MPharm Master of Pharmacy Master of Pharmacy: Research and Biostatistics 4 — Questions and Answers
Question 1: In linear regression applied to pharmacokinetic data, the coefficient of determination (R²) represents:
- The proportion of variance in the outcome explained by the predictor(s) (Correct answer)
- The strength of the causal relationship between dose and response
- The probability that the regression slope equals zero
- The correlation coefficient between two variables
Correct answer: The proportion of variance in the outcome explained by the predictor(s)
R² quantifies how well the independent variable(s) explain variation in the dependent variable, ranging from 0 (no fit) to 1 (perfect fit).
Question 2: The number needed to treat (NNT) is calculated as:
- 1 divided by the absolute risk reduction (Correct answer)
- 1 divided by the relative risk reduction
- Absolute risk reduction divided by relative risk
- Relative risk minus 1, divided by relative risk
Correct answer: 1 divided by the absolute risk reduction
NNT = 1/ARR; it represents how many patients must receive treatment for one additional patient to benefit compared to control.
Question 3: Which regression model is appropriate when the outcome variable is binary (e.g., responded vs. did not respond to treatment)?
- Logistic regression (Correct answer)
- Linear regression
- Poisson regression
- Cox proportional hazards regression
Correct answer: Logistic regression
Logistic regression models the log-odds of a binary outcome and is the standard approach for dichotomous dependent variables in clinical research.
Question 4: In an institutional review board (IRB) submission for a phase I pharmacokinetic study, which ethical principle primarily governs the acceptable risk-benefit ratio?
- Beneficence (Correct answer)
- Autonomy
- Justice
- Non-maleficence
Correct answer: Beneficence
Beneficence requires researchers to maximize benefits and minimize harms, directly guiding the risk-benefit assessment central to IRB review.
Question 5: A Bonferroni correction for multiple comparisons adjusts the significance threshold by:
- Dividing the original alpha by the number of comparisons (Correct answer)
- Multiplying each p-value by the number of comparisons
- Squaring the original alpha level
- Subtracting the false discovery rate from alpha
Correct answer: Dividing the original alpha by the number of comparisons
The Bonferroni correction sets the new threshold as α/m (where m = number of tests) to maintain the familywise error rate at the original alpha.
Question 6: In population pharmacokinetic modeling, which software platform is most widely used for nonlinear mixed-effects modeling (NLMEM)?
- NONMEM (Correct answer)
- SAS
- GraphPad Prism
- SPSS
Correct answer: NONMEM
NONMEM (NONlinear Mixed Effects Modeling) is the gold-standard software for population PK/PD modeling in pharmaceutical research and drug development.
Question 7: The Institutional Animal Care and Use Committee (IACUC) oversees compliance with which set of principles in preclinical pharmaceutical research?
- The 3Rs: Replacement, Reduction, and Refinement (Correct answer)
- GLP, GMP, and GCP standards
- The Declaration of Helsinki principles
- ICH E6 guidelines for good clinical practice
Correct answer: The 3Rs: Replacement, Reduction, and Refinement
IACUC enforces the 3Rs framework—replacing animals when possible, reducing numbers used, and refining procedures to minimize suffering.
MPharm Master of Pharmacy Master of Pharmacy: Research and Biostatistics 4
In linear regression applied to pharmacokinetic data, the coefficient of determination (R²) represents: