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.
By the positions the fresh coefficients off certain adjustable from the dimensions, we can understand the cousin feeling of this adjustable towards the probabilities of staying in particular jobs
The estimates of one’s multinomial logit model mean that discover differential use of business considering gender (pick upper panel away from Desk 8). The brand new coefficient with the women dummy is a lot different from zero when you look at the five field communities as well as the signal may differ across the jobs. Ceteris paribus, the probability of getting an employer otherwise bush and you can host user is leaner (the fresh coefficient to the feminine dummy is actually negative and extreme) plus the probability of are a professional, specialist and you can user professional otherwise good clerical personnel are higher (new coefficient into female dummy was confident and you can high) for females than the dudes.
There isn’t any factor ranging from individuals from the probability of becoming interested while the solution and sales pros or being in the hobby and you will associated 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 results of your own decomposition take action try exhibited when you look at the higher panel of Table nine. We interest primarily towards the decompositions with the higher variations in the genuine shot distributions. The brand new do so means that in the event that you will find zero Cusco marriage website differential access to job of the gender, the new proportion of women engaged just like the pros, auto mechanics and you will associate professionals, and you may clerks will be much smaller compared to noticed, and the proportion of females involved given that professionals and you will plant operators could be more higher than observed (line 5). The remaining “unexplained” part is the reason doing 73-78 percent of seen difference in both women and men during the new dimensions engaged in elite group and you may clerical employment, and 97 % regarding bush and machine operators (column seven). Because of the character of those job, which almost certainly reflects “supply-side” variations in choice of women for light-collar operate. To own managers and you may senior officials, the rest of the “unexplained” change (0.0269) is actually higher than the new observed improvement (0.0198). In the event that you will find zero differential the means to access career by gender, the brand new proportion inside the managerial ranking was high for women than simply for men. It is sometimes complicated to ascribe it trying to find so you can “supply-side” difference between preferences.
