Effect of disease prevalence on predictive values — Flashcards

Flashcard 1: A high _____ test is useful for screening in diseases with low prevalence (sensitivity or specificity)

Answer: sensitivity

Flashcard 2: _____ is the probability that when the disease is present, the test is positive

Answer: Sensitivity

Flashcard 3: How are prevalence and pretest probability related? _____

Answer: They are similar

Flashcard 4: _____ ratios can be multiplied with pretest odds of disease to estimate posttest odds

Answer: Likelihood

Flashcard 5: Under Hardy-Weinberg conditions, what is the expected frequency of an X-linked recessive disease in males? Females?

Answer: males - q females - q2 (if condition is survivable)

Flashcard 6: coefficient of determination (r2) (biostatistics)

Answer: Proportion of the variance in the dependent variable that is predictable from the independent variable. Range: 0 to 1 (It is the square of the Pearson correlation coefficient r)

Extra: Example: If r = 0.6, then r² = 0.36. This means 36% of the variation in variable Y is explained by its linear relationship with variable X.

Flashcard 7: Pearson's correlation coefficient (r) (biostatistics)

Answer: measure of linear correlation -1 is perfect inverse relationship 1 is perfect direct relationship

Flashcard 8: What is the Chi-square (X2) test used for? (biostatistics)

Answer: compare proportions of categorical outcomes between two groups (not comparison of means!)

Flashcard 9: Which parameters, sens/spec or PPV/NPV are affected by prevalence of the disease in the population?

Answer: PPV/NPV

Flashcard 10: PPV (biostatistics)

Answer: Probability that a person actually has disease given a positive test result.

Extra: PPV = TP/(TP+FP)