# Table 8 Sex differences in positive employer response probabilities

Model ix

Model x

Δ in effects for a female

Δ in effects for an ex-offender

Δ in effects for a female ex-offender

Criminal past and sex effects

Effects for a male non-offender

Ex-offender

−0.109*** (0.018)

Female applicant

0.062** (0.024)

Female ex-offender

−0.013 (0.024)

Accounting clerk

Baseline category

−0.020 (0.082)

−0.155*** (0.037)

−0.042 (0.125)

Auto mechanic

0.022 (0.095)

0.018 (0.102)

−0.021 (0.052)

−0.018 (0.064)

Cleaner

−0.116* (0.061)

0.142 (0.099)

−0.091** (0.038)

−0.020 (0.071)

Enrolled nurse

−0.009 (0.093)

0.065 (0.103)

−0.082 (0.066)

0.012 (0.123)

Preschool teacher

0.119 (0.098)

0.170** (0.081)

−0.145*** (0.021)

−0.003 (0.063)

Restaurant worker

−0.015 (0.072)

0.032 (0.046)

−0.076*** (0.024)

−0.014 (0.039)

Salesperson

−0.026 (0.080)

0.203 (0.127)

−0.063 (0.047)

−0.090 (0.060)

Software developer

0.156 (0.116)

0.085 (0.102)

−0.150*** (0.027)

0.074 (0.115)

Truck driver

−0.110* (0.058)

−0.061 (0.069)

0.002 (0.041)

0.054 (0.054)

Observations

2078

2078

Pseudo R 2

0.069

0.116

1. Notes: Model ix gives the marginal effects of applicants’ sex and being an ex-offender as well as the interaction between applicants’ sex and being an ex-offender on the probability of receiving a positive response from an employer. Model x gives the main effects of different jobs in the first column (main effects), the change in marginal effects for female applicants in the second column (interaction between female applicant and job dummies), the change in marginal effects for ex-offenders in the third column (interaction between ex-offender and job dummies), and the change in marginal effects for female ex-offenders in the fourth column (interaction between female applicant, ex-offender, and job dummies). The values were estimated using a probit regression model. Corresponding linear probability models and fixed-effects models generate similar results. The dependent variable is a positive response dummy. Also included in each regression are a dummy for full-time positions, a dummy for tenure, county dummies, season dummies, an application template dummy, and a dummy for order of application. Descriptions of all variables are provided in Table 2. Reported standard errors (in parentheses) are corrected for clustering of the observations at the employer level
2. ***p < 0.01, **p < 0.05, *p < 0.10