We compared mortality during heat-wave days and non-heat-wave days using city-specific generalized linear models.
For the first stage, we used city-specific generalized linear models to estimate the difference in total mortality during heat-wave days compared with non-heat-wave days, as described previously (Hajat et al. 2006).
We therefore built a model without using a city-specific random intercept in the regression analysis and all samples were treated as independent.
Our study and these two studies used city–season specific models to allow for seasonal differences in the effects of temperature and day of the week.
The methods described here can be used for city-specific modeling of long-term climate impacts on concrete infrastructure and provide a scientific basis for future-oriented construction codes.
Using Model 4, estimated city-specific coefficients ranged between 0.0-1.78).
Recalculating the city-specific LUR model using land-use data at a lower resolution, however, showed that the added value of detailed land-use data in the model fit was limited (R = 69 vs. 72% for the recalculated and original city-specific LUR, respectively) [Supplemental Material, Figures 2 and 4 (doi:10.1289/ehp.0901818)].
Methods: We analyzed data from each city using Poisson regression models, and combined city-specific estimates to derive overall effect estimates.
Differently formulated built environment variables in these PNC models suggest that city-specific models may be necessary.
In the city specific analysis we fitted fixed effects models, described above, as well as random intercept logistic regression models using "glmmPQL" function from MASS library in R software, to take into account the correlation among each subject's measurements.
