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 sД±cak lehГ§e kadД±nlar unskilled occupations.
By the ranks the coefficients regarding a given variable from the proportions, we can comprehend the cousin impression of this adjustable to the probabilities of being in certain job
The fresh estimates of your multinomial logit design signify there was differential usage of employment based on gender (pick top committee out of Table 8). New coefficient on the women dummy is a lot unlike no within the five field communities together with signal may vary across the job. Ceteris paribus, the chances of becoming an employer otherwise plant and you may server operator is lower (the newest coefficient towards the women dummy was bad and you can extreme) additionally the odds of being an expert, specialist and you will user elite group otherwise an excellent clerical worker try high (brand new coefficient on the female dummy is self-confident and you will high) for women compared to men.
There’s no factor anywhere between anyone regarding the odds of being engaged just like the provider and conversion experts or becoming into the craft and you may associated trading
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 outcome of one’s decomposition get it done are displayed in the upper panel out-of Table nine. I appeal primarily toward decompositions with the highest differences in the actual sample withdrawals. The fresh new do it shows that in the event that there’s zero differential access to career because of the gender, new proportion of females involved because professionals, mechanics and you can member experts, and you will clerks will be far smaller than observed, while the ratio of females involved as the managers and you will bush operators could be much more greater than observed (line 5). The rest of the “unexplained” component accounts for as much as 73-78 percent of the seen difference in people when you look at the the fresh new dimensions involved with elite group and clerical employment, and you can 97 % in the case of plant and you will servers operators (line 7). Given the nature ones jobs, this more than likely reflects “supply-side” differences in choices of women to possess white-neckband efforts. To own professionals and you will senior authorities, the rest of the “unexplained” variation (0.0269) is basically greater than the brand new observed distinction (0.0198). When the there is no differential usage of job because of the gender, the fresh new proportion inside managerial ranks might be large for ladies than just for men. It is sometimes complicated to help you ascribe that it interested in to help you “supply-side” difference in tastes.
