Marginal quantile regression for dependent data with a working odds-ratio matrix.

Dependent data arise frequently in applied research and several approaches to adjusting for the dependence among observations have been proposed in quantile regression. Cluster bootstrap is generally inefficient and computationally demanding, especially when the number of clusters is large. When the primary interest is on marginal quantiles, estimating equations have been proposed that estimate a working correlation matrix from the regression residuals' sign. However, the Pearson's correlation coefficient is an inadequate measure of dependence between binary variables because its range depends on their marginal probabilities. Instead, we propose to model the working correlation matrix through odds ratios. Different working structures can be easily estimated by suitable logistic regression models. These structures can be parametrized to depend on covariates and clusters. Simulations show that the proposed estimator has similar behavior to that of generalized estimating equations applied to regression for the mean. We study marginal quantiles of cognitive behavior with data from a randomized trial for treatment of obsessive compulsive disorder.

Interleukin-6 and depressive symptom severity in response to physical exercise.

Elevated IL-6 has been implicated in depression. The anti-inflammatory effects of exercise may be associated with its clinical efficacy for depression. We determined if serum IL-6 levels were altered by 12 weeks of physical exercise, and if IL-6 levels were associated with baseline depression severity and change in depression severity in response to exercise. Data from 116 adults (42.7±11.5y) with mild-to-moderate depression (Patient Health Questionnaire >9) who participated in the physical exercise arm of the Regassa RCT (www.regassa.se) were analyzed. Participants were requested to complete three 60-min exercise sessions weekly for 12 weeks. Blood samples were provided at baseline and post-intervention following an overnight fast and were analyzed for serum levels of IL-6 using ELISA. IL-6 values were logarithm-transformed. Higher baseline serum IL-6 levels were significantly associated with reduced depression severity after exercise. Reduced IL-6 levels following exercise were significantly associated with parallel reductions in depression severity. These findings are consistent with a previously reported association between reduced serum IL-1ß levels and reduced depression severity following 12 weeks of physical exercise in 105 depressed adults. Findings support associations between IL-6, depressive symptoms, and exercise response, and provide support for the plausible involvement of IL-6 in the antidepressive effect of exercise.