Covariates that were associated with the outcome at P < 0.05 in a multivariable model (excluding exposure), or for which there were biological priors (parental history of asthma/allergy and child sex) were included in the final models.
In the examination of Birmingham hip resurfacing compared with cemented and uncemented procedures, we included only men and thus refitted the multivariable model excluding the sex covariate, but with no adjustment required for sex, and an adjusted survival curve estimated for each of the three surgery procedures.
The sensitivity analyses involved repeating the multivariable modeling excluding those children who did not maintain continuous enrollment in PFK, then excluding those children with less than 60 days of follow-up after their first event, and finally performing the analyses in those children who did not have birth records in the PFK database.
When we repeated multivariable models, excluding travel-associated infections and including a single case for each identified outbreak, the incidence rate for S. enterica serotype Typhimurium was similar in LTCF residents and community residents (IRR 0.91, 95% CI 0.64 1.29; p = 0.59).
The results of the second multivariable analysis model (excluding baseline glycemia measures and thus including larger numbers) are summarized in Table 4. Variables that were eliminated for all outcomes are not shown.
Parameters that were not significant anymore in the combined multivariable model were excluded from the final multivariable model.
Participants without complete data for all covariates in a given multivariable model were excluded from that analysis.
In each multivariable model, we excluded those, who did not report an outcome of interest, but were infected with another selected STI - as presented in the Table 1.
In the multivariable model that excluded GP characteristics, we found that GPs with correct knowledge about treatment during pregnancy had lower chlamydia testing rates.
Sociodemographic/lifestyle variables that were found to be not significantly associated with an individual outcome variable (within a multivariable model) were excluded from the final model for that outcome variable.
