Biostatistics (Measures of Central Tendency, Tests of Significance, Sampling) MCQs

Community Medicine (PSM) · 247 free questions with answers & explanations.

1. In a community survey on haemoglobin levels, the data are highly skewed due to a few severely anaemic individuals. Which measure of central tendency best represents the typical haemoglobin level of this population?
2. A researcher wants to determine if the mean blood glucose levels differ significantly between diabetics treated with metformin versus diet control alone. With two independent normally distributed groups and equal variances, which statistical test is most appropriate?
3. In a village with 500 households divided into 50 clusters, a researcher randomly selects 10 clusters and surveys all households within those clusters. This sampling method is called:
4. A study finds p = 0.03 for an association between hypertension and stroke. The 95% confidence interval for the relative risk is 1.4 to 5.2. Which of the following statements is CORRECT?
5. Which of the following is a NON-PARAMETRIC test used to compare more than two independent groups when data are not normally distributed?
6. In a dataset of serum cholesterol values, the mean is 220 mg/dL, median is 205 mg/dL, and mode is 195 mg/dL. The distribution is:
7. A researcher compares mean birth weight across three independent groups (normal, preeclamptic, and diabetic mothers). The appropriate single statistical test is:
8. A sample of 400 adults shows a mean systolic BP of 128 mmHg with SD of 20 mmHg. The 95% confidence interval for the population mean is approximately:
9. In stratified random sampling for a TB survey across 5 districts, the number sampled from each district is proportional to its population size. This method is called:
10. A large trial reports p = 0.03 with 95% CI for RR being 1.02–1.08. The most accurate interpretation is:
11. A researcher studying hemoglobin levels in a population with highly skewed distribution including several extreme outliers wants to compare values between two groups. Which measure of central tendency and which non-parametric test are most appropriate, respectively?
12. In a clinical trial, the calculated p-value is 0.04. A 95% confidence interval for the mean difference is reported as (0.2 to 4.8 units). Which statement is most accurate about the relationship between p-value and confidence interval in this context?
13. A health survey uses stratified random sampling to ensure representation from rural and urban areas. The urban stratum has 10,000 people and the rural stratum has 40,000 people. Using proportional allocation with a total sample of 1,000, how many should be sampled from the urban stratum?
14. A researcher tests whether a new vaccine reduces the incidence of measles by comparing proportions between vaccinated and unvaccinated groups using a chi-square test. The degrees of freedom for a 2×2 contingency table used in this analysis is:
15. A study reports a standard deviation of 10 for hemoglobin levels with a sample size of 100 subjects. If the same study were repeated with 400 subjects but the same standard deviation, the standard error of the mean would change from its original value by a factor of:
16. A Type II error in a clinical trial means:
17. A researcher computes a Mann-Whitney U test instead of an independent-samples t-test for comparing pain scores between two treatment groups. The most appropriate reason for this choice is:
18. A study reports: mean hemoglobin = 11.2 g/dL, median = 10.8 g/dL, mode = 10.5 g/dL. Which of the following best describes the distribution of this data?
19. In a clinical trial, a new drug reduces blood pressure by a mean of 2 mmHg (95% CI: 1.8–2.2 mmHg, p < 0.001). A clinician states the result is not clinically meaningful. The discrepancy between the statistical and clinical conclusions is best explained by:
20. A public health researcher wants to estimate the prevalence of anaemia in rural India with a 95% confidence level and an acceptable error of 5%. The assumed prevalence is 40%. Using the standard formula n = Z²pq/d², the minimum sample size required is approximately:
21. A researcher conducting multiple comparisons across 20 outcomes uses alpha = 0.05 for each test without correction. The probability of committing at least one Type I error across all 20 tests is approximately:
22. A clinical trial reports that a new drug reduces systolic BP by 3 mmHg with p = 0.001 but 95% CI of 1–5 mmHg. A physician is deciding whether to prescribe this drug. The MOST appropriate conclusion is:
23. A researcher performs multiple subgroup analyses in a single RCT without pre-specifying them in the protocol. The probability of a Type I error across all comparisons is BEST reduced by:
24. In a study comparing 5-year survival rates among 4 different chemotherapy regimens, which statistical test is MOST appropriate if survival times are not normally distributed?
25. A sampling frame lists all 2,500 households in a district. Every 10th household is selected to form a sample of 250. This method is called:
26. In a study, the mean serum cholesterol is 200 mg/dL with a standard deviation of 20 mg/dL. What percentage of the population would be expected to have cholesterol levels between 160 and 240 mg/dL, assuming a normal distribution?
27. A clinical trial comparing a new antihypertensive with placebo reports p = 0.04. Which of the following statements is CORRECT?
28. In a right-skewed distribution of household incomes in a village, which measure of central tendency is MOST appropriate to represent the typical household income?
29. A researcher wants to compare mean blood glucose levels across three dietary groups (low-carb, moderate-carb, high-carb). The data are normally distributed. The MOST appropriate statistical test is:
30. In a survey of 1000 adults, 400 have hypertension. The 95% confidence interval for the prevalence is 36.96%–43.04%. If the sample size were increased to 4000 with the same observed prevalence (40%), the 95% CI would:
31. A Type II error (β error) in a clinical trial means:
32. A study reports that a new drug reduces systolic blood pressure by 2 mmHg (p = 0.001) in a trial of 50,000 patients. A clinician states the result is clinically insignificant. The discrepancy between statistical significance and clinical significance is BEST explained by:
33. In a skewed distribution of hospital stay duration for appendicectomy patients (positively skewed, range 1–45 days), the best measure of central tendency to report for policy planning is:
34. A researcher compares mean birth weights across four ethnic groups using multiple pairwise t-tests (6 comparisons). The probability of committing at least one Type I error across all comparisons, assuming α = 0.05 per test, is approximately:
35. In a cluster randomized trial of a health education intervention in villages, the design effect (DEFF) is calculated as 2.8. This means the effective sample size is:
36. Which non-parametric test is the most appropriate substitute for a one-way ANOVA when the data are ordinal and the normality assumption is violated across three independent groups?
37. In a distribution of 200 blood glucose values, the mean is 110 mg/dL, median is 95 mg/dL, and mode is 85 mg/dL. This distribution is best described as:
38. A researcher finds a p-value of 0.03 in a study comparing two means. After applying Bonferroni correction for 10 simultaneous comparisons, the adjusted significance threshold is 0.005. The conclusion should be:
39. A clinical trial reports a 95% confidence interval for the mean difference in systolic blood pressure between treatment groups as (-2 mmHg to +8 mmHg). Which interpretation is CORRECT?
40. In a community health survey, every 10th household is selected from a list of 5,000 households after a random start between 1 and 10. This sampling technique is:
41. Paired observations of blood pressure before and after treatment in 30 patients show non-normally distributed differences. The most appropriate statistical test is:
42. A researcher reports that a new diagnostic test has a likelihood ratio positive (LR+) of 15 and a pretest probability of disease of 20%. Using Fagan's nomogram logic, the approximate post-test probability is closest to:
43. In a clinical trial with a continuous outcome, the investigators use a paired t-test instead of an unpaired t-test. The primary statistical consequence of correct pairing is:
44. A dataset of daily caloric intake (kcal) for 200 adults is positively skewed. Which measure of central tendency should be reported and why?
45. A clinical trial randomizes 50 hypertensive patients to drug A and 50 to drug B. Mean SBP reduction was 12 mmHg (SD 8) vs 9 mmHg (SD 10). The appropriate test to compare these means is:
46. In a study comparing outcomes across 4 groups with continuous normally distributed data, the investigator performs 6 pairwise t-tests. The major methodological problem is:
47. A study reports p = 0.03 for a new antihypertensive drug's superiority. The 95% confidence interval for mean SBP reduction is 1–3 mmHg. How should clinicians interpret this finding?
48. Systematic sampling is used to select a study sample. Every 10th person from a numbered list of 500 is selected after a random start. What is the major risk specific to this method?
49. A randomized trial reports that the relative risk reduction (RRR) of a new drug for MI prevention is 30%, with an absolute risk reduction (ARR) of 1.5%. The Number Needed to Treat (NNT) is:
50. In a cluster randomized trial of a school-based nutrition intervention, the intra-class correlation coefficient (ICC) is 0.05. The design effect (DEFF) for a cluster size of 40 children per school is:
51. When comparing means of a continuous variable between three or more independent groups, the appropriate statistical test is ANOVA. Which assumption of one-way ANOVA is MOST commonly tested using Levene's test?
52. A study compares blood pressure reduction (mmHg) after two antihypertensive drugs in 30 matched pairs of hypertensive patients. BP reduction is approximately normally distributed. Which statistical test is MOST appropriate?
53. A prospective study of 500 patients reports a hazard ratio (HR) of 1.85 (95% CI: 1.10–3.12, p=0.02) for developing cardiovascular disease in patients with metabolic syndrome vs those without. Which interpretation of this hazard ratio is MOST accurate in a Cox proportional hazards model?
54. In a clinical trial, the p-value for the primary endpoint is 0.03. The investigators conclude this provides 'strong evidence against the null hypothesis'. However, the sample size was 12 patients per group. Which concept BEST challenges the validity of this conclusion?
55. A clinical trial comparing two antihypertensive drugs reports a p-value of 0.04 for the primary outcome. The study was powered at 80% with α=0.05. Which statement is most accurate regarding interpretation of this result?
56. In a community health survey comparing malnutrition rates across 5 socioeconomic groups, the appropriate test of significance to use is:
57. Number Needed to Treat (NNT) is calculated as the reciprocal of:
58. A pharmaceutical trial reports a p-value of 0.03 for the primary outcome. The 95% confidence interval for the difference in means is −0.1 to 4.5 units. The MOST appropriate clinical interpretation is:
59. In a community survey, the ASHA worker records nutritional status of all children in her village. This sampling method — including all members of the accessible population — is termed:
60. A study comparing mean haemoglobin levels between three groups (tribal, rural, and urban children) uses ANOVA. The F-ratio is 8.6 and p=0.001. The ANOVA result tells us:
61. The term 'power' of a study (1−β) refers to:
62. A drug trial finds p = 0.04. Which interpretation is most accurate?
63. In stratified random sampling for a national nutrition survey, the country is divided into urban/rural strata and samples are drawn proportional to strata size. Compared to simple random sampling, this method:
64. A researcher conducts a study and reports a p-value of 0.03. The pre-specified alpha was 0.05. Which of the following interpretations is CORRECT?
65. In a cross-sectional survey of 1,200 adults, cluster sampling was performed by randomly selecting 30 villages and then interviewing all adults in each selected village. The design effect (DEFF) was 2.1. What does this imply about the effective sample size?
66. In a study comparing mean blood pressure between two independent groups, an independent samples t-test gives p = 0.03. The 95% confidence interval for the mean difference is 2 to 18 mmHg. The correct interpretation is:
67. A researcher studies correlation between serum vitamin D levels (continuous, non-normally distributed) and muscle strength (continuous, normally distributed). The most appropriate statistical test is:
68. In cluster sampling used for vaccine coverage surveys, the EPI coverage survey methodology uses 30 clusters of 7 children each. A limitation unique to cluster sampling compared to simple random sampling is:
69. A pharmaceutical company researcher observes that a new antidiabetic drug reduces HbA1c by a statistically significant 0.1% (p < 0.001, n = 50,000). A clinician states this result is not clinically significant. This discrepancy illustrates:
70. In a community survey, all households in a village are listed serially. Every 10th household is selected starting from a random number between 1 and 10. This sampling method is called:
71. A researcher tests whether a new drug reduces SBP more than placebo. The null hypothesis is H₀: mean SBP difference = 0. The study finds p = 0.03. If the true treatment difference is zero (drug has no real effect), this result represents:
72. In a district immunisation survey using 30-cluster EPI methodology, clusters are selected by probability proportional to size (PPS). The primary advantage of PPS over simple random cluster selection is:
73. The Number Needed to Treat (NNT) to prevent one adverse outcome is calculated as the reciprocal of:
74. In a community survey of 500 adults, the mean systolic BP is 126 mmHg with a standard deviation of 14 mmHg. Assuming a normal distribution, what percentage of individuals are expected to have systolic BP between 112 and 140 mmHg?
75. A study comparing mean hemoglobin levels in three dietary groups (vegetarian, vegan, omnivore) uses which statistical test?
76. In a clinical trial, the p-value for a primary outcome is 0.04 (alpha = 0.05). The 95% confidence interval for the relative risk is 1.08 to 3.42. The correct interpretation is:
77. In systematic sampling, a list of 1,200 students is available, and a sample of 100 is needed. The sampling interval is 12. If the random start is number 7, which of the following is NOT selected?
78. In a screening program, a test with sensitivity 90% and specificity 80% is applied to a population with a disease prevalence of 2%. The positive predictive value (PPV) is approximately:
79. The kappa statistic (Cohen's kappa) is used to measure:
80. In a study with 95% power and 5% type I error (two-sided), if the investigators reduce the acceptable type I error to 1% while keeping all else constant, the required sample size will:
81. The 'receiver operating characteristic' (ROC) curve is used to:
82. In a clinical trial, statin therapy reduces 5-year cardiovascular death from 8% (placebo) to 5% (statin). The Number Needed to Treat (NNT) to prevent one cardiovascular death over 5 years is:
83. In a screening programme for type-2 diabetes, a test has sensitivity 80% and specificity 90%. The prevalence of disease in the population is 10%. Using Bayes' theorem, the Positive Predictive Value (PPV) of this test is:
84. A study tests a new cardiac biomarker. The Receiver Operating Characteristic (ROC) curve for this marker gives an Area Under the Curve (AUC) of 0.72. Which statement best describes this result?
85. A clinical trial finds that 20% of patients in the treatment arm and 30% in the placebo arm develop the outcome. The Number Needed to Treat (NNT) to prevent one additional outcome is:
86. A meta-analysis combines results from 8 randomised trials on antihypertensive therapy. The I² statistic is 75%. This indicates:
87. A likelihood ratio positive (LR+) of 10 for a diagnostic test means:
88. In a study of 200 subjects, a new point-of-care test for tuberculosis is compared with culture (gold standard). Among 50 culture-positive subjects, 40 test positive. Among 150 culture-negative subjects, 30 test positive. The specificity of the new test is:
89. The Mann-Whitney U test is the non-parametric equivalent of which parametric test?
90. A stratified analysis reveals that the association between smoking and lung cancer is 8.0 (OR) in men and 7.8 in women, with a Mantel-Haenszel pooled OR of 7.9. The sex-stratified ORs differ from the crude OR of 7.9 by <5%. This finding is most consistent with:
91. In a cohort study of 2000 individuals, an exposed group of 1000 had 80 events and an unexposed group of 1000 had 40 events. The Number Needed to Harm (NNH) is:
92. A screening test for cervical cancer is applied to 500 women with confirmed disease and 500 without disease. The test is positive in 450 women with disease and 50 without disease. The Positive Predictive Value (PPV) at this prevalence of 50% is:
93. In a study, the 95% confidence interval for Relative Risk (RR) is reported as 1.4 (0.9–2.1). The correct interpretation is:
94. A researcher compares the effectiveness of three antihypertensive regimens in reducing SBP by repeatedly measuring the same 20 patients under each regimen. The most appropriate statistical test is:
95. In a meta-analysis, the I² statistic is reported as 72%. This indicates:
96. A clinical trial reports an Odds Ratio of 0.45 with p = 0.03 for a new drug reducing stroke. The absolute risk in the control group is 20%. The approximate Number Needed to Treat (NNT) is closest to:
97. A study compares the proportion of smokers developing lung cancer using logistic regression. The model controls for age, gender, and occupational exposure. The resulting measure of association produced by logistic regression is:
98. In a systematic review using GRADE methodology, a well-conducted RCT that shows serious risk of bias would be downgraded to:
99. In a study evaluating a new rapid antigen test for typhoid, the receiver operating characteristic (ROC) curve is plotted. The area under the ROC curve (AUROC) is 0.91. Which of the following is the MOST accurate interpretation of this finding?
100. A researcher applies chi-square test to a 2×2 contingency table where one cell has an expected frequency of 2.5. Which correction should be applied and why?
101. In a cohort study of 1000 hypertensive patients, 500 received a new antihypertensive and 500 received standard therapy. After 5 years, 40 in the new therapy group and 80 in the standard therapy group suffered a stroke. What is the Number Needed to Treat (NNT) to prevent one stroke?
102. A rapid diagnostic test for malaria has sensitivity of 90% and specificity of 80%. In a low-endemicity district the prevalence of malaria is 20%. What is the Positive Predictive Value (PPV) of the test in this district?
103. A new diagnostic test for tuberculosis has sensitivity 85% and specificity 90%. In a district with TB prevalence of 20%, what is the Positive Predictive Value (PPV) of this test?
104. A confidence interval for a risk ratio is reported as 1.4 (95% CI: 1.1–1.8) with a p-value of 0.003. Which of the following conclusions is MOST appropriate?
105. In a cluster randomised trial of a school-based health intervention, the intra-cluster correlation coefficient (ICC) is 0.05 and cluster size is 40. What is the design effect (DEFF)?
106. A study reports a pre-test probability of 30% for coronary artery disease in a patient. The positive likelihood ratio (LR+) of the exercise stress test used is 5. What is the approximate post-test probability of disease after a positive result?
107. A meta-analysis of 8 RCTs evaluating aspirin for prevention of myocardial infarction shows significant heterogeneity with I² = 75%. Which of the following is the MOST appropriate statistical model and interpretation?
108. A researcher wishes to compare mean birth weights across three dietary groups using parametric analysis. After applying the Shapiro-Wilk test, the data in one group shows significant non-normality (p = 0.02). Which is the MOST appropriate non-parametric alternative to one-way ANOVA?
109. In a clinical trial, 200 patients were randomised: 100 received the new drug and 100 received placebo. Events (death) occurred in 20 drug-group patients and 40 placebo-group patients. What is the Number Needed to Treat (NNT)?
110. A screening test is applied to a population where disease prevalence is 1%. The test has 99% sensitivity and 99% specificity. What is the Positive Predictive Value (PPV)?
111. A researcher calculates an Odds Ratio of 3.5 with a 95% confidence interval of 1.2 to 10.4 for the association between smoking and disease X. Which statement is MOST appropriate?
112. Which of the following measures is MOST appropriate for describing the central tendency of data on monthly income in a city where a few executives earn extremely high salaries?
113. In a study, the correlation coefficient (r) between height and weight of children is found to be +0.82. What percentage of variance in weight is explained by height?
114. A researcher wants to compare mean blood pressure before and after an intervention in the SAME group of 30 patients. Which statistical test is MOST appropriate?
115. A meta-analysis reports a pooled Relative Risk (RR) of 0.75 (95% CI: 0.60–0.94) for a preventive intervention. This means the intervention:
116. A non-parametric alternative to the independent samples t-test for two unpaired groups with non-normal data distribution is:
117. In a cohort study on 500 exposed and 500 unexposed individuals followed for 5 years, 50 exposed developed disease versus 20 unexposed. The Attributable Risk (AR) is:
118. Which type of bias occurs when cases recall past exposures differently from controls, leading to differential misclassification?
119. A researcher calculates the 95% confidence interval for a mean as 48.2 to 55.8. A second study using the same sample size finds a 99% confidence interval for the same parameter. Which of the following correctly describes the expected change?
120. In a study comparing mean blood glucose values between diabetics and controls using an independent samples t-test, the p-value is 0.03. The researcher then discovers that the data violates the normality assumption. Which non-parametric test is the most appropriate alternative?
121. A study of 1000 individuals finds systolic blood pressure data with mean = 120 mmHg and standard deviation = 10 mmHg. Assuming normal distribution, the number of individuals expected to have SBP between 110 and 130 mmHg is approximately:
122. In cluster sampling, a city is divided into 50 ward clusters, and 10 clusters are randomly selected; all households in selected clusters are surveyed. Compared to simple random sampling with equal total sample size, cluster sampling typically:
123. A case-control study finds an odds ratio of 3.5 with a 95% CI of 1.2 to 10.2. The p-value is 0.02. Which of the following statements is MOST accurate?
124. A meta-analysis reports an I² statistic of 78%. What does this indicate?
125. A researcher uses stratified random sampling to study hypertension prevalence, stratifying by age (<40, 40–60, >60). Compared to simple random sampling, this approach is MOST advantageous when:
126. In a 2×2 contingency table for a screening test, the test correctly identifies 90 of 100 true cases (diseased) and correctly excludes 135 of 150 non-cases. Compute the positive predictive value if the test is used in a population with 40% disease prevalence.
127. A Receiver Operating Characteristic (ROC) curve is plotted for a new biomarker. The area under the curve (AUC) is 0.62. This indicates that the test:
128. A study finds a correlation coefficient (r) of 0.82 between dietary fat intake and serum LDL. The coefficient of determination (r²) is approximately 0.67. What does r² = 0.67 indicate?
129. In a community screening study, a new diagnostic test is evaluated. Of 100 patients with the disease, 90 test positive. Of 200 truly healthy individuals, 180 test negative. The positive predictive value of this test in a population with 10% disease prevalence is:
130. A clinical trial evaluates a new antihypertensive drug. The incidence of stroke in the treatment group is 3% and in the placebo group is 8% over 5 years. The Number Needed to Treat (NNT) to prevent one stroke is:
131. A case-control study examines smoking and oral cancer. Among 50 cases, 40 are smokers. Among 50 controls, 20 are smokers. The Odds Ratio for oral cancer associated with smoking is:
132. In a food poisoning outbreak, 150 out of 500 people who attended a wedding banquet developed gastroenteritis. The attack rate is:
133. A cohort study of factory workers reveals 50 new cases of occupational lung disease over 5 years of follow-up among 1000 person-years of observation. The incidence rate is:
134. During a cholera outbreak, 200 patients died out of 2000 confirmed cases. The Case Fatality Rate (CFR) is:
135. A biostatistician wants to compare blood pressure measurements before and after a yoga intervention in the same group of hypertensive patients. The most appropriate statistical test is:
136. In a normally distributed dataset of haemoglobin values, the mean is 12 g/dL and standard deviation is 2 g/dL. Approximately what percentage of values fall between 10 and 14 g/dL?
137. A Type II (beta) error in hypothesis testing refers to:
138. The measure of central tendency least affected by extreme outliers in a skewed distribution is:
139. A new diagnostic test for diabetes is evaluated in 1000 individuals: 80 true positives, 20 false negatives, 40 false positives, and 860 true negatives. The specificity of the test is:
140. In a clinical trial comparing a new antihypertensive with placebo, the absolute risk of cardiovascular events was 12% in the placebo group and 6% in the treatment group. The Number Needed to Treat (NNT) is:
141. In stratified random sampling, the main advantage over simple random sampling is:
142. A study comparing mean blood glucose levels among three diet groups (low-carb, Mediterranean, standard) should use which statistical test?
143. In a frequency distribution that is positively skewed, the correct relationship among measures of central tendency is:
144. A study on weight reduction shows a p-value of 0.04 with 95% confidence interval for mean weight loss of −0.2 kg to −5.8 kg. The MOST correct interpretation is:
145. In cluster sampling used for national health surveys, the primary advantage is:
146. In a study comparing two diagnostic tests on the same patients, the agreement beyond chance is assessed using Cohen's kappa. If the observed agreement is 0.80 and the expected agreement by chance is 0.50, what is the kappa value?
147. A Bland-Altman plot is constructed to compare a new portable spirometer with the gold-standard lab spirometer for FEV1 measurements. The mean difference (bias) is +0.12 L and the standard deviation of differences is 0.15 L. What are the 95% limits of agreement?
148. In a logistic regression analysis, the odds ratio for hypertension associated with obesity is 2.8 (95% CI: 1.4–5.6, p = 0.004) after adjusting for age and sex. Which statement BEST describes this result?
149. A survival analysis using the Kaplan-Meier method shows median survival of 24 months for drug A versus 18 months for drug B, with the log-rank test p = 0.03. What does this result indicate?
150. In a meta-analysis, the I² statistic is reported as 78%. What does this MOST accurately indicate?
151. An ROC curve analysis compares three diagnostic tests for detecting latent TB infection. Test A has AUC = 0.91, Test B has AUC = 0.74, and Test C has AUC = 0.50. Which statement is CORRECT?
152. In a study on malaria treatment, the NNT (Number Needed to Treat) is calculated. In the control group 40% develop severe malaria; in the treatment group 20% develop severe malaria. What is the NNT?
153. The E-value in epidemiology is used to assess unmeasured confounding. If an observed RR of 2.5 has an E-value of 4.5, what does this mean?
154. In a study of 200 patients, the sensitivity of a diagnostic test is 80% and specificity is 90%. The prevalence of disease in this population is 10%. Using Bayes' theorem, the Positive Predictive Value (PPV) of this test is closest to:
155. A researcher compares mean blood pressure before and after a dietary intervention in the same 30 participants. The most appropriate statistical test to use is:
156. A study reports an odds ratio of 3.5 with a 95% confidence interval of 1.2 to 10.3. Which of the following statements is most accurate?
157. In a community survey, households are first stratified by socioeconomic status, and then a random sample is drawn from each stratum. This type of sampling is called:
158. In a clinical trial, 100 patients received Drug A and 100 received placebo. Event rate in drug group = 10%, in placebo = 20%. The Number Needed to Treat (NNT) is:
159. In a distribution that is positively skewed, the correct order of measures of central tendency is:
160. A systematic review of 12 randomized controlled trials shows heterogeneity (I² = 75%). The most appropriate method of analysis in this scenario is:
161. Which of the following describes the 'power' of a statistical test?
162. In a study of 500 patients, the sensitivity and specificity of a new test are each 90%. The prevalence of the disease is 10%. The positive predictive value (PPV) is closest to:
163. In a survival analysis, a patient who withdraws from the study before the event occurs is described as:
164. A researcher compares blood pressure reduction across four drug groups. The appropriate statistical test for comparing means of a continuous variable across more than two independent groups is:
165. In a study evaluating a new diagnostic test against a gold standard, the area under the ROC curve (AUC) is 0.50. This indicates that the test:
166. In a clinical trial where the control event rate is 20% and the experimental event rate is 10%, the Number Needed to Treat (NNT) is:
167. Non-parametric equivalent of the paired t-test, used when data does not follow normal distribution and involves matched pairs, is:
168. In a community survey using cluster sampling, one cluster has 500 households and another has 50 households, yet each is selected with equal probability. This represents a problem of:
169. A clinical trial reports a p-value of 0.03 for the primary outcome. The most accurate interpretation is:
170. A Type II error (beta error) in hypothesis testing is defined as:
171. In a dataset of exam scores: 45, 50, 50, 55, 60, 200 — the measure of central tendency least affected by the extreme value (200) is:
172. In a case-control study on obesity and type 2 diabetes, the matched odds ratio is calculated using the McNemar's test rather than the standard chi-square test. This is because:
173. A new rapid diagnostic test for tuberculosis is evaluated in 1000 subjects (100 with TB confirmed by culture, 900 without TB). The test is positive in 90 of the 100 TB cases and also in 90 of the 900 non-TB subjects. The negative predictive value (NPV) of this test is:
174. In the context of screening, the Likelihood Ratio Positive (LR+) combines sensitivity and specificity into a single measure. For a test with sensitivity 85% and specificity 90%, LR+ is:
175. Pearson's correlation coefficient (r) ranges from -1 to +1. An r value of -0.85 between hours of physical activity and blood glucose levels indicates:
176. In a clinical trial, the p-value for comparing two treatment arms is 0.03. The pre-specified significance level (alpha) is 0.05 and power (1-beta) is 0.80. Which statement about the study result is MOST accurate?
177. A researcher calculates a 95% confidence interval for a risk ratio as 1.8 (95% CI: 1.2–2.7). What is the correct interpretation?
178. In a study with 200 participants, 100 are assigned to drug A and 100 to placebo. Among drug A group, 20 develop the outcome; among placebo group, 40 develop the outcome. What is the Number Needed to Treat (NNT)?
179. A new diagnostic test for diabetes is evaluated in 1000 individuals: 200 have diabetes (gold standard). The test is positive in 180 of the 200 diabetics and in 60 of the 800 non-diabetics. What is the Positive Predictive Value (PPV)?
180. A paired t-test is used to compare pre- and post-treatment blood pressure measurements in the same group of patients. The assumption underlying this test (compared to independent samples t-test) is:
181. Which statistical test is most appropriate for comparing the proportion of adverse events in three independent groups (e.g., three different drug regimens)?
182. A study reports that the correlation coefficient (r) between serum cholesterol and BMI is +0.62 (p < 0.001). What does this indicate?
183. In a skewed distribution, which measure of central tendency best represents the 'typical' or central value of the data?
184. In a study, ROC (Receiver Operating Characteristic) curve analysis of two diagnostic tests yields AUC values of 0.92 and 0.67 respectively. What can be correctly inferred?
185. A systematic review pools data from 8 RCTs using meta-analysis. The I² statistic is reported as 74%. What does this indicate?
186. In a study of 200 patients with hypertension, the mean systolic blood pressure is 148 mmHg with a standard deviation of 12 mmHg. A researcher wants to test whether this mean differs from the population mean of 145 mmHg. Which test is MOST appropriate?
187. A clinical trial shows a new drug reduces LDL cholesterol by a mean of 18 mg/dL (95% CI: 14 to 22 mg/dL, p=0.002). Which statement about this result is CORRECT?
188. A study screening 1000 individuals for diabetes finds 100 true positives, 50 false positives, 820 true negatives, and 30 false negatives. Calculate the Positive Predictive Value (PPV).
189. In a randomized controlled trial, the absolute risk in the treatment group is 10% and in the control group is 25%. What is the Number Needed to Treat (NNT)?
190. A researcher is comparing mean blood glucose levels among three groups of patients receiving different dietary interventions. Which statistical test is MOST appropriate assuming normal distribution?
191. A systematic review pools data from 5 studies on a new antihypertensive drug. The I² statistic is reported as 78%. What does this indicate?
192. In a village survey, households are selected by first dividing the village into 10 blocks, then randomly selecting 5 households from each block. This sampling method is called:
193. In a cohort study, the incidence of coronary artery disease in smokers is 40 per 1000 person-years and in non-smokers is 10 per 1000 person-years. The Attributable Risk Percent (AR%) in smokers is:
194. A receiver operating characteristic (ROC) curve is plotted for a new diagnostic test. The area under the curve (AUC) is 0.55. This indicates that the test:
195. In a case-control study on lung cancer, the odds of exposure to asbestos among cases were 4:1 and among controls were 1:1. The Odds Ratio (OR) is:
196. A researcher studies systolic blood pressure (SBP) in 200 hypertensive patients. The mean SBP is 158 mmHg with a standard deviation of 20 mmHg. If SBP is normally distributed, the percentage of patients expected to have SBP between 138 and 178 mmHg is:
197. A study finds the median family income in a district to be Rs 18,000/month while the mean is Rs 32,000/month. The most appropriate interpretation is:
198. In a randomised controlled trial comparing two antihypertensive drugs, the outcome is reduction in SBP (a continuous variable). The data is normally distributed and group sizes are equal (n=45 each). The most appropriate statistical test is:
199. A study in 5 villages reports the following malaria incidence rates per 1000 population: 12, 15, 18, 22, and 83. The MOST appropriate measure of central tendency to represent this data is:
200. A district has 50,000 children aged 12–23 months. To estimate measles vaccination coverage, a two-stage cluster sampling is done: 30 clusters are selected, and 7 children are sampled per cluster. This design is BEST described as:
201. The sensitivity of a screening test for cervical cancer is 80% and specificity is 90%. In a population of 1000 women where the prevalence of cervical cancer is 10%, the Positive Predictive Value (PPV) is:
202. A study reports a chi-square value of 9.21 with 2 degrees of freedom. Based on the chi-square distribution table (p<0.01 at χ²=9.21 for 2 df), the conclusion is:
203. The number needed to treat (NNT) is BEST defined as:
204. In a cross-sectional survey of 1000 individuals, 40 have hypertension and of these 28 are on antihypertensive treatment. Of the 28 treated, 20 have controlled BP (< 140/90 mmHg). What is the proportion of hypertensives with controlled hypertension among all hypertensives?
205. A sensitivity of 80% and specificity of 90% is reported for a screening test. In a population where disease prevalence is 10%, what is the Positive Predictive Value (PPV)?
206. In a randomized controlled trial, 200 patients received a new drug and 200 received placebo. Events occurred in 40 drug group and 60 placebo group patients. What is the Number Needed to Treat (NNT)?
207. A study reports a Relative Risk of 2.5 with a 95% confidence interval of 1.8–3.5 and a p-value of 0.001. Which statement is MOST accurate about this finding?
208. In a cohort study of 500 exposed and 500 unexposed individuals followed for 5 years, 50 exposed and 20 unexposed developed the outcome. What is the Attributable Risk Percent (AR%) in the exposed?
209. For comparing proportions from two independent groups in a cross-sectional study, which test is MOST appropriate?
210. A diagnostic study reports Sensitivity = 75%, Specificity = 85%, prevalence = 20%. What is the Negative Predictive Value (NPV)?
211. In a study comparing a new diagnostic test to the gold standard in 200 patients, 60 have the disease. The test correctly identifies 48 true positives and 128 true negatives. What is the specificity?
212. In a clinical trial, the Odds Ratio (OR) for an outcome comparing a new drug to placebo is 0.4 (95% CI 0.2–0.8). How should this be interpreted?
213. Which sampling method ensures that every member of the population has an EQUAL and INDEPENDENT chance of selection?
214. In a study, a diagnostic test for pulmonary tuberculosis is evaluated. Among 200 truly positive patients, 170 test positive. Among 300 truly negative individuals, 240 test negative. What is the positive likelihood ratio (LR+) of this test?
215. A meta-analysis reports a pooled odds ratio of 2.1 (95% CI: 1.8–2.5, I² = 72%). Which statement BEST describes the interpretation of the I² value?
216. A researcher tests whether a new screening tool reduces mortality in a population of 1000 participants. The mortality in the control group is 8% and in the intervention group is 5%. What is the Number Needed to Screen (NNS) to prevent one death?
217. In a study on hypertension prevalence, the mean SBP is 135 mmHg with a standard deviation of 15 mmHg. The distribution is perfectly normal. What percentage of the population has SBP between 105 mmHg and 165 mmHg?
218. A clinical researcher wants to compare mean blood glucose levels across four treatment groups. The data are normally distributed and variances are equal. Which statistical test is MOST appropriate?
219. In a ROC curve analysis for a cardiac biomarker, the area under the curve (AUC) is 0.92. What does this BEST indicate?
220. A study reports a p-value of 0.003 for a difference in mean HbA1c between two groups. Which interpretation is CORRECT?
221. Which sampling method is MOST appropriate when a researcher wants to ensure equal representation from each of 5 geographical zones, and from each zone selects individuals using a random process?
222. A researcher constructs a ROC curve for a new biomarker to diagnose early sepsis. The area under the ROC curve (AUC) is 0.92. Which statement BEST interprets this result?
223. In a study of 200 patients, a diagnostic test yields TP=72, FP=18, FN=8, TN=102. What is the Positive Likelihood Ratio (LR+)?
224. A randomised controlled trial reports a relative risk reduction (RRR) of 30% with a control event rate of 10%. What is the number needed to treat (NNT)?
225. A confidence interval for an odds ratio is reported as 1.8 (95% CI: 0.9–3.6). Which conclusion is MOST appropriate?
226. In survival analysis using the Kaplan-Meier method, what is the correct handling of 'censored' observations?
227. A study reports a p-value of 0.04. The researchers conclude that the intervention is effective. Which limitation of this interpretation is MOST important to recognise?
228. In a community survey, systolic blood pressure values are: 110, 115, 120, 122, 125, 300 mmHg. Which measure of central tendency would BEST represent this dataset?
229. A researcher uses logistic regression to adjust for confounders while studying the association between smoking and lung cancer. The adjusted OR for smoking is 8.4 (95% CI: 5.1–13.8). What does this adjusted OR represent?
230. Which sampling method is MOST appropriate when the study population is naturally divided into non-overlapping subgroups and proportional representation of each subgroup is essential?
231. A two-sample t-test is planned to compare mean haemoglobin levels between two groups. The data in one group is found to be heavily right-skewed with outliers. What is the MOST appropriate alternative?
232. A researcher wants to estimate the prevalence of hypertension in a district. Expected prevalence is 30%, acceptable error is 5% (absolute), and 95% confidence level. The minimum sample size required using the formula n = Z²pq/d² is:
233. In Systematic Random Sampling from a population of 10,000 using a sample size of 500, the sampling interval 'k' and the starting point are determined. If the randomly selected starting point is 12, the second element selected would be:
234. The 'receiver operating characteristic' (ROC) curve of a diagnostic test has an area under the curve (AUC) of 0.88. This indicates that:
235. In a clinical trial comparing two proportions, the type II error (β) is set at 0.20. The statistical power of the study is:
236. A new rapid diagnostic test for malaria has sensitivity 80% and specificity 95.6%. In a population with disease prevalence of 10%, the Positive Predictive Value (PPV) of the test is approximately (using the formula):
237. The Kappa (κ) statistic is used to assess:
238. The non-parametric equivalent of the unpaired t-test, used when data is not normally distributed, is:
239. In a study of 400 children, the mean serum calcium is 9.2 mg/dL with a standard deviation (SD) of 0.8 mg/dL. What is the 95% confidence interval for the true population mean?
240. Which test is used to compare observed frequencies with expected frequencies for a categorical variable with more than 2 categories?
241. Number Needed to Harm (NNH) is calculated from a drug trial where 8% of treated patients experience a severe adverse event versus 2% in the control group. What is the NNH?
242. A study assessing association between categorical variables (smoking: yes/no) and disease outcome (lung cancer: yes/no) in a 2×2 table should use which statistical test when all expected cell frequencies are ≥ 5?
243. A Type II error (beta error) in a clinical trial means:
244. In calculating sample size for a cohort study comparing two proportions, which factor directly REDUCES the required sample size?
245. A researcher reports a statistically significant result (p = 0.04) from a trial, but the 95% CI for the relative risk is 1.02–1.38. What is the MOST important clinical interpretation?
246. In a study, 200 patients receive drug X and 200 receive placebo. After 1 year: 40 deaths in drug X group, 60 deaths in placebo group. What is the Relative Risk Reduction (RRR) and Number Needed to Treat (NNT)?
247. Bayesian statistics differs from frequentist statistics primarily in that: