Vmayke.vmayke.org

Library/Engineering & Science/StataCorp Stata

Engineering & Science / StataCorp

StataCorp Stata

Statistical analysis, data management and publication graphics in one environment, with the full estimation command set and a reproducible do-file workflow.

Version 17.0
Size 1.42 GB
Edition MP, pre-activated
Updated 2 weeks ago
Downloads 105 945
Rating 4.7 / 5

Overview

Stata is the analysis environment that most economics, epidemiology and political science work still runs through, and the reason is consistency. One data set is in memory, one command syntax covers everything from a summary table to a multilevel mixed effects model, and the do-file that produced a result runs again years later and produces the same numbers. That reproducibility is why journals and research groups keep asking for Stata code rather than a spreadsheet.

The estimation coverage is enormous. Linear and generalised linear models, panel data with fixed and random effects, instrumental variables, survival analysis, time series with ARIMA and state space forms, multilevel models, structural equation modelling with a graphical builder, treatment effects, survey weighted estimation, Bayesian analysis with its own MCMC engine, and a full complement of postestimation commands that produce margins, contrasts and predictions from whatever was just fitted.

Around the statistics sits the part people underrate: data management. Merge, reshape, collapse, encode, labels on variables and values, frames that hold several data sets in memory at once, and an import layer that reads spreadsheets, delimited text, SAS, SPSS and ODBC sources. Graphics are publication ready out of the box with a scheme system, and results export to Word, Excel, LaTeX, HTML and PDF through the reporting commands.

What it does well

Full estimation library

Regression, panel, survival, time series, multilevel, SEM, Bayesian and survey weighted estimators, each with a matching postestimation set.

Reproducible do-files

Scripts capture every step from import to final table, so an analysis reruns identically on another machine years later.

Data frames

Several data sets held in memory at once with linking between them, which removes most of the save and reload churn from a merge heavy project.

Publication graphics

Scatter, line, bar, box, survival and margins plots with a scheme system, editable in a graph editor and exported as vector output.

Reporting commands

Tables and results written straight to Word, Excel, LaTeX, HTML and PDF, so a document rebuilds from the analysis rather than by hand.

Changes in this build

  • Table command rebuilt with a far more flexible layout and collection system for customised output.
  • Bayesian estimation extended with additional model types and faster sampling.
  • Lasso and elastic net commands added for prediction and inference on wide data.
  • Do-file editor gained better autocompletion and inline syntax help.
  • Faster import for very large delimited files and improved ODBC handling.

What is in the package

  • Stata offline installer, 64-bit
  • Complete command and estimation library
  • Full documentation set in PDF, linked from the help system
  • Example data sets used throughout the manuals
  • Graph scheme library and export templates

System requirements

ProcessorIntel or AMD 64-bit, multicore strongly recommended
Memory8 GB minimum, 32 GB or more for large panel data
GraphicsAny GPU with a current driver
Storage4 GB free for the install plus space for data
Display1920 x 1080 recommended
SystemWindows 10 or Windows 11, 64-bit

Installation

  1. Extract the archive to a local drive, not a network share.
  2. Run the setup binary and accept the default install path.
  3. Complete the configuration step included with the package before first launch.
  4. Start the application and set the memory allocation for your data size.
  5. Point the working directory at your project folder so do-files resolve relative paths.

Before you start

Set the working directory at the top of every do-file, it is the single most common cause of a script failing on another machine.

Frames make merges easier but they also make it easy to analyse the wrong data set, name them clearly.

Turn off the update check so the installed build stays exactly where it is.

Questions about this title

Which edition is this?

The MP configuration, which uses multiple cores and carries the highest variable and observation limits.

Is the documentation included?

Yes, the full manual set installs as PDF and is linked from every help entry.

Can it read SPSS or SAS files?

Yes, the import commands handle both, along with spreadsheets, delimited text and ODBC sources.

Will my old do-files run?

Yes, and the version control command lets a script pin itself to older syntax behaviour if needed.

About this listing

This entry was checked on a clean install of Windows 10 / 11 (64-bit) before it was published, and it is rechecked whenever the package is rebuilt. The figures on this page come from the site index rather than from the publisher, so the download count is what people here have actually pulled.

If a mirror stops answering, use the contact form and it gets replaced. Reports about a specific title are handled faster than general messages because they name the file, the mirror and the point at which the transfer stopped.

Requests for a different version, a different language build or an older release go on the requests page. Older versions of a title are usually still held even when only the current one is listed.