1. (StataNow) Import data from Parquet files. New command import parquet reads into memory a Parquet file. Most of the Parquet compression methods and variable types are supported.
2. (StataNow) Causal mediation with two mediators. Existing command mediate fits causal mediation models and estimates natural direct, natural indirect, and total effects of a treatment on an outcome. mediate now supports estimation of these effects for two mediator variables. mediate can fit both parallel mediation models (when there is no causal order among mediators) and sequential mediation models (when a causal order exists among mediators). By accounting for each path-specific component of a treatment effect, mediate estimates the finest possible decomposition of a total effect into natural direct and indirect effects. Because the number of decompositions grows at a rapid rate when more than one mediator is included, the finest possible decomposition potentially encompasses many estimands. Coarser decompositions are available by estimating mediator-specific natural effects. Postestimation commands are available to estimate controlled
   direct effects and to perform a sequential mediation sensitivity analysis.
3. (StataNow) Mata quantile function. New Mata function quantile(X, p[, method]) computes quantile values of data matrix X at specified quantile vector p. Optional argument method allows you to choose from several quantile calculation methods, including both discontinuous and continuous piecewise linear methods.

NEW COMMANDS

• The new h2omlgraph permimp command plots permutation variable importance. The graph is useful for identifying influential predictors after using h2oml for gradient boosting or random forest.

© Copyright 1996–2026 StataCorp LLC. All rights reserved.

• You can now obtain regression diagnostic plots after using h2oml gbregress to perform gradient boosting regression or h2oml rfregress to perform random forest regression.
  • h2omlgraph rvfplot graphs the residuals against the fitted values.
  • h2omlgraph rvpplot graphs the residuals against a predictor.
• The Stata–Python API specification has the following new series features for interacting with NumPy arrays and pandas DataFrames
• The new gencohort command creates a cohort variable to be used with hdidregress and xthdidregress.

ADDITIONAL UPDATES

• Command syntax now supports numbers in minimum option abbreviations, identified by capital letters at the beginning of option names. This means you can now define an option name such as case1option with minimum abbrevation case1op by defining the option as CASE1OPtion with the syntax command.
• The estat aggregation command for aggregating average treatment effects on the treated after hdidregress and xthdidregress now allows you to specify the weights() option to determine the type of weights used when aggregating. weights(timecohort) uses weights that vary across cohorts and time periods. weights(cohort) uses weights that vary across cohorts but are constant for all time periods within each cohort.
• The hdidregress and xthdidregress commands now allow the usercohort option for specifying a known cohort variable rather than allowing these commands to determine cohorts based on the time and group variables.