear Incidence Mortality Case-fatality Year Cases # Deaths Population per 100,000 per 100,000 (%) 1986 50 7 350,000 14 2 14.3 1987 62 11 374,690 17 3 17.7 1988 55 9 397,990 14 2 16.4 1989 78 18 492,755 18 4 23.1 1990 89 21 469,945 19 5 23.6 Formula used Incidence per 100,000 = (# cases*100,000)/population Mortality per 100,000 = (# Deaths*100,000)/population Case fatality = (Mortality/Incidence)*100 Questions 6 and 7 refer to the following information: OUTCOME AFTER 10 YRS At Beginning of Study CHD Developed CHD Did Not Develop 2,000 Healthy smokers 90 1,910 4,000 Healthy nonsmokers 40 3,960 The results of a 10-year cohort study of smoking and coronary heart disease (CHD) are shown above: 6. The incidence of CHD in smokers that can be attributed to smoking is: [ONE POINT] a = 90, b = 1910, c = 40 and d = 3960 Incidence of CHD in smokers = (a/b)*100 = {90/1910}*100 = 4.7% 7. The proportion of the total incidence of CHD in smokers that is attributable to smoking is: [ONE POINT] Proportion of total incidence of CHD in smokers = {[(a/(a+b))-(c/(c+d))]/(a/(a+b))}*100 □ {[(90/2000)-(40/4000)]/(90/2000)}*100 = 77.78% 8. What type of study design is considered to be the ‘gold standard’ in assessing causality? [ONE POINT] a. Cohort b. Case-control c. Ecological d. Experimental this is because the experimental study design helps us to find whether the treatment will work or not. 9. In a study of a disease in which all cases that developed were ascertained, if the relative risk for the association between a factor and the disease is equal to 1.0, then: [ONE POINT] a. The factor protects against development of the disease b. Either matching or randomization has been unsuccessful c. There is no association between the factor and the disease d. The comparison group used was unsuitable, and a valid comparison is not possible e. There is either no association or a negative association between the factor and the disease the relative risk of 1 means that there is no association because there is nothing that relates the factor with the disease. 10. To study the relationship between oral contraceptive use and ovarian cancer, CDC initiated a study – the Cancer and Steroid Hormone Study. Case-patients were enrolled through eight regional cancer registries participating in the Surveillance, Epidemiology, and End Results (SEER) program of the National Cancer Institute. a. What type of study design is this study? [ONE POINT] This is case control study b. What types of bias are of particular concern in this study? [ONE POINT] We are not able to calculate the risk ratio in this case c. What steps might you take to minimize these potential biases? [ONE POINT] We will use odd ratio for risk ratio but this is not a good approximation for risk ratio. d. The primary purpose of this study was to measure and test the association between OC use and Ovarian cancer. The distribution of exposure to OCs among cases and controls is shown in Table 2 below. Table 2. Ever-use of oral contraceptives among ovarian cancer cases and controls, Cases Controls Ever Never Total 179 1642 e. From these data, can you calculate the risk of ovarian cancer among oral contraceptive users? Why or why not? [ONE POINT] yes, we can calculate the risk of ovarian cancer among oral contraceptive using odds ratio. f. What is confounding? Under what circumstances would age be a confounder in this study? [TWO POINTS]