AxiomCode
Verifiable intelligence for AI software engineering. Everything starts with a formally grounded code graph.
Excel add-in for forward, backward and stepwise regression. Reports match Excel’s Data Analysis Regression output. Works in Excel for the web, Windows and Mac.
PluginsVBA · PythonGitHub @cranksrustOnlineOwner unconfirmed
Have you tried it? One tap is enough. No sign-in needed.
No updates detected yet. GitHub releases will appear here.
Owners of public repositories under a personal GitHub account can sign in to verify ownership and manage the introduction themselves. No administrator approval is needed.
Sign in, generate a verification file, and commit it to this repository’s default branch within 30 minutes. Files on other branches or forks do not count. Then check the file below to manage the project without administrator approval. Keep the file to retain your access.
If needed, you will go to sign-in. After signing in, return here and press your chosen verification button again.
Run /nomorevibe verify in your project folder to verify ownership and manage the introduction yourself.
Verify in one minuteAsk about other verification options
The maker's introduction consists of the line above. Read the repository README for more details. Repository README ↗
Loading the full README.
Read the full README ↗An Excel add-in that runs forward selection, backward elimination and stepwise regression, then writes a report in the same layout as Excel's Data Analysis > Regression tool (with Standard Error shown as RMSE). Variables enter and leave on |T-Stat| ≥ 2 by default, or on p-values if you prefer.
Install page: https://cranksrust.github.io/stepwise-regression-excel/
The add-in is not in the Office Add-ins store yet, so it is installed from a small file called HOUMBA-28-Stepwise-Regression.xml (Microsoft calls this a manifest: it tells Excel the add-in's name, button and web address). This takes about two minutes and only needs to be done once per browser or computer.
HOUMBA-28-Stepwise-Regression.xml somewhere easy to find, such as Downloads.Excel for the web (recommended, works for everyone)
HOUMBA-28-Stepwise-Regression.xml, and click Upload.Excel for Mac
~/Library/Containers/com.microsoft.Excel/Data/Documents/wef and press Return. If it says the folder does not exist, go to ~/Library/Containers/com.microsoft.Excel/Data/Documents and create a folder named wef.HOUMBA-28-Stepwise-Regression.xml into the wef folder.Excel for Windows (desktop)
Go to Home > Add-ins > More Add-ins > My Add-ins. If Upload My Add-in is shown, follow steps 4 to 6 above. If it is not, use Excel for the web.
Download home-prices.xlsx: 60 fictional home sales with eight candidate predictors. Use Y A1:A61 and X B1:I61 on the Home Prices sheet, then run Forward, Backward and Stepwise and compare the steps.
| Step | Forward | Backward | Stepwise |
|---|---|---|---|
| Start | intercept only | all 8 | intercept only |
| 1 | + TAX_ASSESSED | − GARAGE | + TAX_ASSESSED |
| 2 | + AGE | − BATHROOMS | + AGE |
| 3 | + SQFT | − BEDROOMS | + SQFT |
| 4 | + MILES_DOWNTOWN | − TAX_ASSESSED | + MILES_DOWNTOWN |
| 5 | + SCHOOL_RATING | − TAX_ASSESSED | |
| 6 | + SCHOOL_RATING | ||
| Final R Square | 0.9082 (5 terms) | 0.9070 (4 terms) | 0.9070 (4 terms) |
TAX_ASSESSED looks like the best single predictor, but it only echoes the real drivers. Stepwise drops it once they are in the model (its T-Stat falls to 1.58). Forward selection never re-checks, so it ends with TAX_ASSESSED still in the model at a T-Stat of −0.85.
| Problem | Fix |
|---|---|
| No Add-ins button | The window is too narrow. Check under ⋯ on the Home ribbon or the Insert tab, or widen the window. |
| Upload My Add-in is missing or greyed out | Your school or work account may block custom add-ins. Sign in to office.com with a personal Microsoft account and try again. |
| The button disappeared | In Excel for the web, uploaded add-ins are remembered per browser. Upload the add-in file again. |
| "Every X column must start and end on the same rows as Y" | Select the same rows for Y and X, for example A4:A48 and B4:F48. |
| "The model with every predictor cannot be estimated" | Two X columns carry the same information (for example one is a fixed number minus the other). Remove one, or use Forward or Stepwise. |
More help: https://cranksrust.github.io/stepwise-regression-excel/support.html
Built by the University of Texas at Austin's MBA at Houston Class of '28 for Professor Tom Sager's BA 286T Statistics course, Fall 2026.