A study examined the role of biomarkers in diagnosing hypertrophic cardiomyopathy (HCM). The study population included patients without HCM, patients with borderline HCM, and patients with definite HCM. The following echocardiography measurements of the mean left ventricular wall thickness were reported: Assuming homoscedasticity and normality, which of the following tests was used to compare measurements?

Question

A study examined the role of biomarkers in diagnosing hypertrophic cardiomyopathy (HCM).  The study population included patients without HCM, patients with borderline HCM, and patients with definite HCM.  The following echocardiography measurements of the mean left ventricular wall thickness were reported: Assuming homoscedasticity and normality, which of the following tests was used to compare measurements?

Quizplus · Accepted Answer

Explanation: Choosing the best test for statistical analysis depends on the type and number of variables studied. The ANalysis Of VAriance (ANOVA) test is best suited for a scenario where the meanvalues of a continuous variable in several groups (categorical variable) are being compared. In this example, the continuous variable is left ventricular wall thickness and the categorical variable is the category of hypertrophic cardiomyopathy (HCM) with 3 groups: no HCM, borderline HCM, and definite HCM. The ANOVA test gives an F statistic (based on the variation within and between the different groups) that can be used to obtain a p-value. Specific conditions (eg, homoscedasticity or homogeneity of variances, which means that the data are scattered to about the same extent; normality, which means that the data follow the normal distribution) need to be satisfied for the test to be valid. (Choices B and E) The Pearson chi-squared test is used to compare the association between categorical variables. Fisher's exact test is used to study the association between 2 categorical variables when the number of observations is small (ie, when the Pearson chi-squared test cannot be performed due to the small sample size). For example, the association between 2 categorical variables (eg, treatment result [success/failure] and gender [man/woman]) can be determined using the Pearson chi-squared test, or, if the sample size is small (eg, 20 subjects), using Fisher's exact test. However, this study is assessing the mean values of a continuous variable (left ventricular wall thickness). (Choice C) The McNemar test compares the difference between 2 paired proportions; patients serve as their own control (eg, success/failure before and after treatment in the same subjects). (Choice D) A paired t-test can test the difference between 2 paired means; patients serve as their own control (eg, mean blood pressure before and after treatment in the same subjects). Educational objective: The ANalysis Of VAriance (ANOVA) test is useful in studying the difference in mean values among several groups. References: Which is the correct statistical test to use? (http://www.ncbi.nlm.nih.gov/pubmed/17961892)

A Study Examined the Role of Biomarkers in Diagnosing Hypertrophic