NBME Biostatistics and Epidemiology 1 — Questions and Answers
Question 1: A dataset has a mean, median, and mode that are all equal. Which of the following BEST describes this distribution?
- Positively skewed
- Negatively skewed
- Normal (bell-shaped) (Correct answer)
- Bimodal
Correct answer: Normal (bell-shaped)
When mean, median, and mode are equal, the distribution is symmetric and follows a normal (Gaussian) bell-shaped curve.
Question 2: A screening test has 90% sensitivity and 80% specificity. The disease prevalence is 10%. What is the approximate positive predictive value (PPV)?
- 33% (Correct answer)
- 50%
- 80%
- 90%
Correct answer: 33%
PPV = (sensitivity × prevalence) / [(sensitivity × prevalence) + (1−specificity)(1−prevalence)] = (0.9×0.1) / (0.9×0.1 + 0.2×0.9) ≈ 33%.
Question 3: Which measure of central tendency is MOST affected by extreme outliers in a dataset?
- Mode
- Median
- Mean (Correct answer)
- Interquartile range
Correct answer: Mean
The mean uses all values in its calculation, so a single extreme outlier can substantially shift it, unlike the median or mode.
Question 4: A study reports a p-value of 0.03 with alpha set at 0.05. What is the correct interpretation?
- There is a 3% probability the null hypothesis is true
- There is a 3% probability of obtaining results this extreme if the null hypothesis is true (Correct answer)
- The study has 97% statistical power
- The finding is clinically significant
Correct answer: There is a 3% probability of obtaining results this extreme if the null hypothesis is true
A p-value represents the probability of observing results at least as extreme as those found, assuming the null hypothesis is true — not the probability that the null is true.
Question 5: The Number Needed to Treat (NNT) is calculated as:
- 1 / Absolute Risk Reduction (Correct answer)
- 1 / Relative Risk Reduction
- Absolute Risk Reduction × 100
- Relative Risk / Absolute Risk
Correct answer: 1 / Absolute Risk Reduction
NNT = 1 / ARR; it tells you how many patients must be treated to prevent one adverse outcome compared to control.
Question 6: A researcher compares mean systolic blood pressure between a drug group and a placebo group (continuous outcome, two independent groups, normally distributed). Which statistical test is MOST appropriate?
- Chi-squared test
- Student's t-test (Correct answer)
- Pearson correlation
- Kaplan-Meier analysis
Correct answer: Student's t-test
The Student's t-test is used to compare means between two independent groups when data are normally distributed.
Question 7: Type I error (α) in hypothesis testing is defined as:
- Failing to reject a false null hypothesis
- Rejecting a true null hypothesis (Correct answer)
- Having insufficient power to detect a true effect
- Using an inappropriately small sample size
Correct answer: Rejecting a true null hypothesis
A Type I error (false positive) occurs when the null hypothesis is actually true but is incorrectly rejected; its probability equals α.
NBME Biostatistics and Epidemiology 1
A dataset has a mean, median, and mode that are all equal.
Which of the following BEST describes this distribution?