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

This paper studies how visible women’s economic activity is in Australia, one of the 19 sovereign G20 members scored in the series, using the Gender Economic Visibility Index (GEVI). The index converts 13 indicators into parity scores, averages them into five dimensions (labour participation, job quality and seniority, enterprise and legal rights, institutional visibility, and statistical and political voice) and combines the dimensions with a weighted geometric mean, so that a strong dimension cannot fully compensate for a weak one. Every input carries an evidence grade that sets its uncertainty. Australia scores 89.3 out of 100, in the Visible band, with a 90% uncertainty interval of 86.6 to 90.6 from 10,000 joint Monte Carlo draws (median 88.9) and a point rank of 3 of 19 (rank median 3; 5th to 95th percentile range 2 to 3). The strongest dimension is D1 Labour participation (0.961); the weakest is D3 Enterprise and legal rights (0.806). A Shapley attribution of the 10.7-point gap to full parity assigns the largest share, 4.1 points (38%), to D3 Enterprise and legal rights. Of the 13 inputs, 12 are grade A and one (firm ownership) is grade C, imputed from the series median, giving a blind-spot ratio of 0.08; the imputed input widens the interval and explains 46.6% of simulated output variance, against 25.4% for weight uncertainty. Rank runs from 3 to 4 across seven weighting schemes and from 1 to 3 across ten alternative specifications (benchmark, parity cap and imputation rule), with scores moving by at most 8.1 points. The largest single-lever scenario is a +0.10 rise in legal and enforcement scores (S3, +1.3 points), and a greedy pathway of +0.10 steps reaches the 90-point threshold after one step. These pathways order priorities; they are not forecasts. The index contains no direct measure of women’s visibility in taxpayer records, so the paper proposes adding a sex field to wage-tax and taxpayer records and publishing an annual gender tax profile; this would extend the model and is not part of the current score. The priority data actions are to publish women’s share of senior and middle management on a common definition (I5), fund the missing supporting mechanisms (I10) and publish enforcement data (I9). The weights and uncertainty settings are judgmental assumptions, the study is cross-sectional, and the scenarios describe index arithmetic rather than policy effects. All results are reproducible from the accompanying Python scripts with a fixed random seed of 2026; scores and intervals are research estimates, not official statistics.