A data-science study of how visible women's economic activity is: measurement model, uncertainty, sensitivity, scenarios and value of information - United Kingdom

This paper, the eighteenth of nineteen in the G20 member series, measures how visible women’s economic  activity is in the United Kingdom using the Gender Economic Visibility Index (GEVI). The index converts 13  inputs into parity scores, averages them within five dimensions, and combines the dimensions by a weighted  geometric mean, so that a strong dimension cannot fully offset a weak one. Each input carries an evidence  grade that sets its uncertainty, and the paper carries that uncertainty, together with uncertainty about the  weights, through 10,000 joint Monte Carlo draws. It then tests the result against seven weighting schemes  and ten alternative specifications, attributes the gap to full parity with Shapley values, and runs eight  scenarios, a greedy improvement pathway and a value-of-information analysis for the data. 
The United Kingdom scores 91.1 out of 100, in the Visible band, with a 90% interval of 89.2 to 91.6 and a  rank of 1 of 19 that ranges from 1 to 2 across the draws. Its strongest dimension is labour participation  (0.958) and its weakest is enterprise and legal rights (0.841), which accounts for the largest share of the 8.9 point gap to full parity: 3.3 points, or 37%. All 13 inputs are measured (grade A) and none is imputed, so  weight uncertainty, which explains 42.5% of the output variance, drives the spread rather than imputation.  Across the alternative specifications the rank runs from 1 to 2 and the score changes by at most 8.0 points.  Of the six single-lever scenarios, raising the legal and enforcement scores by 0.10 gives the largest gain, +1.4  points, and a greedy pathway reaches the 95-point threshold after five steps. The priorities that follow are  largely about measurement: publishing complaint, prosecution and remedy data so that enforcement can be  measured and not only perceived, funding the missing supporting mechanisms, and publishing women’s  share of senior and middle management on a common definition. No sex-disaggregated taxpayer statistic  was found, so the index does not yet measure visibility in the tax system directly. 
The weights are a prior and the grade-based standard deviations are judgemental settings, not estimates.  The scenarios show what the index would do if an indicator changed, not that a policy would change the  indicator. Scores and intervals are research estimates, not official statistics.