Objective: The use of multilevel modelling with data from population-based surveys is often limited by the small number of cases per level-2 unit, prompting many researchers to use single-level techniques such as ordinary least squares regression. Design: Monte Carlo simulations are used to investigate the effects of data sparseness on the validity of parameter estimates in two-level versus single-level models. Setting: Both linear and non-linear hierarchical models are simulated in order to examine potential differences in the effects of small group size across continuous and discrete outcomes. Results are then compared with those obtained using disaggregated techniques (ordinary least squares and logistic regression). Main results: At the extremes of data sparseness (two observations per group), the group level variance components are overestimated in the two-level models. But with an average of only five observations per group, valid and reliable estimates of all parameters can be obtained when using a two-level model with either a continuous or a discrete outcome. In contrast, researchers run the risk of Type I error (standard errors biased downwards) when using single-level models even when there are as few as two observations per group on average. Bias is magnified when modelling discrete outcomes. Conclusions: Multilevel models can be reliably estimated with an average of only five observations per group. Disaggregated techniques carry an increased risk of Type I error, even in situations where there is only limited clustering in the data.

Research on the effects of the built environment in the pathway from impairment to disability has been largely absent. Using data from the Chicago Community Adult Health Study (2001–2003), the authors examined the effect of built environment characteristics on mobility disability among adults aged 45 or more years (n = 1,195) according to their level of lower extremity physical impairment. Built environment characteristics were assessed by using systematic social observation to independently rate street and sidewalk quality in the block surrounding each respondent's residence in the city of Chicago (Illinois). Using multinomial logistic regression, the authors found that street conditions had no effect on outdoor mobility among adults with only mild or no physical impairment. However, among adults with more severe impairment in neuromuscular and movement-related functions, the difference in the odd ratios for reporting severe mobility disability was over four times greater when at least one street was in fair or poor condition (characterized by cracks, potholes, or broken curbs). When all streets were in good condition, the odds of reporting mobility disability were attenuated in those with lower extremity impairment. If street quality could be improved, even somewhat, for those adults at greatest risk for disability in outdoor mobility, the disablement process could be slowed or even reversed.