A case-control study was conducted to estimate the association between simvastatin therapy and serum levels of fibrinogen in patients who underwent percutaneous coronary intervention. Cases were identified as patients who underwent percutaneous coronary intervention and had high periprocedural levels of fibrinogen (400 mg/dL), and controls were identified as patients who underwent percutaneous coronary interventions but had normal levels of fibrinogen (200-400 mg/dL). History of simvastatin therapy use was assessed through chart review for every patient. The number of patients corresponding to each classification criteria is given in the table below. Which of the following is the best statistical method to estimate the association between simvastatin use and high serum fibrinogen levels in this study?

Question

A case-control study was conducted to estimate the association between simvastatin therapy and serum levels of fibrinogen in patients who underwent percutaneous coronary intervention.  Cases were identified as patients who underwent percutaneous coronary intervention and had high periprocedural levels of fibrinogen (>400 mg/dL), and controls were identified as patients who underwent percutaneous coronary interventions but had normal levels of fibrinogen (200-400 mg/dL).  History of simvastatin therapy use was assessed through chart review for every patient.  The number of patients corresponding to each classification criteria is given in the table below.  Which of the following is the best statistical method to estimate the association between simvastatin use and high serum fibrinogen levels in this study?

Quizplus · Accepted Answer

11ec160b_3727_d00b_9249_af054cef4972_MD0001_00 Variables can be broadly classified as qualitative (ie, categorical) or quantitative (eg, continuous) based on their scale of measurement. Qualitative variables (eg, disease status, blood type) represent categories or groups, whereas quantitative variables (eg, body weight, glucose levels) represent numerical values. Choosing the correct statistical test always depends on the type of dependent and independent variables under consideration. The chi-square test for independence (also known as chi-square test for association) is used to evaluate the association between 2 categorical variables. In this example, patients are divided into 2 groups based on serum fibrinogen levels (dependent categorical variable: normal [200-400 mg/dL], high [>400 mg/dL]) and then divided again based on simvastatin exposure status (independent categorical variable: treated, not treated), with the data recorded in a 2 × 2 table. A chi-square test may be conducted to determine whether a statistically significant association exists between simvastatin use and the high levels of serum fibrinogen. A large difference in the frequency of simvastatin use between cases and controls is indicative of an association between simvastatin use and high levels of fibrinogen (ie, the null hypothesis is rejected). (Choices A and E) The analysis of variance (ANOVA) and two-sample t-test are used to compare the means between groups. This would require the dependent variable (ie, outcome) to be a quantitative variable. The difference between these 2 tests resides in the number of groups compared. The t-test is used to compare 2 group means, whereas the ANOVA is used to compare ≥2 group means. Either of these tests would be appropriate in this example if fibrinogen levels were recorded as a quantitative variable (ie, the actual measured level in mg/dL) instead of a categorical variable (ie, normal or high). (Choice C) The correlation coefficient is a measure of the strength and direction of a linear relationship between 2 quantitative variables. For example, a study may report a correlation coefficient describing the association between hemoglobin A1c levels and average blood glucose levels. (Choice D) Meta-analysis is an epidemiological method of pooling the data from several studies to conduct an analysis having a relatively larger statistical power than that of the individual studies. Educational objective: A 2 × 2 table is normally used to record the presence or absence of exposure and disease in research. Rows and columns represent the different levels for each categorical (ie, exposure and disease) variable. The chi-square test for independence is used to evaluate the association between 2 categorical variables.

A Case-Control Study Was Conducted to Estimate the Association Between