Biostatistics in Pharmacy is the application of statistical methods to design, analyze, and interpret data from pharmaceutical research, clinical trials, pharmacokinetics, and epidemiology. For B.Pharm students, mastering descriptive statistics, probability, hypothesis testing, confidence intervals, regression, and survival analysis is essential for evidence-based drug development, therapeutic monitoring, and regulatory submissions. Understanding sampling, power and sample size, diagnostic test evaluation (sensitivity, specificity, ROC), and study design improves research quality and patient safety. These skills enable critical appraisal of literature, accurate reporting, and informed clinical decisions in pharmacy practice. ‘Now let’s test your knowledge with 30 MCQs on this topic.’
Q1. What is the primary role of biostatistics in pharmacy?
- To perform laboratory experiments with drugs
- To apply statistical methods to biomedical and pharmaceutical data
- To synthesize new chemical entities
- To design drug packaging
Correct Answer: To apply statistical methods to biomedical and pharmaceutical data
Q2. Which is an example of nominal data often used in pharmacy studies?
- Drug dose in mg
- Blood pressure in mmHg
- Patient blood group (A, B, AB, O)
- Pain score on a 0–10 scale
Correct Answer: Patient blood group (A, B, AB, O)
Q3. For a highly skewed pharmacokinetic parameter, which measure of central tendency is most appropriate?
- Arithmetic mean
- Median
- Mode
- Geometric mean regardless of distribution
Correct Answer: Median
Q4. Which measure of dispersion is least affected by outliers?
- Standard deviation
- Variance
- Interquartile range (IQR)
- Range
Correct Answer: Interquartile range (IQR)
Q5. What does the standard error of the mean (SE) represent?
- Variability of individual observations around the mean
- Variability of the sample mean across repeated samples
- Difference between two sample means
- Average distance of data from the median
Correct Answer: Variability of the sample mean across repeated samples
Q6. How is a p-value best interpreted in hypothesis testing?
- Probability the null hypothesis is true
- Probability the alternative hypothesis is true
- Probability of observing data as extreme as observed assuming the null hypothesis is true
- Magnitude of the treatment effect
Correct Answer: Probability of observing data as extreme as observed assuming the null hypothesis is true
Q7. A Type I error (alpha) in a drug trial corresponds to which event?
- Failing to detect a real drug effect
- Incorrectly declaring a drug effective when it is not
- Random sampling variability
- Choosing the wrong dose
Correct Answer: Incorrectly declaring a drug effective when it is not
Q8. What does statistical power (1 − beta) indicate in a study?
- Probability of finding any result
- Probability of rejecting the null hypothesis when it is false
- Probability of observing a Type I error
- Precision of estimates
Correct Answer: Probability of rejecting the null hypothesis when it is false
Q9. Which action generally increases the statistical power of a clinical trial?
- Decreasing sample size
- Increasing measurement error
- Increasing effect size or sample size
- Using a less sensitive outcome measure
Correct Answer: Increasing effect size or sample size
Q10. Which test is most appropriate to compare proportions between two independent groups?
- Student’s t-test
- Chi-square test
- Pearson correlation
- ANOVA
Correct Answer: Chi-square test
Q11. When comparing mean systolic blood pressure between two independent normally distributed groups, which test is appropriate?
- Mann–Whitney U test
- Paired t-test
- Independent (unpaired) Student’s t-test
- Chi-square test
Correct Answer: Independent (unpaired) Student’s t-test
Q12. Which scenario requires a paired t-test?
- Comparing blood pressure between two different patient populations
- Comparing before-and-after blood pressure in the same patients
- Comparing three dose groups
- Comparing categorical outcomes
Correct Answer: Comparing before-and-after blood pressure in the same patients
Q13. ANOVA is used to:
- Compare variances of two groups
- Compare means across three or more independent groups
- Assess correlation between two continuous variables
- Test for normality
Correct Answer: Compare means across three or more independent groups
Q14. If pharmacokinetic data are not normally distributed, which nonparametric test compares two independent groups?
- Mann–Whitney U test
- Independent t-test
- Paired t-test
- One-way ANOVA
Correct Answer: Mann–Whitney U test
Q15. Which correlation coefficient is suitable for ordinal or non-normally distributed data?
- Pearson correlation
- Spearman rank correlation
- Chi-square
- Cohen’s kappa
Correct Answer: Spearman rank correlation
Q16. In linear regression, R-squared represents:
- Average residual error
- Proportion of variance in the outcome explained by the model
- Significance of the slope
- Number of predictors
Correct Answer: Proportion of variance in the outcome explained by the model
Q17. Logistic regression is most appropriate when the dependent variable is:
- Continuous and normally distributed
- Binary (e.g., success/failure)
- Time-to-event
- Ordinal with many levels
Correct Answer: Binary (e.g., success/failure)
Q18. What does the area under the ROC curve (AUC) indicate for a diagnostic test?
- Optimal cutoff value directly
- Overall diagnostic accuracy across all thresholds
- Prevalence of disease
- False discovery rate
Correct Answer: Overall diagnostic accuracy across all thresholds
Q19. Sensitivity of a diagnostic test refers to:
- Proportion of true negatives correctly identified
- Proportion of true positives correctly identified
- Probability disease is absent when test is negative
- Prevalence-adjusted accuracy
Correct Answer: Proportion of true positives correctly identified
Q20. Specificity of a test measures:
- Ability to detect disease when present
- Ability to identify absence of disease when absent
- Positive predictive value
- Test reliability over time
Correct Answer: Ability to identify absence of disease when absent
Q21. Which value is most affected by disease prevalence?
- Sensitivity
- Specificity
- Positive predictive value (PPV)
- Likelihood ratio
Correct Answer: Positive predictive value (PPV)
Q22. Kaplan–Meier analysis is used to:
- Compare means across groups
- Estimate time-to-event (survival) functions accounting for censoring
- Calculate correlation coefficients
- Adjust for multiple comparisons
Correct Answer: Estimate time-to-event (survival) functions accounting for censoring
Q23. A hazard ratio (HR) greater than 1 in survival analysis indicates:
- No difference in hazard between groups
- Lower hazard in the treatment group
- Higher hazard (increased risk) in the numerator group
- An error in analysis
Correct Answer: Higher hazard (increased risk) in the numerator group
Q24. The main purpose of randomization in clinical trials is to:
- Ensure blinding of investigators
- Guarantee statistical significance
- Balance known and unknown confounders between groups
- Reduce sample size
Correct Answer: Balance known and unknown confounders between groups
Q25. Blinding in a trial primarily reduces which type of bias?
- Selection bias
- Measurement/observer bias and placebo effects
- Confounding by indication
- Reporting bias only
Correct Answer: Measurement/observer bias and placebo effects
Q26. A confounder is best described as:
- A variable caused by the exposure
- A variable associated with both exposure and outcome that distorts their relationship
- An outcome misclassification
- A type of random error
Correct Answer: A variable associated with both exposure and outcome that distorts their relationship
Q27. Intention-to-treat (ITT) analysis means:
- Analyzing only participants who completed the treatment per protocol
- Including all randomized participants in the groups to which they were assigned
- Excluding participants with missing data
- Replacing missing outcomes with group means
Correct Answer: Including all randomized participants in the groups to which they were assigned
Q28. Regulatory bioequivalence criteria typically require 90% confidence intervals for AUC and Cmax to fall within which range?
- 50–150%
- 70–130%
- 80–125%
- 90–110%
Correct Answer: 80–125%
Q29. Intraclass correlation coefficient (ICC) is used to assess:
- Association between two categorical variables
- Agreement or reliability of continuous measurements made by different raters
- Predictive power of a model
- Normality of data
Correct Answer: Agreement or reliability of continuous measurements made by different raters
Q30. Performing many statistical tests on the same dataset without adjustment primarily increases the risk of:
- Type II error
- Type I error (false positives)
- Improved validity
- Reduced variance
Correct Answer: Type I error (false positives)
I am a Registered Pharmacist under the Pharmacy Act, 1948, and the founder of PharmacyFreak.com. I hold a Bachelor of Pharmacy degree from Rungta College of Pharmaceutical Science and Research. With a strong academic foundation and practical knowledge, I am committed to providing accurate, easy-to-understand content to support pharmacy students and professionals. My aim is to make complex pharmaceutical concepts accessible and useful for real-world application.
Mail- Sachin@pharmacyfreak.com