Non-response bias in the analysis of the association between mental health and the urban environment : a cross-sectional study in Brussels, Belgium

Abstract: Background This paper aims at analysing the impact of partial non-response in the association between urban environment and mental health in Brussels. The potential threats of the partial non-response are biases in survey estimates and statistics. The effect of non-response on statistical associations is often overlooked and evidence in the research literature is lacking. Methods Data from the Belgian Health Interview Survey 2008 and 2013 were used. The association between non-response and potential determinants was explored through logistic regressions. Results Participants with low... Mehr ...