<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk" -->

---
title: olsrr 0.7.1 | daily.dev
description: olsrr 0.7.1 is on CRAN and fixes three calculations that change numbers already in published reports. Holm-adjusted Breusch-Pagan p-values, the Cramér–von...
canonical: https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: olsrr 0.7.1 | daily.dev
og:description: olsrr 0.7.1 is on CRAN and fixes three calculations that change numbers already in published reports. Holm-adjusted Breusch-Pagan p-values, the Cramér–von...
og:url: https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk
og:image: https://api.daily.dev/og/posts/RN5jJyihk.png
og:image:alt: olsrr 0.7.1
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# olsrr 0.7.1

**[R-bloggers](https://daily.dev/sources/rbloggers)** · 12 min read · 0 upvotes · 0 comments

## Summary

olsrr 0.7.1 is on CRAN and fixes three calculations that change numbers already in published reports. Holm-adjusted Breusch-Pagan p-values, the Cramér–von Mises normality test, and residual MSE/RMSE in model summaries all changed to match base R and reference packages car, lmtest and nortest. In one example, MSE moved from 5.8011 to 6.8754 after fixing a wrong divisor. The release also adds include/exclude arguments to stepwise selection, a ten-panel diagnostics grid, model comparison via ols_compare_model_performance(), and weighted regression support in ols_regress(). Two known issues, an uncorrected Kolmogorov-Smirnov test and a duplicate plot title, remain open for 0.7.2.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.r-bloggers.com/2026/11/olsrr-0-7-1>

## Questions this post answers

### Why did my MSE and RMSE values change after updating olsrr to 0.7.1?

olsrr versions before 0.7.1 divided the residual sum of squares by the sample size n instead of the residual degrees of freedom, producing an incorrect, smaller MSE. For lm(mpg ~ disp + hp + wt + qsec, data = mtcars) with 27 residual degrees of freedom, 0.7.0 gave MSE = 5.8011 and RMSE = 2.4085, while 0.7.1 correctly reports MSE = 6.8754 and RMSE = 2.6221, matching the ANOVA residual mean square and summary(model)$sigma.

_Anyone re-running regression reports after a package update can track fixes like this olsrr MSE correction on daily.dev._

### Is the Cramér-von Mises normality test in olsrr reliable?

Not in versions before 0.7.1. Earlier releases compared the Cramér-von Mises statistic against a standard uniform distribution instead of a normal distribution fitted to the residuals' mean and standard deviation, causing it to reject normality for almost any regression. Version 0.7.1 calls nortest::cvm.test() directly, so results now agree with that reference package and align with Shapiro-Wilk and Anderson-Darling results on the same residuals.

_Developers validating statistical package upgrades can follow fixes like olsrr's normality test correction on daily.dev._

### How do I keep specific predictors in the model during stepwise variable selection in R with olsrr?

Use the include argument, added between olsrr 0.6.0 and 0.7.1, with functions like ols_step_both_aic(), passing predictor names or column indices to lock them in throughout the selection process. An exclude argument is also available. On the surgical dataset, locking age and alc_heavy keeps both in the base model and every subsequent step even though age ends up statistically insignificant in the final fit.

_Anyone building stepwise selection workflows with locked confounders can track olsrr feature updates on daily.dev._

## Similar posts on daily.dev

- [Major Update for revss Package for R – v3.1.0](https://daily.dev/posts/major-update-for-revss-package-for-r-v3-1-0-krvjaaili) · R-bloggers · 0 upvotes · 0 comments
- [The Oracle Files](https://daily.dev/posts/the-oracle-files-lau0gkgn1) · Medium · 0 upvotes · 0 comments
- [Spurious correlations 0.2 is on CRAN\!](https://daily.dev/posts/spurious-correlations-0-2-is-on-cran--vertfhcft) · R-bloggers · 0 upvotes · 0 comments
- [How to Make Linear Regression Survive Outliers](https://daily.dev/posts/how-to-make-linear-regression-survive-outliers-3dbnrrqqd) · Towards Data Science · 0 upvotes · 0 comments
- [smooth v4.4.0](https://daily.dev/posts/smooth-v4-4-0-u3nddmveb) · R-bloggers · 0 upvotes · 0 comments

---

Tags: [#testing](https://daily.dev/tags/testing), [#r](https://daily.dev/tags/r), [#statistics](https://daily.dev/tags/statistics), [#regression-analysis](https://daily.dev/tags/regression-analysis)

[View this post on daily.dev](https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"olsrr 0.7.1","url":"https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk"},"datePublished":"2026-11-19T09:05:07.643Z","dateModified":"2026-11-19T09:05:39.910Z","description":"olsrr 0.7.1 is on CRAN and fixes three calculations that change numbers already in published reports. Holm-adjusted Breusch-Pagan p-values, the Cramér–von...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0e5fa67f82168b6f5dcf2020399ad748?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0e5fa67f82168b6f5dcf2020399ad748?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"R-bloggers","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"R-bloggers","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/98bcbbdf72774292a55ceda8f2277f1e","url":"https://daily.dev/sources/rbloggers"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"testing,r,statistics,regression-analysis","timeRequired":"PT12M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"R-bloggers","item":"https://daily.dev/sources/rbloggers"},{"@type":"ListItem","position":3,"name":"olsrr 0.7.1"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/olsrr-0-7-1-rn5jjyihk#faq","mainEntity":[{"@type":"Question","name":"Why did my MSE and RMSE values change after updating olsrr to 0.7.1?","acceptedAnswer":{"@type":"Answer","text":"olsrr versions before 0.7.1 divided the residual sum of squares by the sample size n instead of the residual degrees of freedom, producing an incorrect, smaller MSE. For lm(mpg ~ disp + hp + wt + qsec, data = mtcars) with 27 residual degrees of freedom, 0.7.0 gave MSE = 5.8011 and RMSE = 2.4085, while 0.7.1 correctly reports MSE = 6.8754 and RMSE = 2.6221, matching the ANOVA residual mean square and summary(model)$sigma. Anyone re-running regression reports after a package update can track fixes like this olsrr MSE correction on daily.dev."}},{"@type":"Question","name":"Is the Cramér-von Mises normality test in olsrr reliable?","acceptedAnswer":{"@type":"Answer","text":"Not in versions before 0.7.1. Earlier releases compared the Cramér-von Mises statistic against a standard uniform distribution instead of a normal distribution fitted to the residuals' mean and standard deviation, causing it to reject normality for almost any regression. Version 0.7.1 calls nortest::cvm.test() directly, so results now agree with that reference package and align with Shapiro-Wilk and Anderson-Darling results on the same residuals. Developers validating statistical package upgrades can follow fixes like olsrr's normality test correction on daily.dev."}},{"@type":"Question","name":"How do I keep specific predictors in the model during stepwise variable selection in R with olsrr?","acceptedAnswer":{"@type":"Answer","text":"Use the include argument, added between olsrr 0.6.0 and 0.7.1, with functions like ols_step_both_aic(), passing predictor names or column indices to lock them in throughout the selection process. An exclude argument is also available. On the surgical dataset, locking age and alc_heavy keeps both in the base model and every subsequent step even though age ends up statistically insignificant in the final fit. Anyone building stepwise selection workflows with locked confounders can track olsrr feature updates on daily.dev."}}]}
```

