Skip to main content

Advertisement

Table 4 Absolute frequencies, outcome prevalences, exposure prevalences, crude and pooled prevalence ratio (PR) estimates, and relative confounding for the analysis of the modified data using asthma as the outcome, maternal smoking as the risk factor and social class as confounder (situation 2 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
  Asthma No All  
  N Prev. N N Exp. prev. = 26.6%
Mother smokes 21 14.6% 123 144 PR = 1.21
No 48 12.1% 350 398 M-H weight = 12.75
All 69 12.7% 473 542  
Second stratum: Low social class
  Asthma No All  
  N Prev. N N Exp. prev. = 43.3%
Mother smokes 194 68.1% 91 285 PR = 1.70
No 149 39.9% 224 373 M-H weight = 64.54
All 343 52.1% 315 658  
Combined strata: High and low social class
  Asthma No All Exp. prev. = 35.8%
  N Prev. N N PR (crude) = 1.96
Mother smokes 215 50.1% 214 429 PR (M-H) = 1.62
No 197 25.6% 574 771 Confounding = -17.3%
All 412 34.3% 788 1200 P-value(het)*= 0.2
  1. * P-value for testing heterogeneity of the prevalence ratios across strata.