Formats estimation output as a publication-quality regression table with stars, SEs, and fit statistics. Use when creating a results table.
Create a publication-quality regression table from estimation output in a notebook.
$ARGUMENTS — a notebook reference and/or description of the table (e.g., "notebook-02 OLS results" or "main regression table with 3 specifications")Identify the source notebook and the estimation output:
pyfixest, statsmodels, linearmodels; R: fixest, lm, felm; Stata: reg, reghdfe, ivregress)Ask the user for table specifications:
Build the table manually as pipe-delimited Markdown (do NOT use pf.etable(type="md"), etable(markdown=TRUE), or esttab md — their output doesn't render correctly in the Quarto manuscript). Extract coefficients, SEs, and p-values from model objects and construct the table row by row:
| | (1) OLS | (2) FE | ... |* p<0.10, ** p<0.05, *** p<0.01Export the table in three formats to ../tables/:
<label>.md — Markdown (for {{< include >}} in manuscript)<label>.csv — CSV (for data reuse)<label>.tex — LaTeX with booktabs (for standalone use)To embed in index.qmd, use {{< include >}} (NOT {{< embed >}}):
**Table N: Caption text.**
{{< include tables/<label>.md >}}
::: {.table-notes}
*Note:* Dependent variable: ... Standard errors clustered by ... in parentheses.
Significance levels: * p<0.10, ** p<0.05, *** p<0.01. All regressions include a constant (not reported).
:::