A categorical variable was retained if the composite linear Wald test of all the variable's strata and the Wald test for at least one individual stratum indicator variable was significant (p < 0.05).
Stratified Cox regression was used to compute total hazard ratios in forest plots and multivariate analysis, using the dataset as the stratum indicator, thus allowing for different baseline hazard functions between cohorts.
Because control of factors changing across strata is no longer achieved by design, in addition to the regressors x i we also include stratum indicator variables (a vector z i ): 2 It helps understand the conditional variant of this model to re-write the term α T z i as αs where day i falls in stratum s (thus vector α = (α1,…, αS)).
It has been established that a Poisson model for counts with stratum indicators gives identical estimates and can allow for these phenomena [ 2], but it is little used, probably because of the overheads in estimating many stratum parameters.
The imputation model was: Z2 = α0 + α1 I case + α2 Strata + ε, where α0 and α1 are scalar, α2 is a vector coefficient, I case is the case indicator, Strata is the vector of stratum indicators and є is the vector of errors independently and identically distributed ~ N (0, σ).
It has been established that a Poisson model for counts with stratum indicators gives identical estimates to those from conditional logistic regression and does not have these limitations, but it is little used, probably because of the overheads in estimating many stratum parameters.
We examined pollutant concentration distributions across pollution indicator strata used for site selection and allocation: traffic density, emission-weighted proximity to industry, and elevation above sea level using Spearman correlation analysis, to account for non-normal distribution of pollution concentrations.
As sampling at the 36 sites was evenly allocated across six Monday-through-Friday sampling sessions (six sites sampled per session), we sought to balance source indicator strata and spatial distribution across sessions to avoid confounding spatial and temporal patterns in pollution concentrations.
We examined two temporal adjustment methods for deriving seasonal mean concentration estimates at distributed locations, and found that the choice of reference site(s) influenced observed relationships between measured concentrations and emissions indicator strata (i.e., elevation, traffic density, industrial emissions) for NO2, but not for PM2.5 or BC.
For each stratum, two types of indicators of cancer frequency were calculated: 1. Incidence rate: observed number of cases divided by the stratumspecific number of personyears, given per 100,000 person-years.
We therefore stratified analyses according to maternal education level [as an indicator of socioeconomic status (De Vries et al. 2003; Maas et al. 2009b)] to explore variation across socioeconomic strata.
