Stata

Stata 18

With Stata, choose the reference in statistical software

Fast. Accurate. Easy to use.

Stata is a complete and integrated software that meets all your data science needs: powerful statistical analyses, customizable visualizations, easy data manipulation, and automated reproducible reporting, all in one complete package.

Take your research further with the newest features in Stata 18.

5 good reasons to use this software

  • Complete statistical software
  • Easy to use and learn
  • Reference software for econometrics, epidemiology and survey processing
  • Rich technical support and documentation
  • Easy and fast processing of large data sets
Stata offers advantages over other similar software packages in that it is user-friendly, flexible through its programming and graphics interface, has excellent help files and command manuals, and a large, worldwide user-network.
Sunčica Vujić
Associate Professor of Applied Econometrics at the University of Antwerp

Why choose Stata?

Stata is a comprehensive software that covers all your needs to analyze your data efficiently and accurately: statistics, visualization, data manipulation, automated reports.

The reference in: 

  • Econometrics
  • Epidemiology
  • Survey processing
  • Behavioral Science
  • Biostatistics
  • Data science
  • Institutional Research
  • Medicine
  • Political Science
  • Education
  • Finance, business and marketing
  • Public Health
  • Public Policy
  • Sociology

Data management

Stata offers many features allowing you a total control over your data:

  • Import/Export
  • Data transformation
  •  ODBC support
  • Combination of datasets,
  • Specific data management (cross-sectional data: panel data, time series, longitudinal data, slice data…)

Key statistical features

Stata gives you access to a wide range of statistical features:

Contrast; Pairewise; Comparison and margins; Epidemiology; GMM; Longitudinal data/panel data; Bayesian analysis; Structural Equation Modelling (SEM); Survey processing; Treatment effects; Time series….

Quality graphics

You can easily generate quality graphics for your publications and reports:

Graphic - Stata 18

Reproducibility, Testing and Certification (FDA)

  • Reproducibility between different operating systems and between different editions of Stata
  • Tested, verified, and certified commands and functions
  • Certified by the FDA for submissions to regulatory agencies

Ease of use

Stata offers a user-friendly interface allowing easy access to all features, even for non- programmers.

StataCorp Technical Support

  • As a user of the current edition of Stata (Stata 18), you are entitled to free technical support
  • Quick, clear, precise and detailed answers
  • A dedicated team of researchers and experts (master, PHD)

Documentation, resource sharing, user community

As a Stata user, you have access to many resources and can count on a very dynamic community:

  • 35 manuals with over 18,000 pages
  • User forum, Stata researchers’ blog
  • Stata Journal: quarterly class A journal
  • Stata International Conferences

Cross-platform compatible

Stata is compatible with Windows, Mac and Linux platforms.

An edition that adapts to your needs

Depending on the power of your computers and the volume of data to be processed, Stata offers a range of 3 different editions to suit your needs:

  • Stata/BE: Basic edition; for medium-sized datasets
  • Stata/SE: Standard edition; for larger datasets
  • Stata/MP: Multi-Processors; the fastest edition of Stata (for dual-core, quad-core and multi-core/multi- processor computers); for the largest datasets

Affordable price

Stata is offered as a complete package, without any additional module!

All Stata Versions offer the same features, but here are several purchase options to fit your specific needs, whether you have large datasets to handle or are in need for the fastest computing ever.

Annual and multiyear subscriptions are the easiest way to secure access to the latest features and keep you focus on your research.

SoftwareMax. number of variablesMax. number of right-hand variablesMax. number of observations64-bit edition availableDesign for parallel
computing
?
Platforms
Stata/MP120 00065 53220 billion*YesYesWin, Mac (64-bits) or Unix
Stata/SE32 76710 9982.14 billion*YesNoWin, Mac or Unix
Stata/BE2 0487982.14 billion*YesNoWin, Mac or Unix

Features

Stata includes a wide range of features to meet all your data science needs. Some of the key features are listed below:

Summaries; cross-tabulations; correlations; t-tests; equality of variance tests; proportion tests; confidence intervals; factorial variables...

Curves; scatterplots; histograms; pie charts; hi-lo charts; contour plots; graph editor; diagnostic regression plots; non-parametric smoothers; Q-Q graph distribution...

Results window; Command window; Examination window; Data editor; Head of variables; Ne-file editor; Variable properties; Viewer; Clipboard preview tool; Menus/dialogs for all commands; multiple preference sets...

Random and fixed effects with robust standard errors; linear mixed models; random effects probit; GEE; random and fixed Poisson effects; dynamic panel data models; instrumental variables regression models; AR (1) perturbations…

ARIMA; ARFIMA; ARCH/GARCH; VAR; VECM; multivariate GARCH; unobserved component model; state-space models; business schedules; forecasts; impulse-response functions; unit root tests; smoothers…

Continuous and binary outcomes; cross-random effects; ML and REML estimation; residual error structures; support for survey data in multilevel linear models...

Bootstrap; BRR, linearized jackknife and SDR variance estimation; poststratification; DEFF; predictive margins; means; proportions, ratios; totals; summary tables; instrumental variables; probit; Cox regression...

Symmetric and asymmetric designs; factorial, nested and mixed designs; repeated measures; marginal means; contrasts...

Kaplan-Meier and Nelson-Aalen estimators; Cox regression (fragility); parametric models (fragility); competing risks; covariates; left and right censoring; exponential Weibull analysis and Gompertz models; sample size and power analysis...

Graphical model builder; standardized and non-standardized estimates; modification indices; direct and indirect effects; path diagrams; factor scores and other predictions; estimates with groups and invariance tests; goodness of fit; MAR data manipulation by FIML; survey data; pooled data…

Wald tests; LR tests; linear and non-linear combinations; generalized forecasts and predictions; marginal means; least squares means; adjusted means; marginal and partial effects; Hausman tests...

Factor analysis; principal components; discriminant analysis; rotation; multidimensional scaling; procrustes analysis; correspondence analysis; biplots; dendrograms...

Comparison of means, intercepts or slopes; comparison of adjacent categories; comparison with reference or grand mean category; orthogonal polynomials; adjustment for multiple comparisons; treatment effects; graphical effects and potential outcomes…

Ten link functions; user-defined links; seven distributions; ML and IRLS estimation; nine variance estimators; seven residuals…

Rate normalization; case-control; cohort; matched case-control; Mantel-Haenszel; pharmacokinetics; ROC analysis; ICD-9-CM...

Wilcoxon-Mann-Whitney ranks; Wilcoxon and Kruskal-Wallis tests; Spearman and Kendall correlations; Kolmogorov-Smirnov tests; exact binomial CI; survival data; ROC analysis; smoothing; bootstrapping…

Sample size and power; Kappa measure of agreement between two coders; Cronbach's alpha, normality tests; mathematical and statistical functions...

Exact logistics and Poisson regression; exact case-control study; binomial test; Fisher's exact test for r × c tables...

Generalized method of moments (GMM); non-linear regression...

Bootstrap; jackknife; Monte Carlo simulation, permutation test...

User-specified functions; NR, DFP, BFGS, BHHH; OIM, OPG, robust, bootstrap, and jackknife matrices; Wald tests; survey data; numerical or analytical derivatives…

Adding new commands; scripting commands; if; while; parsing commands; debugging; programming menu and dialog box; markup and control language...

IQ report for regulatory agencies such as the FDA; verification of the accessibility of the facility for people with disabilities...

Thousands of free additions: for meta-analysis; data management; survival; econometrics...

Ability to install new commands; web updates; web file sharing; latest news from Stata and much more...

What’s new in the Stata 18 edition

Stata 18 presents a wide range of new features! Here is a zoom on some of the main features:

Bayesian model averaging (BMA)

Uncertain which predictors to use in your regression? Model averaging can help! Use this feature to account for model uncertainty in your analysis, explore influential models and predictors, get better predictions, and more.

Stata - Bayesian model averaging

Causal mediation analysis

This new feature allows you to evaluate how the treatment affects the outcome. You can also estimate direct, indirect and total effects. You can fit models for continuous, binary and count outcomes as well as mediators. The mediate command is very flexible and supports 24 combinations of models.

Causal mediation analysis

Heterogeneous difference in differences (DID)

Estimate treatment effects that vary over groups and time. You can fit models for repeated cross-sectional or panel data. You can also visualize effects and aggregate them within group, time, or exposure to treatment.

Heterogeneous difference in differences (DID)

Relative excess risk due to interaction (RERI)

Use RERI to determine how do exposures interact to increase risk? You can fit logistic, binomial, Poisson, Cox, and other models. You can also estimate relative excess risk due to interaction (RERI), attributable proportion and the synergy index.

Relative excess risk due to interaction (RERI)

Robust inference for linear models

Stata 18 offers new ways to obtain standard errors and confidence intervals for linear models fit with regress, aref and xtreg, fe. You can estimate cluster-robust standard errors, with few clusters, unbalanced clusters or multiple clustering variables. You can now add the vce(hc2 clustvar) option to obtain HC2 cluster-robust standard errors. Also use the wild cluster bootstrap for robust p-values and confidence intervals.

Robust inference for linear models

Stata 18 offers other major new features among which:

  • Tables of descriptive statistics
  • Group sequential designs
  • Multilevel meta-analysis
  • Meta-analysis for prevalence
  • Wild cluster bootstrap
  • Local projections for IRFs
  • Flexible demand system models
  • TVCs with interval-censored Cox model
  • Lasso for Cox model
  • IV quantile regression
  • IV fractional probit model
  • Alias variables across frames
  • Data Editor enhancements
  • Do-file Editor enhancements
  • All-new graph style

Find in detail all the new key features of Stata 18 here.

This new version also includes the following new features / optimizations:

  • Corrected and consistent AIC
  • Model selection for ARIMA and ARFIMA
  • GOF plots for survival models
  • New spline functions
  • Graph colors by variable
  • Create, load, and save sets of frames
  • Boost-based regular expressions
  • Vectorized numerical integration
  • New reporting features in putdocx, putexcel, and putpdf

Configuration

Operating systems

Operating systemVersion
Microsoft WindowsWindows 11*
Windows 10*
Windows Server 2022, 2019, 2016, 2012R2*
Apple MacOSMac with Apple Silicon or Intel processor (Core i3 or higher)
MacOS 11.0 (Big Sur) or higher for Macs with Apple Silicon and MacOS 10.13 (High Sierra) or newer for Macs with Intel 64-bit processors
LinuxAny 64-bit architecture (Core i3 equivalent or better) running Linux
Minimum requirements include the GNU C library (glibc) 2.17 or higher and libcurl4
For Stata, you must have GTK 2.24 installed
(*) Windows 64-bit

Memory and disk space configuration

PackageRandom Access Memory (RAM)Disk space
Stata/MP
Fast and powerful
4 GB2 GB
Stata/SE
large data sets
2 GB2 GB
Stata/BE
basic edition
1 GB2 GB
Stata on Unix requires a graphics card that can display thousands of colors or more (16 – bit or 24-bit colors).


Starting from (excl tax)
Prices
Subscription
160 € / year
Student subscription
51 € / year