Skip to main content

Advertisement

Table 6 Absolute frequencies, outcome prevalences, exposure prevalences, crude and pooled prevalence ratio (PR) estimates, and relative confounding for the analysis of the modified data using mother in a paid job as the outcome, father living with the family as the risk factor and social class as confounder (situation 3 modified).

From: Alternatives for logistic regression in cross-sectional studies: an empirical comparison of models that directly estimate the prevalence ratio

First stratum: High social class
  Mother employed No All  
  N Prev. N N Prev. exp. = 15.0%
Father Present 73 90.1% 8 81 PR = 1.80
No 230 50.0% 230 460 M-H weight = 34.44
All 303 56.0% 238 541  
Second stratum: Low social class
  Mother employed No All  
  N Prev. N N Prev. exp.= 80.0%
Father Present 295 56.0% 232 527 PR = 1.39
No 53 40.2% 79 132 M-H weight = 42.38
All 348 52.8% 311 659  
Combined strata: High and low social class
  Mother employed   No All Prev. exp.= 50.7%
  N Prev. N N PR (crude) = 1.27
Father Present 368 60.5% 240 608 PR (M-H) = 1.58
No 283 47.8% 309 592 Confounding = 24.6%
All 651 54.3% 549 1200 P-value(het) *= 0.01
  1. * P-value for testing heterogeneity of the prevalence ratios across strata.