Stata 18 //top\\ Jun 2026

Furthermore, the software introduces Bayesian Model Averaging (BMA), a sophisticated technique that accounts for model uncertainty by averaging across multiple potential models. This reflects a broader trend in the version toward , which is further supported by an extensive Reference Manual dedicated to these methods. Streamlining Data Communication

This public link is valid for 7 days and shares a thread, including any personal information you added. This link or copies made by others cannot be deleted. If you share with third parties, their policies apply. Can’t copy the link right now. Try again later.

Stata 18 builds upon features introduced in Stata 17 while adding many new ones. Key differences include:

| Feature | Description | Use Case | |---------|-------------|----------| | | Run .md files as dynamic documents, code chunks | Reproducible reports without separate tools | | frame meta-data | frame put + frame rename + frame drop _all | Safer multi-frame workflows | | pystata integration | Run Python in Stata, exchange data via sfi module | ML, string processing, APIs | | Bayesian multilevel | bayes: melogit etc. | Hierarchical models with full Bayes | | Local projections | lpirf for IRFs, lp for general local projections | Panel time series, Jorda’s method | | dtable | Descriptive table with built-in balancing tests | Publication-ready Table 1 | | collect enhancements | collect layout + collect style | Custom table/figure templates |

The command models proportions or rates with endogenous covariates, particularly useful when the dependent variable is bounded between 0 and 1.

: Features "tooltips" that show the full text for values that are too long to fit in a cell. How to display text and calculations using Stata 18

(formerly Intercooled): Handles mid-sized datasets with up to 2,048 variables. Suitable for basic research and teaching.

Creating Table 1 (descriptive statistics table for research papers) becomes dramatically easier with the new command. It reports summary statistics for both continuous and factor variables, exports to multiple formats (Word, Excel, PDF, LaTeX, HTML, Markdown), and supports customization.