Hi Guys,
First of all - this is my first post so I'd like to take this opportunity to thank you for everything I've learned from you so far.
I've got a question in the scope of statistical analysis of stocks and indices.
How would you interpret having low R-squared values for most of the companies in a given sector combined with having betas below 1? I know this is mostly theoretical, I'm just looking for any possible explanations.
Thanks, Paul
| +139 | UBS Catastrophic Q1-Q3 26, M&A -17%, Outside Top 10 in Americas, EMEA & APAC | 42 | 22m |
| +64 | PWP acquisition by Piper cancelled | 23 | 22h |
| +44 | No return offer - UPDATE. | 12 | 20h |
| +31 | Evercore poaches Baird DC Defense Team | 24 | 9h |
| +24 | Is my MD a grifter? 16 years, 8 firms | 13 | 7h |
| +22 | Best Houston Banks for Culture in 2026 | 17 | 4h |
| +21 | Lack of talent in IB! | 19 | 1d |
| +18 | Article: UBS Wall Street Rebuild Is a Study in Management Failure | 4 | 16h |
| +17 | Internal lateral from coverage to M&A (focused on coverage) | 4 | 1d |
| +16 | How standard is weekend work in IBD? | 13 | 53m |
Career Resources
Get instant access to lessons taught by experienced private equity pros and bulge bracket investment bankers including financial statement modeling, DCF, M&A, LBO, Comps and Excel Modeling.
Low R-squared means that the model is not good at explaining the stock's returns. More generally, it likely means that the stocks you are looking at are highly impacted by unsystematic risk.
Assuming you are using a standard OLS regression, R-squared is the explained sum of square differences over total sum of square differences:
R^2=ESS/TSS
Like unfriend said, this means that your explanatory variables are not controlling for much of the variance in the stock. I don't think this really has any bearing whatsoever on what the coefficient on beta is; you should be looking at the standard error on beta and considering the corresponding p-value. If this shows your coefficient to be significant then a low beta obviously means that the stock has a lower systematic risk. Importantly, this says nothing about idiosyncratic risk - this could also be low.
Both above posters are correct
All right, I think I've got this - I run some p-value calculations and betas turned out to be statistically significant throughout the whole sample.
Thanks for your quick responses guys!
R squared is correlation, low R squared means its not correlated. Number is typically in a decimal that you can convert into a percentage. There are excel functions ( I think CORREL) for these.
Et quaerat illum earum quasi. Veniam adipisci quae voluptas. Ut quibusdam dicta dolor nostrum.
Ipsum saepe possimus vel distinctio. Minus est saepe dolorem quia. Suscipit id est placeat incidunt minima neque. Provident nisi aut et delectus. Voluptate facilis natus incidunt qui incidunt iure molestias aut.
Est molestiae maxime est ipsa. Alias quo corporis consequatur est velit. Culpa blanditiis reiciendis quia voluptatem laboriosam. Magni distinctio dolor quis incidunt. Odio aliquid voluptatem eos non.
See All Comments - 100% Free
WSO depends on everyone being able to pitch in when they know something. Unlock with your email and get bonus: 6 financial modeling lessons free ($199 value)
or Unlock with your social account...