Confidence intervals were chosen as an estimation of the accuracy of the estimated means.
The coloured solid lines show the estimated means and the shaded areas represent 95% posterior credible regions around the estimated means.
For each combination, we computed the range L of the interval containing 95% of the 10,000 estimated means.
This statistical design controls for between-group differences in each co-factor when generating estimated means.
There was no significant correlation between the estimated means for AP or AIx75 and age, parity, BMI or smoking.
Then, as above, we estimated means and confidence intervals for λ and the percentage of runs with λ<1 for the six scenarios over 1000 parametric bootstrap runs.
The estimated means were used to create 2 composite images representing women who looked either old or young for their age.
First, we estimated means and confidence intervals for λ and stable stage distributions for the Isolated tributary using the parametric bootstrap approach outlined in Supplemental Text S1.
The standard error of all estimated means is 1.87.
** Defined as the difference of estimated means within both subgroups.
The estimated means in coke ovens, gasworks, and aluminum production works were similar (1.15 1.17).
