No abstract

OBJECTIVETo evaluate the association between recurrent subthreshold depressive episodes and functioning in a prospective community sample of people with type 2 diabetes. RESEARCH DESIGN AND METHODSA prospective community study in Quebec, Canada, was carried out between 2008 and 2013 (n = 1,064). Five yearly follow-up assessments (telephone interviews) were conducted. Baseline and the first three follow-up assessments were used to identify recurrent subthreshold depressive episodes (Patient Health Questionnaire [PHQ]-9). Functioning (World Health Organization Disability Assessment Schedule II [WHODAS-II]) and health-related quality of life (Centers for Disease Control and Prevention [CDC] unhealthy days) at 4-and 5-year follow-up assessments were the outcome measures. RESULTSNearly half of the participants suffered from at least one episode of subthreshold depressive symptoms. After adjusting for potentially confounding factors, the risk of poor functioning/impaired health-related quality of life was nearly three times higher (relative risk = 2.86) for participants with four subthreshold depressive episodes compared with participants with no/minimal depression. Results suggest a dose-response relationship: the risk of poor functioning/impaired health-related quality of life increased with the number of recurrent subthreshold depressive episodes even after controlling for potentially confounding variables (significant linear trend, P < 0.001). CONCLUSIONSRecurrent subthreshold depressive symptoms might be an important risk factor for poor health outcomes in type 2 diabetes. Early identification, monitoring, and treatment of recurrent subthreshold depressive symptoms might improve functioning and quality of life in people with type 2 diabetes.

Abstract Partial least square regression (PLSR) is a statistical modeling technique that extracts latent factors to explain both predictor and response variation. PLSR is particularly useful as a data exploration technique because it is highly flexible (e.g., there are few assumptions, variables can be highly collinear). While gaining importance across a diverse number of fields, its application in the social sciences has been limited. Here, we provide a brief introduction to PLSR, directed towards a novice audience with limited exposure to the technique; demonstrate its utility as an alternative to more classic approaches (multiple linear regression, principal component regression); and apply the technique to a hypothetical dataset using JMP statistical software (with references to SAS software).