TABLE 4
FROM:
The Effect of Childhood Sexual Victimization on Women's Income
John Robst and Stacy Smith
BACK TO ARTICLETable 4. Logistic regression results: the relationship between characteristics of abuse and self-reported effects
| Coef | Marg eff | |
|---|---|---|
| Intercept | -0.1428 (0.845) | |
| Intercourse | 2.363* (1.36) | 0.138 |
| Perpetrator was an adult | 0.3919 (0.598) | 0.042 |
| Number of people who abused respondent a few times | 0.7592* (0.433) | 0.139 |
| Number of people who abused respondent several times | 1.879** (0.769) | 0.344 |
| Intrafamilial abuse | -0.9051* (0.486) | -0.095 |
| Years before puberty abuse began | 0.1203 (0.098) | 0.022 |
| N | 137 | |
| Proportion reporting effects | 75.9% | |
| Likelihood ratio | 22.5 |
Notes: Standard errors are in parentheses.
** P<0.05; * P<0.10.
The marginal effects are computed as 
p(1-p) for continuous variables, and for categorical variables the difference in predicted probabilities with the categorical variables set to 0 and 1.