[Response bias in a population postal survey on Health-Related Quality of Life (sf-12v2)]. / Sesgo de respuesta en una encuesta postal poblacional sobre calidad de vida relacionada con la salud (SF-12v2).

BACKGROUND: the bias associated with the low response rate may limit the economic advantage of population surveys by mail. The factors associated with non-response were estimated with an emphasis on Health-Related Quality of Life (HRQoL). METHODS: people who had answered to the Health Survey Murcia-2007 2007 (≥ 18 years), realized by telephone, were sent another postal questionnaire four months later. Both evaluations included information about HRQoL: SF-12v2 (by phone) and EQ-5D (postal). A logistic regression was realized to identify baseline factors (sociodemographic factors, health-related behaviors and HRQoL-physical component summary (PCS) and mental component summary (MCS) of the SF-12v2) associated with non-response to the postal survey. RESULTS: 2,078 individuals (61.5%) did not answer. Multivariate analysis: non-response was associated with marital status, more likely not to respond if it was not married: widower OR: 2,24; IC95% 0,61/0,88; separate/divorced 1,69; 1,10/2,59-; single 1,53; 1,23/1,90 ) and inversely with age (25-34 years OR: 0,95; IC95% 0,69/1,29; 35-44 years 0,60; 0,43/0,85; 45-54 years 0,42; 0,29/0,60; 55-64 years 0,29; 0,20/0,43; 65-74 years 0,17; 0,11/0,26-;≥75 years 0,15; 0,09/0,23) and educational level (low-OR: 0,65; IC95% 0,48/0,86; intermediate 0,41; 0,30/0,57; high-0,22; 0,16/0,30). It was also associated with HRQoL, but differentially for PCS (those with intermediate scores have less probability of not answering OR: 0.73; 95% CI: 0.61/0.88) than for the MCS (the persons in the highest tertile were more likely to not answering 1.47; 1.22/1.78. CONCLUSION: the HRQoL influences the non- response to the postal surveys, leading to an overrepresentation of individuals with middle physical health and low mental health, which it adds small magnitude bias in the estimation of population HRQoL.

Inverse probability weighted estimation of social tariffs: an illustration using the SF-6D value sets.

This paper presents a novel approach to model health state valuations using inverse probability weighting techniques. Our approach makes no assumption on the distribution of health state values, accommodates covariates in a flexible way, eschews parametric assumptions on the relationship between the outcome and the covariates, allows for an undetermined amount of heterogeneity in the estimates and it formally tests and corrects for sample selection biases. The proposed model is semi-parametrically estimated and it is illustrated with health state valuation data collected for Spain using the SF-6D descriptive system. Estimation results indicate that the standard regression model underestimates the utility loss that the Spanish general population assigns to departures from full health, particularly so for severe departures.