Sex interactions PLUS Education dummies, i.e.:

 MODEL: CON1=A_M*WIN1*(SEX=M) + A_F*WIN1*(SEX=F)+A_E1*(Educ=1)+...+A_E4*(Educ=4)

                                      TOBIT ESTIMATION
      Dependent variable: CON1
  Number of observations = 456  Schwarz B.I.C. = 1458.02
 Number of positive obs. = 331  Log likelihood = -1439.65
 Fraction of positive obs. =    0.725877    

                          Standard
 Parameter  Estimate        Error       t-statistic   P-value
 WIN1SEXM   .177529       .028110       6.31552       [.000]
 WIN1SEXF   .251317       .055416       4.53508       [.000]
 EDUC1      4.12033       1.58832       2.59414       [.009]
 EDUC2      4.06210       1.09276       3.71728       [.000]
 EDUC3      5.07477       1.34069       3.78520       [.000]
 EDUC4      9.48241       2.28415       4.15140       [.000]
 SIGMA      13.0708       .543156       24.0645       [.000]

 Standard Errors computed from   analytic second derivatives 
 (Newton)

                                      dP/dX

                      0             1 
 WIN1SEXM    -0.0043875     0.0043875 
 WIN1SEXF    -0.0062111     0.0062111 
 EDUC1         -0.10183       0.10183 
 EDUC2         -0.10039       0.10039 
 EDUC3         -0.12542       0.12542 
 EDUC4         -0.23435       0.23435