Skip to main content

Table 8 Logistic regression model

From: Partner HIV serostatus disclosure and determinants of serodiscordance among prevention of mother to child transmission clients in Nigeria

Model summary
Step −2 Log likelihood Cox & Snell R Square Nagelkerke R square
1 389.005a 0.014 0.019
Hosmer and Lemeshow test
Step Chi-square df Sig.
1 5.668 8 0.684
Classification table
  Observed Predicted
   Serodiscordancy Percentage correct
Concordance Serodiscordance
Step 1 HIV Sero-status Concordance 19 116 14.1
Serodiscordance 8 141 94.6
Overall Percentage    56.3
The cut value is .500b
Variables in the equation
  B S.E. Wald df Sig. Exp(B) 95 % C.I.for EXP(B)
Lower Upper
Step 1a WHO_clinical_stage(1) −1.453 0.816 3.167 1 0.075 0.234 0.047 1.159
CD4+ count 0 0 0.436 1 0.509 1 0.999 1.001
Age −0.003 0.024 0.011 1 0.915 0.997 0.951 1.046
Constant 0.363 0.781 0.216 1 0.642 1.438   
  1. Bold data is the test statistics predicts serodiscordant or concodant partner relationaship, since the wald coefficient 3.167 is greater than 0
  2. aEstimation terminated at iteration number 4 because parameter estimates changed by less than .001
  3. bVariable(s) entered on step 1: WHO_clinical_stage, CD4_raw, and Age