Table. Bayesian logistic regression model of prevalence of infection with Schistosoma haematobium in children in 418 schools in Burkina Faso, Mali, and Niger, 2004–2006*.

Variable	Posterior distribution
	Mean (95% CrI)	SD
Female gender	0.70 (0.65–0.76)	0.03
Age, y
9–10	1.16 (1.00–1.33)	0.08
11–12	1.51 (1.31–1.73)	0.10
13–16	1.79 (1.53–2.06)	0.14
Distance to perennial water body	0.34 (0.21–0.54)	0.08
Land surface temperature	0.80 (0.51–1.21)	0.18
Land surface temperature2	1.10 (0.85–1.40)	0.14
Rate of decay of spatial correlation	2.03 (1.48–2.74)	0.32
Variance of the spatial random effect (sill)	7.03 (5.36–9.31)	1.01

*CrI, Bayesian credible interval. Values for the fixed effects are odds ratios; note the odds ratios for the climate variables are on a common scale, where the variables were standardized to have a mean = 0 and SD = 1. The reference group for sex was boys and for age was 6–8 y. The number of children found to be infected with S. haematobium was modeled by using a binomial distribution described by the proportion infected and the total number sampled in each survey location. The proportion infected was modeled by using logistic regression with an intercept, covariates (sex, age, distance to perennial water body, land surface temperature, and a quadratic term for land surface temperature), and a random effect that described spatial correlation (i.e., clustering). Model outputs were distributions (termed posterior distributions) that can be summarized by using the mean, SD, and 95% CrI (representing the range of values that contains the true value with a probability of 95%). More details on the model are presented in the Technical Appendix.