Table 5.
Model | Probit Regression Coefficient | Odds Ratio [95% CI] | 1st IV condition X2/F [df] | 2nd IV condition X2 [df] | Exogenous Cigarettes X2 [1] |
---|---|---|---|---|---|
Excluding OTHER_BEHAVIOR | |||||
Probit – | 0.023** (0.011) | 1.26** [1.02,1.56] | |||
CML-IV probit – Instrument Specification 1 | 0.172*** (0.046) | 5.5* [0.65,11.5] | 13.88** [6] | 2.49 [5]; p=0.78 | 4.93** |
Two stage IV probit – Instrument Specification 1 | 0.190** (0.081) | 5.1* [0.99,11.26] | 2.63** [6, 831] | 4.51** | |
CML-IV probit under alternative instrument specifications | |||||
Instrument Specification 2 | 0.181*** (0.045) | 5.88* [0.97,9.95] | 13.17** [6] | 2.04 [3]; p=0.56 | 5.51** |
Note: The models are based on a sample size of 856 observations. Standard errors of regression coefficients are in parentheses. The 95% confidence bounds of the odds ratio estimates are in brackets. The first IV condition column reports a chi-square test of the joint significance of the instruments in the cigarette 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.