Another way this result should manifest itself is in the changes in the estimated race gaps in wages for the alternative subsamples. In particular, when statistical discrimination is likely to be more important (i.e., for the probationary workers) the estimates should indicate that a larger fraction of estimated race gaps in wages are attributable to statistical discrimination. Table 5 reports these results, providing the estimated race coefficients corresponding to the specifications in Table 4 for the male-only sample.35 The results for both blacks and Hispanics are consistent with expectations. Simply using the point estimates, the estimated proportion of the wage gap attributable to statistical discrimination is higher for the probationary workers. Indeed, for the probationary workers the IV estimates of the race/ethnicity gaps in wages are non-negative, whereas for the non-probationary workers the IV estimates of these gaps are about three-fourths as large as the OLS estimates. In results for women not reported in the table, the same conclusion emerged.

(1) (2) (3) (4) (5) (6) (7) (8) (9)
В. Usine loe performance ratine
Performance rating .062(.068) -.021(.062) 1.623(.613) .006(.063) 2.184(.642) .041(.067) 2.627(.704) 3.028(.764)
Black -.136(.036) -.156(.036) -.108(.055) -.173(.037) -.096(.066) -.186(.039) -.090(.076) -.075(.084)
Hispanic -.010(.037) -.042(.037) -.044(.054) -.062(.038) -.051(.065) -.042(.040) -.033(.073) -.031(.081)
R2 .228 .001 .204 .148 .037
P-value from F-test of instruments in first-stage regression:
Age variables only Education variables only .21.00
Job requirement variables only .82
Instruments Educ. Educ., age Educ., age Educ., age, job requirements
F-statistic on instruments in
first-stage regression: 4.58 3.60 3.94 2.56
Overidentifying restrictions, p-value: .52 .84 .12
Bias in OLS estimates, p-value from Hausman test:
Performance rating .01 .00 .00 .00
Black .25 .16 .14 .13
Hispanic .96 .82 .88 .88

For black-white differences (there are essentially no Hispanic-white differences for women, as shown in Table 3), the estimated proportion of the wage gap due to statistical discrimination was .06-. 13 for the non-probationary sample, compared with .43-.51 for the probationary sample. Thus, in general, the findings for tests of statistical versus taste discrimination are consistent with the IV results being driven by imperfect information on the part of employers.