Вы находитесь на странице: 1из 1

Fig. 4.5.

the posterior predictive distribution of the D = Y1 – Y2 the difference in the number


of children of two randomly sampled women, one from each of the two educational
populations.

Sampling a women with one ( probabilitas of 0.27 and 0.28, respectively ). These two
distributions seem to be in conflict. If the observed data have twice as many women with two
children than one, why should we be predicting otherwise.

Fig. 4.6. evaluation of model fit. The first panel shows the empirical and posterior predictive
distributions of the number of children of women without a bachelor’s degree. The second
panel shows the posterior predictive distributions of the empirical odds of having two children
versus one child in a dataset of zise n = 111. The observed odds are given in the short vertical
line.

Вам также может понравиться