Differentially Private Classical Statistical Inference
![[R logo]](../../../doc/html/Rlogo.svg)
![[Up]](../../../doc/html/left.jpg)
![[Top]](../../../doc/html/up.jpg)
Documentation for package ‘DPrivStats’ version 0.1.0
Help Pages
| advanced_composition_epsilon | Advanced composition |
| analytic_gaussian_mechanism | Analytic Gaussian mechanism |
| analytic_gaussian_sigma | Analytic Gaussian calibration (Balle & Wang, 2018) |
| basic_composition | Basic (sequential) composition |
| can_spend | Check whether a release fits in the remaining budget |
| clip_gradients | Per-sample gradient clipping |
| compare_composition | Compare composition rules over a workflow |
| compare_utility | Compare utility of non-private and private fits |
| confint.dp_lm | Confint interface for dp_lm objects |
| cpp_clip_gradients | Fast per-sample gradient clipping (C++) |
| cpp_rlaplace | Fast Laplace sampling (C++) |
| dp_anova | DP one-way ANOVA F-test |
| dp_chisq_test | DP chi-square test of independence |
| dp_confint | Privacy-aware confidence intervals |
| dp_glm | DP-SGD for generalized linear models |
| dp_histogram | DP histogram |
| dp_ks_test | DP Kolmogorov-Smirnov test |
| dp_lm | Differentially private linear regression |
| dp_lm_sensitivity | Global L2 sensitivity of OLS coefficients |
| dp_mean | DP mean |
| dp_median | DP median via the exponential mechanism |
| dp_quantile | DP quantile via the exponential mechanism |
| dp_t_test | DP two-sample t-test |
| dp_utility_diagnostics | Utility diagnostics for DP estimators |
| dp_variance | DP variance |
| empirical_delta_from_losses | Empirical delta from simulated privacy losses |
| epsilon_to_rdp | Convert epsilon-DP to zCDP (RDP) parameter |
| example_microdata | Census-like example microdata |
| exponential_mechanism | Exponential mechanism sampler |
| gaussian_mechanism | Gaussian mechanism |
| gaussian_sigma | Classic Gaussian noise scale |
| laplace_mechanism | Laplace mechanism |
| laplace_plr_quantile | Privacy loss random variables for the Laplace mechanism |
| laplace_plr_tail | Privacy loss random variables for the Laplace mechanism |
| new_privacy_budget | Create a privacy budget object |
| print.dp_confint | Print method for dp_confint objects |
| print.dp_estimate | Print method for dp_estimate objects |
| print.dp_glm | Print method for dp_glm objects |
| print.dp_htest | Print method for dp_htest objects |
| print.dp_lm | Print method for dp_lm objects |
| print.privacy_budget | Print method for privacy_budget objects |
| print.summary.dp_lm | Print method for summary.dp_lm objects |
| rdp_composition | RDP composition |
| rdp_to_epsilon | Convert zCDP (RDP) parameter to (epsilon, delta)-DP |
| rlaplace | Sample Laplace noise |
| simulate_data | Simulate synthetic microdata |
| simulate_gaussian_losses | Simulate privacy losses of Gaussian releases |
| spend | Spend privacy budget |
| stat_sensitivities | Sensitivity of common bounded-data statistics |
| summary.dp_lm | Summarize a dp_lm fit |
| validate_coverage | Validate confidence-interval coverage by Monte Carlo |