Table 2.
Model | Probit Regression Coefficient | Odds Ratio [95% CI] | 1st IV condition X2 [df] | 2nd IV condition X2 [df] | Exogenous Cigarettes X2 [1] |
---|---|---|---|---|---|
Cigarettes before Pregnancy | |||||
Probit | 0.013* (0.007) [0.005*] | 1.2* [0.97,1.48] | |||
CML-IV probit | 0.100*** (0.029) [0.033***] | 4.16** [1.06,8.0] | 26.87*** [8] | 3.3 [7]; p=0.86 | 5.7** |
Cigarettes in the first trimester | |||||
Probit | 0.020* (0.011) [0.008*] | 1.21* [0.98,1.52] | |||
CML-IV probit | 0.172*** (0.046) [0.057***] | 5.41* [0.88,9.81] | 15.54** [6] | 2.52 [5]; 0.77 | 5.31** |
Note: The models are based on a sample size of 856 observations. Standard errors of regression coefficients are in parentheses. The marginal effects of cigarettes, evaluated holding all model variables at their means, are listed in brackets under the regression coefficient column (the standard errors of the marginal effects are suppressed for simplicity but are available from the authors upon request). The 95% confidence bounds of the odds ratio estimates are in brackets. The first IV condition column reports a chisquare test of the joint significance of the instruments in the cigarettes function (degrees of freedom [df] in brackets). The second IV condition reports the over-identification chi-square test (df in brackets).
p < 0.1,
p < 0.05,
p < 0.01.