v1.0.0

What's Changed

New features

• ecdf_pit: ensure the envelope starts at 0 and ends at 1 by @aloctavodia in #288
• Add ability to specify a reference model in compare() by @jordandeklerk in #291
• Add functions for loo_subsample to array layer by @jordandeklerk in #287
• Use custom rounding rules for summary by @aloctavodia in #294
• Add custom rounding rules to compare by @aloctavodia in #304
• Add diagnose by @aloctavodia in #299

Maintenance and bug fixes

• Fix CI after arviz-base and h5netcdf updates by @tomicapretto in #286
• Fix bins computation by @aloctavodia in #295
• Fix bug compute_pit_for_histogram by @aloctavodia in #308
• update dependencies by @OriolAbril in #309

Documentation

• Add missing entry for mean and median by @aloctavodia in #292
• Improvements to contributing docs and workflow by @OriolAbril in #296

Full Changelog: v0.8.0...v1.0.0

v0.8.0

What's Changed

New features

• Add original Pareto k to ELPDData for moment matching by @jordandeklerk in #246
• Track full importance weights and compute n_eff_i in moment matching by @jordandeklerk in #248
• Add group argument to residual_r2 and bayesian_r2 by @aloctavodia in #254
• Add mean and median functions, use consistent rounding by @aloctavodia in #255
• Add calculate_khat_bin_edges for Pareto k diagnostics by @jordandeklerk in #257
• Expose moment matched log-weights by @jordandeklerk in #253
• Change internal Pareto stacking dimension name by @jordandeklerk in #259
• Add array-only interface for loo() by @jordandeklerk in #251
• Add mixture importance sampling LOO-CV support by @jordandeklerk in #260
• Add function to weight predictions by @aloctavodia in #263
• Add bfmi by @aloctavodia in #270
• Add top_only argument and match density by @aloctavodia in #272
• Add function to compute density diagnostics by @aloctavodia in #273
• Add fmt argument to summary by @aloctavodia in #280

Maintenance and bug fixes

• Fix r2_score and add more R2 flavors by @aloctavodia in #242
• Use faster cdf for hypergeometric by @aloctavodia in #256
• Fix bug, remove bootstrapping, and handle residuals for ppc_pava by @aloctavodia in #261
• Fix histogram and ecdf for multiple models by @aloctavodia in #264
• Fix qds for plotting by @aloctavodia in #266
• Add numba to docs tox environment by @jordandeklerk in #268
• Centralize PSIS-LOO-CV computations in array layer by @jordandeklerk in #267
• Fix finite-sample bias in PSIS-LOO CRPS/SCRPS by @jordandeklerk in #271
• Fix and simplify computation for rootogram data also adds option for median and mode by @aloctavodia in #274
• Use processed dts in difference_ecdf_pit by @aloctavodia in #276
• Bump the actions group with 2 updates by @dependabot[bot] in #277
• Move more LOO functions into the array layer by @jordandeklerk in #275
• Return non finite values unmodified by @aloctavodia in #278

Documentation

• Add version attribute and api crosref by @OriolAbril in #245
• Correct some minor grammar issues by @star1327p in #247
• Add link to moment matching EABM chapter by @jordandeklerk in #252
• Add link to EABM for posterior corrections by @jordandeklerk in #265

New Contributors

• @tomicapretto made their first contribution in #282

Full Changelog: v0.7.0...v0.8.0

v0.7.0

What's Changed

New features

• Add reloo for exact refitting in PSIS-LOO-CV by @jordandeklerk in #148
• Add method for multiple chains, remove optimization method by @aloctavodia in #151
• Log Weights API change for LOO functions by @jordandeklerk in #156
• Add warnings for finite data and fix computation for discrete data by @aloctavodia in #159
• Add loo_kfold for exact K-fold cross validation by @jordandeklerk in #158
• Compute isotonic regression for categorical and ordinal data by @aloctavodia in #167
• Organize computations for visualizations and make it easy to apply on groupbys by @OriolAbril in #162
• Add functionality to compute quantile dots by @aloctavodia in #171
• Add mode computation by @aloctavodia in #174
• Add support for Jacobian adjustment to elpd_loo values by @jordandeklerk in #175
• Add more informative errors for model comparison in compare() by @jordandeklerk in #184
• Add loo_i function for single observation PSIS-LOO-CV computation by @jordandeklerk in #182
• Add correct output for loo_kfold() by @jordandeklerk in #190
• Implement array interface ecdf by @aloctavodia in #188
• Add function loo_score() for CRPS and SCRPS using PWM identity by @jordandeklerk in #196
• Update default ci_prob value by @aloctavodia in #200
• Add functions to support plot_ppc_censored by @aloctavodia in #203
• Add subsampling support in compare() by @jordandeklerk in #216
• Add order statistic diagnostic for compare() by @jordandeklerk in #237

Maintenance and bug fixes

• Remove extra metrics.py file by @OriolAbril in #152
• Fix function-specific k-hat computation by @jordandeklerk in #165
• Fix loo_moment_match to be more modular by @jordandeklerk in #166
• Bump actions/download-artifact from 4 to 5 by @dependabot[bot] in #173
• Bump actions/checkout from 4 to 5 by @dependabot[bot] in #172
• Bump actions/setup-python from 5 to 6 by @dependabot[bot] in #194
• Fix typing issue in compare() by @jordandeklerk in #198
• Rework PLPD and LPD approximation for loo_subsample() by @jordandeklerk in #192
• Make hypergeom computation more robust by @aloctavodia in #199
• Add callable log likelihood argument to loo_i() by @jordandeklerk in #201
• Robustify pareto_min_ss computation by @aloctavodia in #204
• Survival helper: use view instead of copy by @aloctavodia in #205
• Make pareto_khat consistent with pareto_min_ss by @aloctavodia in #206
• Remove unused function by @aloctavodia in #207
• Add Python 3.13 to tests by @aloctavodia in #209
• Pin numba version by @aloctavodia in #210
• Use a lookup table for hypergeometric computation instead of numba by @aloctavodia in #211
• Fix the sign of PSIS inputs in loo_approximate_posterior() by @jordandeklerk in #213
• Add computational fixes for loo_moment_match() by @jordandeklerk in #212
• Make thin works with arrays by @aloctavodia in #214
• Automatically compute reff for pareto_khat by @aloctavodia in #215
• Patch computations in compare() for subsampling by @jordandeklerk in #217
• Fix stacking weights computation by @aloctavodia in #226
• Add support for Jacobian adjustment to subsampled PSIS-LOO-CV by @jordandeklerk in #227
• Bump actions/download-artifact from 5 to 6 by @dependabot[bot] in #228
• Refactor and expand tests by @jordandeklerk in #220
• Add Jacobian tests for PSIS-LOO-CV subsampling by @jordandeklerk in #231
• Extend CI jobs and tox settings by @OriolAbril in #230
• Remove redundancy in _split_moment_match() by @jordandeklerk in #235

Documentation

• Improve documentation by @jordandeklerk in #197
• Improve the API formatting for arviz_stats.compare by @star1327p in #202
• Remove tutorial section (and duplicated link) by @aloctavodia in #208
• Update the "See Also" parts of API Reference by @star1327p in #221
• Add links to Testing arviz-stats page by @star1327p in #222
• Add link to EABM chapter by @jordandeklerk in #229
• Fix return docstrings for loo functions by @jordandeklerk in #233
• Remove extra references in arviz_stats.rhat by @star1327p in #236
• Fix references and bullet points in arviz_stats.rhat_nested by @star1327p in #239
• Add the reference Säilynoja et al. (2022) from EABM by @star1327p in #241
• Change truncation_factor name to avoid possible confusion by @aloctavodia in #240
• Add tests for numpy logsumexp by @jordandeklerk in #238

New Contributors

• @star1327p made their first contribution in #202

Full Changelog: v0.6.0...v0.7.0

v0.6.0

What's Changed

New Features

• Add loo_pit function by @aloctavodia in #84
• Add randomized loo_pit by @aloctavodia in #85
• Add Nested rhat by @aloctavodia in #87
• Add loo expectations and metrics by @aloctavodia in #89
• Isotonic: add group option by @aloctavodia in #92
• Add group argument to difference_ecdf_pit by @aloctavodia in #94
• Update KDE computation & Bayes factor implementation (#55) by @PiyushPanwarFST in #95
• Adding rank normalisation methods to rhat_nested by @zaxtax in #102
• Add loo_approximate_posterior function by @jordandeklerk in #101
• Add loo_subsample function for large datasets by @jordandeklerk in #106
• Add support for different variable names in loo_pit by @jordandeklerk in #115
• Add R2 by @aloctavodia in #108
• Add Wasserstein distance and KL-divergence by @aloctavodia in #119
• Add "regular" metrics by @aloctavodia in #121
• Fix loo pit randomization by @aloctavodia in #120
• Add ci_in_rope by @aloctavodia in #123
• Add loo_moment_match by @jordandeklerk in #126
• Add function-specific Pareto k-hat for loo_expectations by @jordandeklerk in #132

Maintenance and bug fixes

• Add more tests and examples for loo_metrics by @aloctavodia in #90
• Fix specific test failure by @amaloney in #99
• Autocorr, do not add coords by @aloctavodia in #97
• Start ess ess-related improvements by @OriolAbril in #44
• Testing infrastructure and architecture documentation by @OriolAbril in #103
• Fix ess prob validation by @OriolAbril in #109
• Fix ess prob validation by @OriolAbril in #110
• Fix HDF error in doc build by @OriolAbril in #113
• Improve publish workflow by @OriolAbril in #117
• Improved bayes_factor for multi-variable support by @PiyushPanwarFST in #104
• Fix summary bugs and add tests by @aloctavodia in #128
• psense: update link warning by @aloctavodia in #133
• enforce dim+sample_dims convention on functions by @OriolAbril in #131
• Remove "anes" dataset from tests by @aloctavodia in #135
• update tests to use arviz_base by @aloctavodia in #137
• Computational fixes for loo_moment_match by @jordandeklerk in #141
• raise when extra kwargs present in hdi&kde, add test for eti,hdi,kde&histogram by @OriolAbril in #143

Documentation

• Fix link eabm by @aloctavodia in #105
• Add overview guide by @aloctavodia in #129

New Contributors

• @rohanbabbar04 made their first contribution in #93
• @amaloney made their first contribution in #99
• @zaxtax made their first contribution in #102
• @jordandeklerk made their first contribution in #101

Full Changelog: v0.5.0...v0.6.0

v0.5.0

What's Changed

• Add randomized PIT by @aloctavodia in #75
• Simplify rank_ecdf by @aloctavodia in #76
• Add loo by @aloctavodia in #77
• Add Compare by @aloctavodia in #78
• Cap tail at 20% by @aloctavodia in #79
• Transform PIT values into ETI coverage values by @aloctavodia in #80

New Contributors

• @github-actions made their first contribution in #73

Full Changelog: v.0.4.0...v0.5.0

v.0.4.0

What's Changed

• move in power_scale_dataset from arviz-plots by @aloctavodia in #38
• Use datatree from xarray by @OriolAbril in #35
• Update pyproject.toml by @OriolAbril in #42
• Add functions by @aloctavodia in #39
• Add Rhat and MCSE functions by @aloctavodia in #47
• fix docstring mcse by @aloctavodia in #49
• Add thin function by @aloctavodia in #48
• Add separated prior and likelihood groups by @aloctavodia in #53
• Priorsense functions: allow inferencedata as input by @aloctavodia in #54
• Add bayes_factor function by @PiyushPanwarFST in #52
• Add summary function by @aloctavodia in #51
• Add isotonic regression fit by @aloctavodia in #58
• isotonic_ fit, work on datatrees by @aloctavodia in #60
• psense: Enhance citations and references to external information sources. by @aloctavodia in #57
• utils functions for rootogram by @aloctavodia in #61
• change var_names argument to data_pairs for isotonic fit by @aloctavodia in #64
• Add autocorr accessor to _BaseAccessor class by @suhaani-agarwal in #65
• Ensure we preserve number of observations by @aloctavodia in #66
• Add upper bound sphinx by @aloctavodia in #67
• Add functions for ecdf_pit and simultaneuous confidence bands computations by @aloctavodia in #69
• Automatic changelog and bump version by @aloctavodia in #70
• update dependencies for release by @aloctavodia in #72

New Contributors

• @PiyushPanwarFST made their first contribution in #52
• @suhaani-agarwal made their first contribution in #65

Full Changelog: v0.3.0...v.0.4.0

Release 0.3.0

This will be the final release that uses xarray-datatree library. From here on, the DataTree class from xarray itself will be used.

Initial release

Initial arviz-stats release. It only has a handful of features, mostly for use in arviz-plots. Documentation at https://arviz-stats.readthedocs.io