USMLE Step 1 Quiz: Statistical Tests
20 questions · exam conditions
0:00
Statistical TestsQuestion 1 of 20

Compare survival curves for two treatments. Which test?

Chi-square test
Kaplan-Meier
Log-rank test
Student t-test
← Back to quizzes

USMLE Step 1 Quiz

USMLE Step 1 Quiz: Statistical Tests

Practice Statistical Tests in USMLE Step 1 with focused quiz questions that help you check what you know, review explanations, and build confidence with test-style prompts.

What this quiz covers

This quiz focuses on Statistical Tests, giving you a quick way to practice the rules, question types, and explanations that matter most for USMLE Step 1.

How to use this quiz

Try each quiz question before looking at the correct answer. Use the explanations to review missed ideas, then come back to similar questions until the pattern feels familiar.

All questions

Question 1

Compare survival curves for two treatments. Which test?

  1. Chi-square test
  2. Kaplan-Meier
  3. Log-rank test (correct answer)
  4. Student t-test
Explanation: To compare two survival curves, you need a hypothesis test that accounts for censored data across follow-up time. The log-rank test does exactly this by comparing the observed and expected event rates over time. Kaplan-Meier is tempting because it estimates survival curves, but it does not formally test the difference between them. Chi-square and t-tests are not designed for time-to-event data.

Question 2

Quantify linear association of two continuous variables. Which test?

  1. Spearman correlation
  2. Pearson correlation (correct answer)
  3. Chi-squared test
  4. Mann-Whitney U test
Explanation: To quantify linear association between two continuous variables, use Pearson correlation; it measures the strength and direction of a linear relationship. Spearman correlation is the tempting choice, but it assesses monotonic association, not specifically linearity. Chi-squared and Mann-Whitney apply to categorical or group comparisons.

Question 3

Paired binary outcome before/after intervention. Which test?

  1. McNemar's test (correct answer)
  2. Chi-square test
  3. Fisher's exact
  4. Paired t-test
Explanation: For a before/after binary outcome, the two observations per subject are paired, so you must use McNemar's test to compare discordant pairs. The chi-square test is tempting because both variables are categorical, but it treats the groups as independent and ignores the pairing. Paired t-test is wrong because the outcome is binary, not continuous.

Question 4

Compare mean LDL in twin pairs, one twin per pair on statin. Which test?

  1. Mann-Whitney U
  2. One-way ANOVA
  3. Chi-square test
  4. Paired t-test (correct answer)
Explanation: Each twin pair gives two linked LDL values, so the data are paired. The paired t-test compares the mean difference within pairs, directly assessing statin effect. Mann-Whitney U is tempting but wrong because it treats the twins as independent groups and compares ranks, not paired means.

Question 5

Compare ordinal disability scores across 3 treatments. Which test?

  1. One-way ANOVA
  2. Kruskal-Wallis (correct answer)
  3. Chi-square test
  4. Paired t-test
Explanation: The outcome is ordinal and there are three independent treatment groups, so use Kruskal-Wallis, the nonparametric rank-based alternative to one-way ANOVA. One-way ANOVA is tempting but wrongly assumes a continuous, normally distributed outcome rather than ordinal disability scores.

Question 6

Researchers investigate the association between daily saturated fat intake (in grams) and serum LDL cholesterol levels (in mg/dL). After analyzing the data from their study population, they calculate a Pearson correlation coefficient (r) of 0.70.

Based on this result, what percentage of the variability in serum LDL cholesterol levels can be explained by the variability in daily saturated fat intake?

  1. 35%
  2. 49% (correct answer)
  3. 70%
  4. 95%
Explanation: The coefficient of determination, or r-squared (r²), represents the proportion of the variance in the dependent variable that is predictable from the independent variable. To find this value, the correlation coefficient (r) is squared. In this case, r = 0.70, so r² = (0.70)² = 0.49. This means that 49% of the variability in serum LDL cholesterol levels can be explained by the variability in daily saturated fat intake in this study population.

Question 7

A large observational study in a seaside town finds a strong positive correlation (r = +0.85) between monthly ice cream sales and the number of drowning incidents.

Based on this information, which of the following is the most appropriate conclusion?

  1. Consumption of ice cream increases the risk of drowning.
  2. The observed association is likely due to a confounding variable. (correct answer)
  3. Drowning incidents lead to increased ice cream consumption.
  4. The statistical test used was inappropriate for this type of data.
Explanation: Correlation does not imply causation. A strong correlation between two variables does not mean that one causes the other. In this classic example, a third factor, or confounding variable (e.g., warm weather), is likely responsible for the increase in both ice cream sales and swimming activities, which in turn leads to more drowning incidents. This is a much more plausible explanation than a direct causal link.

Question 8

A study is conducted to assess the relationship between body mass index (BMI) and fasting plasma glucose in a group of 500 non-diabetic adults. The analysis yields a Pearson correlation coefficient (r) of +0.60.

Which of the following is the best interpretation of this correlation coefficient?

  1. Higher BMI is associated with higher fasting glucose levels in this group. (correct answer)
  2. For every 1 unit increase in BMI, fasting glucose increases by 0.60 mg/dL.
  3. 60% of the variation in fasting glucose is explained by the variation in BMI.
  4. Elevated BMI is the primary cause of elevated fasting glucose.
Explanation: The Pearson correlation coefficient (r) measures the strength and direction of a linear relationship between two continuous variables. A positive value (r = +0.60) indicates a positive association, meaning that as one variable (BMI) increases, the other variable (fasting glucose) tends to increase. The slope of the relationship is determined by regression analysis, not the correlation coefficient itself. The proportion of variance explained is r-squared (r²), which would be 0.36 or 36% in this case. Correlation does not establish causation.

Question 9

A new lifestyle intervention program aims to reduce systolic blood pressure (SBP) in patients with prehypertension. Researchers measure the SBP of 40 participants at the beginning of the program and again after 12 weeks of participation. They want to assess if the intervention was effective.

Which statistical test is most appropriate for comparing the mean SBP before and after the intervention in this group of participants?

  1. Paired t-test (correct answer)
  2. Independent samples t-test
  3. Chi-square test
  4. Linear regression
Explanation: A paired t-test is the most appropriate test in this scenario because the measurements are taken from the same group of individuals at two different time points (before and after). This means the data points are paired or dependent. An independent samples t-test would be used if comparing two different groups of people. A chi-square test is for categorical data, and linear regression is for prediction.

Question 10

A pharmacologist is studying the effect of a new analgesic. A total of 120 subjects with moderate pain are randomly assigned to one of four groups: placebo, 10 mg of the new drug, 20 mg of the new drug, or a standard dose of ibuprofen. The primary outcome is the self-reported pain score on a continuous scale 2 hours after administration.

Which statistical test should be used to determine if there is a significant difference in mean pain scores among the four treatment groups?

  1. Paired t-test
  2. A series of six independent t-tests
  3. Analysis of variance (ANOVA) (correct answer)
  4. Chi-square test
Explanation: Analysis of variance (ANOVA) is the appropriate statistical test for comparing the means of a continuous variable across three or more independent groups. Using multiple t-tests to compare each pair of groups would inflate the probability of making a Type I error (falsely concluding there is a difference). ANOVA analyzes the variance between groups relative to the variance within groups to test the null hypothesis that all group means are equal.

Question 11

A study is conducted to examine the relationship between a specific genetic polymorphism (Allele A present vs. Allele A absent) and the risk of developing Crohn's disease (diagnosed vs. not diagnosed). Data are collected from a large cohort of individuals.

Which statistical test is most suitable for determining if there is a significant association between the presence of Allele A and the diagnosis of Crohn's disease?

  1. Independent samples t-test
  2. Pearson correlation
  3. Analysis of variance (ANOVA)
  4. Chi-square test (correct answer)
Explanation: The Chi-square test is used to assess for an association between two categorical variables. In this scenario, both the genetic polymorphism (present/absent) and the disease status (diagnosed/not diagnosed) are categorical. The test compares the observed frequencies in each category to the frequencies that would be expected if there were no association between the variables.

Question 12

An investigator wishes to compare the mean weight loss between a diet-only group and a diet-plus-exercise group. Each group has only 12 participants. The distribution of weight loss in the diet-plus-exercise group is noted to be significantly skewed, not following a normal distribution.

The use of an independent samples t-test in this situation may be invalid because which of its key assumptions has been violated?

  1. The samples must be independent.
  2. The outcome variable must be continuous.
  3. The data from the underlying population must be normally distributed. (correct answer)
  4. The variances of the two groups must be equal.
Explanation: The t-test is a parametric test, which means it relies on certain assumptions about the data. A key assumption is that the data are sampled from a population with a normal distribution. While the t-test is robust to minor violations, especially with larger sample sizes, significant skewness in a small sample (n=12) makes its results unreliable. The assumption of independence is met, and the outcome is continuous. While equal variances (homoscedasticity) is an assumption, the violation of normality is the more critical issue here prompting the use of a non-parametric test.

Question 13

A study evaluates the effect of a mindfulness-based stress reduction program on telomere length in a small group of 15 healthcare workers. Telomere length is measured from leukocytes before the 8-week program and again at its conclusion. The distribution of the differences in telomere length (post-pre) is found to be significantly skewed.

Which statistical test is the most appropriate to determine if there was a significant change in telomere length?

  1. Paired t-test
  2. Mann-Whitney U test
  3. Wilcoxon signed-rank test (correct answer)
  4. Spearman correlation
Explanation: This study uses a pre-post design with the same subjects, so the data are paired. The paired t-test is the standard parametric test for this design, but it assumes that the differences between paired measurements are normally distributed. Since this assumption is violated (the differences are skewed), the appropriate nonparametric alternative is the Wilcoxon signed-rank test.

Question 14

An emergency department physician is comparing the time to pain relief for three different non-opioid analgesics given for acute renal colic. Twenty patients are randomized to each of the three drug groups. The outcome, time to relief, is highly skewed as some patients take a very long time to respond. The physician wishes to see if there is any difference among the three drugs.

What is the most appropriate statistical test to use to compare the central tendency of time to pain relief among the three groups?

  1. Analysis of variance (ANOVA)
  2. Kruskal-Wallis test (correct answer)
  3. A series of Mann-Whitney U tests
  4. Wilcoxon signed-rank test
Explanation: The Kruskal-Wallis test is the nonparametric alternative to one-way ANOVA. It is used to determine if there are statistically significant differences between two or more independent groups on a continuous or ordinal dependent variable when the assumptions of ANOVA (like normality) are not met. Since the data are highly skewed and there are three independent groups, the Kruskal-Wallis test is the most suitable choice.

Question 15

An endocrinologist wants to understand the factors affecting bone mineral density (BMD) in postmenopausal women. She plans to analyze the relationship between BMD (a continuous variable) and several factors simultaneously: patient age, daily calcium intake, and vitamin D levels.

Which statistical method would allow the researcher to evaluate the independent contribution of each factor to bone mineral density while controlling for the effects of the others?

  1. Multiple linear regression (correct answer)
  2. A series of Pearson correlations
  3. Analysis of variance (ANOVA)
  4. Logistic regression
Explanation: Multiple linear regression is the appropriate technique when assessing the relationship between a single continuous dependent variable (BMD) and two or more independent variables (age, calcium intake, vitamin D levels). This method allows for the assessment of each variable's independent effect while statistically controlling for the others, which helps to mitigate confounding.

Question 16

In a hospital, a rare, aggressive bacterial infection is identified in 8 patients. An investigation is launched to determine if the infection is associated with a specific type of intravenous catheter used in the ICU. Of the 8 infected patients, 6 had used the catheter. In a control group of 20 uninfected ICU patients from the same period, only 2 had used the catheter.

Due to the small number of cases, which statistical test would be most appropriate for analyzing the association between catheter use and infection?

  1. Independent samples t-test
  2. Chi-square test with Yates' correction
  3. Fisher's exact test (correct answer)
  4. Analysis of variance (ANOVA)
Explanation: Fisher's exact test is used to analyze categorical data in a 2x2 table, particularly when the sample size is small and the expected frequencies in any cell are less than 5. In such cases, the Chi-square test, which is an approximation, becomes inaccurate. Given the very small number of cases (8), Fisher's exact test provides a more accurate p-value for the association between the two categorical variables (catheter use and infection status).

Question 17

A research team wants to develop a model to predict the probability of a patient having a myocardial infarction (MI) within the next 10 years. The outcome is binary (MI or no MI). The potential predictor variables include age, smoking status (yes/no), presence of hypertension (yes/no), and serum cholesterol level.

Which statistical method is most appropriate for building this predictive model?

  1. Multiple linear regression
  2. Logistic regression (correct answer)
  3. Cox proportional hazards model
  4. Pearson correlation
Explanation: Logistic regression is the appropriate statistical technique when the dependent (outcome) variable is dichotomous or binary, such as the occurrence of an MI (yes/no). It allows for the modeling of how multiple independent variables (both continuous and categorical) predict the probability of the outcome. Multiple linear regression is used for continuous outcomes. A Cox model would be used for time-to-event data, which is more specific than what is described.

Question 18

Researchers are investigating whether there is an association between the type of infant feeding (exclusively breastfed, mixed-fed, exclusively formula-fed) and the incidence of otitis media in the first year of life (yes/no).

Which statistical test is most appropriate to analyze the relationship between these two variables?

  1. Analysis of variance (ANOVA)
  2. Independent samples t-test
  3. Chi-square test (correct answer)
  4. Kruskal-Wallis test
Explanation: This analysis involves two categorical variables: infant feeding type (with three categories) and incidence of otitis media (with two categories). The Chi-square test is the appropriate statistical method to determine if there is a significant association between two categorical variables by comparing observed frequencies to expected frequencies.

Question 19

A randomized controlled trial is conducted to evaluate a new medication designed to reduce intraocular pressure (IOP) in patients with glaucoma. Sixty patients are randomly assigned to receive either the new medication or a placebo eye drop. After one month, the mean IOP is measured in each group. The data are approximately normally distributed.

Which statistical test is most appropriate to determine if there is a significant difference in the mean IOP between the medication and placebo groups?

  1. Paired t-test
  2. Independent samples t-test (correct answer)
  3. Analysis of variance (ANOVA)
  4. Pearson correlation
Explanation: An independent samples t-test (or two-sample t-test) is the correct statistical method for comparing the means of a continuous outcome variable (IOP) between two independent, unrelated groups (medication vs. placebo). A paired t-test is used for related samples (e.g., before and after treatment in the same group). ANOVA is used for comparing means of three or more groups. Pearson correlation assesses the association between two continuous variables.

Question 20

A nephrologist wants to create a model to predict a patient's glomerular filtration rate (GFR) based on their serum creatinine level. Data on both continuous variables are collected from a large patient cohort.

Which of the following statistical methods is most appropriate for developing an equation to estimate GFR from serum creatinine?

  1. Chi-square test
  2. Analysis of variance (ANOVA)
  3. Independent samples t-test
  4. Simple linear regression (correct answer)
Explanation: Simple linear regression is used to model the relationship between two continuous variables and to create a predictive equation. The goal is to predict the value of a dependent variable (GFR) based on the value of an independent variable (serum creatinine). The other options are incorrect: a t-test compares means between two groups, ANOVA compares means among three or more groups, and a chi-square test assesses the association between categorical variables.