where ? k is the vector of h coefficients corresponding to the k th occupation group. The total number of parameters to be estimated is h(N – 1), since coefficients for each element of x are determined only up to an arbitrary normalization. Thus, the estimated coefficients for each occupation group do not represent marginal probabilities, but indicate the change in the log of odds of being in that occupation instead of in unskilled occupations.
Because of the ranking the latest coefficients off certain changeable by the proportions, we are able to see the relative feeling of the changeable on the likelihood of being in particular job
Brand new quotes of one’s multinomial logit model imply that there is certainly differential accessibility occupations predicated on gender (look for upper panel away from Desk 8). The latest coefficient with the female dummy is much distinctive from zero in five field organizations plus the indication varies all over work. Ceteris paribus, the likelihood of are an employer or bush and you may servers operator is lower (the newest coefficient on the female dummy try bad and tall) plus the likelihood of are a professional, professional and you will user top-notch or an effective clerical staff member is actually highest (the brand new coefficient with the women dummy was positive and high) for females versus dudes.
There is absolutely no factor between men about odds of getting engaged as the solution and sales specialists or becoming when dГјnyanД±n en ateЕџli kadД±nlarД± you look at the interest and relevant trade
To measure the impact of differences in “tastes”, hiring prejudices, or other unobservable factors on the occupational distribution, we estimate a separate model of occupational attainment for men (see lower panel of Table 8). Employing these estimates, we obtain the predicted distribution for each sex as follows: substitute the sample data for each sex into the estimated model, producing for each individual a vector of predicted probabilities of belonging to each of the eight occupation groups, and calculate the mean of the predicted probabilities for each occupation after summing over observations. For men this estimation yields a predicted distribution which is identical to their actual sample distribution, i.e., M p = M a . The difference in the predicted distributions of men and women (M a –W p ), is the ‘explained’ component due to difference in characteristics, and the residual difference, (W p –W a ), is the ‘unexplained’ component due to differences in tastes, hiring prejudices, or other unobservable factors.
The outcomes of your own decomposition do so try displayed when you look at the higher panel out of Dining table 9. We attract generally towards decompositions for the higher differences in the real take to withdrawals. The fresh new exercise suggests that when the there is no differential use of job by the gender, the new ratio of women engaged while the professionals, auto mechanics and you can representative pros, and you can clerks could well be far smaller than observed, in addition to ratio of women interested as professionals and you will plant operators was considerably higher than noticed (column 5). The remaining “unexplained” parts makes up about to 73-78 % of noticed difference between women and men for the the brand new dimensions engaged in top-notch and you will clerical business, and you may 97 % regarding bush and you may servers operators (column seven). Because of the character ones employment, which probably reflects “supply-side” variations in needs of women for light-collar perform. To possess managers and you can older authorities, the rest of the “unexplained” differences (0.0269) is basically higher than the newest noticed improvement (0.0198). In the event that discover no differential entry to profession by gender, the brand new ratio during the managerial ranks could be highest for females than just for males. It is sometimes complicated to help you ascribe that it looking for so you can “supply-side” difference in choice.