ERM - models to fit linear models, probit model and ordered probit models with endogenous co-variates, sample selection and non-random treatment assignment.
Latent class analysis (LCA)
Discover and understand the unobserved groupings in your data. Use LCA's model based classification to find out
how many groups you have
who is in those groups
what makes those groups distinct
Stata's new dsge command estimates the parameters of DSGE models that are linear in the variables but potentially nonlinear in the parameters.
Markdown and dynamic documents
Create webpages from Stata
Intermix text, regressions, results, graphs, etc
See changes in data or commands automatically reflected on webpages.
Power analysis for linear regression
Stata's power command performs power and sample-size analysis (PSS). Its features now include PSS for linear regression.
Finite mixture models (FMMs)
Model the probability of belonging to each unobserved group; estimate distinct parameters of a regression model or distribution in each group; classify individuals into the groups; and draw inferences about each group behaviour.
Bayes logic and
The bayes prefix combines Bayesian features with Stata's intuitive and elegant specification of regression models.
Create Word documents with embedded Stata results
Create Word, PDF, or HTML files to report results direct from Stata using three new commands.
Spatial autoregressive models
Spatial autoregressive (SAR) models are fit using datasets that contain observations on geographical areas or on any units with a spatial representation.
Interval-censored survival models
Fit any of Stata's six parametric survival models to interval-censored data. All the usual survival features are supported.
Non-linear multi-level mixed-effects models
Because some problems are not linear in the parameters.
Mixed logit models: Advanced choice modelling
People make decisions every day and researchers have access to much of the data about their choices. Mixed logit introduces random effects into choice modelling relaxing the IIA assumption and increases flexibility.
Bayesian multi-level models
If you have only a small number of groups or many hierarchical levels or would prefer making probability statements then consider Bayesian multi-level modelling.
Time-series regression may change at a certain point in time or at multiple points. You may not know that threshold. Stata can now help to estimate the thresholds.
Search, browse, and import FRED data
The St. Louis Federal Reserve makes over 470,000 US and International time series available. Search, browse and import direct from Stata.
When you know that something matters, but you don't know how.
Panel-data tobit with random coefficients
Stata now has the option for random coefficients.
Panel-data cointegration tests
Researchers use cointegration tests when time-series are non-stationary to determine whether they have a stable, long-run relationship.
Multi-level regression for interval-measured outcomes
Sometimes incomes are recorded in groupings as are people's weights, insect counts and more. In these cases we need multilevel regression for interval measured outcomes.
Multi-level tobit regression for censored outcomes
The new metobit command fits multilevel and panel-data models for which the outcome is censored.
Stata now allows alignment to US diagnosis codes. icd10cm and icd10pcs let you validate diagnosis codes, add new variables as code descriptions and indicators.
Tests for multiple breaks in time series
When you fit a time-series regression there is an assumption that the co-efficients are stable over time. The new estat sbcusum tests that assumption.
Multiple-group generalised SEM
Generalise SEM now supports multiple-group analysis. GSEM models include continuous, binary, ordinal, count, categorical, survival and multilevel models.
Hetroskedastic linear regression
Stata's new command hetregress fits linear regressions in which the variance is an exponential function of covariates that you specify.
Power for cluster randomised designs
Power analysis for comparing one and two sample means, one and two sample proportions and two sample survival curves.
Power for linear regressions models
Stata's power command performs power and sample-size analysis. Its features include PSS for regression.
More in graphics
Stata 15 introduces transparency in graphs and you can now export graphs as scalable vector graphics (.svg) format.
Poisson models with sample selection
New command heckpoisson fits models to count data and produces estimates as though the sample selection did not occur.
More in panel data
Non-linear models with random effects including random coefficients.
Bayesian panel data models.
Interval regression with random intercepts and random coefficients.
More in statistics
Bayesian survival models.
Zero-inflated ordered probit.
Add your own power and sample-size methods.
Bayesian sample-selection methods.
Now in Simplified Chinese
In addition to improvements in the Do-file editor, the Stata interface is now available in simplified Chinese.