More Considerations on Both Model Assumptions and Results Interpretations —Evaluating Readmission

To the Editor Joshi et al claim that for the 3 target conditions of acute myocardial infarction, heart failure, and pneumonia, most of the decline in excess readmissions is due to regression to the mean (RTM) when applying the statistical model described by Linden and Davis to the excess readmission ratios (ERRs). Unfortunately, Joshi et al did not assess the plausibility of the underlying model assumptions. Davis pointed out that the underlying statistical model to estimate the effects of RTM requires that the distributions of the ERRs during the 2 evaluation periods be gaussian with equal means and variances. To check this assumption, we ran the Levene test for the equality of variances for each of the 3 conditions and found that the P values for both pneumonia and acute myocardial infarction were less than .01. This suggests that the model assumptions underlying the RTM effects estimation by Joshi et al for these 2 conditions are violated. Consequently, the magnitude of RTM ’s effects reported by Joshi et al may be inaccurate.
Source: JAMA Internal Medicine - Category: Internal Medicine Source Type: research