Biostatistics & Hypothesis Testing Flashcards
7 cards from real CRA practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 Biostatistics & Hypothesis Testing flashcards as text
Which of the following best describes the concept of statistical power in a clinical trial?
Answer: The probability of detecting a true effect when it exists
Power (1−β) is the probability that the study will correctly reject a false null hypothesis, i.e., detect a real effect.
Multiple testing in a clinical trial without correction inflates the probability of:
Answer: Type I error
Each additional hypothesis test at alpha=0.05 adds a 5% chance of a false positive; without correction, the family-wise Type I error rate exceeds alpha.
In a linear regression model, R² = 0.64 means that:
Answer: 64% of the variance in the outcome is explained by the model
R² (coefficient of determination) represents the proportion of total variance in the dependent variable accounted for by the independent variable(s).
A stratified analysis reveals different effect estimates across subgroups, suggesting the presence of:
Answer: Effect modification (interaction)
When the magnitude or direction of an association differs across strata of a third variable, that variable is an effect modifier (interaction).
Which statistic quantifies the agreement between two raters assessing the same categorical outcome, correcting for chance agreement?
Answer: Cohen's kappa
Cohen's kappa measures inter-rater reliability for categorical data and adjusts for the level of agreement expected by chance alone.
Bayesian inference differs from frequentist hypothesis testing primarily in that it:
Answer: Incorporates prior probability distributions into the analysis
Bayesian analysis updates prior beliefs with observed data using Bayes' theorem to produce a posterior probability distribution.
In a crossover trial, the primary advantage of using a paired t-test rather than an independent samples t-test is:
Answer: It removes between-subject variability, increasing power
The paired t-test accounts for individual differences by analyzing within-subject changes, reducing error variance and increasing sensitivity.