A New Class of Private Chi-Square Hypothesis Tests
Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, PMLR 54:991-1000, 2017.
In this paper, we develop new test statistics for hypothesis testing over differentially private data. These statistics are designed specifically so that their asymptotic distributions, after accounting for privacy noise, match the asymptotics of the non-private chi-square tests for testing if the multinomial data parameters lie in lower dimensional manifolds (examples include goodness-of-fit and independence testing). Empirically, these new test statistics outperform prior work, which focused on noisy versions of existing statistics.