Why Fama–MacBeth R-Squared Can Differ from Panel R-Squared
Summary
The document raises a methodological issue when comparing the goodness of fit of Fama–MacBeth regressions with that of a pooled panel regression. The author argues that the procedures do not estimate one shared regression: Fama–MacBeth runs separate cross-sectional regressions over time and averages their results. Consequently, familiar R-squared calculations based on residuals or fitted values may not coincide with the panel regression’s R-squared, even when estimates look very close in a particular full-sample comparison.
The author reports numerical experiments in which rolling-window results differed more substantially, including R-squared values outside the usual zero-to-one range under some calculation choices. These observations motivate a question about whether discrepancies shrink as data frequency rises and whether competing explanations are contradictory. The document provides no accepted answer or derivation resolving the issue, so its claims should be treated as a research question rather than a settled result. It is useful as a reminder to define the R-squared calculation precisely and avoid assuming that fit statistics from distinct estimators are directly comparable.
Key ideas
- Fama–MacBeth estimation averages separate cross-sectional regressions rather than fitting one pooled panel regression.
- R-squared measures based on residuals or fitted values may differ across these procedures.
- The author reports larger discrepancies in rolling-window calculations than in a full-sample comparison.
- The document raises, but does not resolve, whether differences diminish as data frequency increases.
- Comparisons should state the precise R-squared definition and estimation procedure.
Tags
Full text
# Are Fama-Macbeth R-Squared (R2) just assymptotically correct? # Are Fama-Macbeth R-Squared (R2) just assymptotically correct? I have been doing a research on comparing Fama-MacBeth and panel regression procedures. Think of it as an emerging market case for Petersen (2009) link. My research consists of a route based on full-sample betas of Fama-French (for 90 months) and another based on 30 rolling 60-month windows. I have used this page for finding the R^2 in both routes. I have noticed that the R^2 from the two procedures are very close in the full-sample case (up to 13 decimals!). But the story is very different for the rolling case (discussed below) and this has made me think of adding this to that page I referred above: The problem with FM R^2 is that since it is not the original regression procedure, using each of formulae of R^2 (using residuals or fitted values) would not give you the same result. Of course, as the frequency of the data increase, they will converge significantly but algebraically they will never be the same, simply because you are not feeding the whole data set to a unique regression (i.e a panel regression) and are just running separate regressions and averaging their results. I have checked this numerically for different scenarios. Just try it for as many as 5*5 portfolios and 30 periods (with periodically changing FF betas). You might even see a negative R^2 from one and a more-than-1 R^2 from the other! > The problem with FM R^2 is that since it is not the original regression procedure, using each of formulae of R^2 (using residuals or fitted values) would not give you the same result. Of course, as the frequency of the data increase, they will converge significantly but algebraically they will never be the same, simply because you are not feeding the whole data set to a unique regression (i.e a panel regression) and are just running separate regressions and averaging their results. I have checked this numerically for different scenarios. Just try it for as many as 5*5 portfolios and 30 periods (with periodically changing FF betas). You might even see a negative R^2 from one and a more-than-1 R^2 from the other! Do you agree with my comment? I guess this would further enrich the fruitful discussion done there. Also, the more important issue is that the answers on the page referred above and this page are contradictory. In my opinion, the former is correct. What do you think? Obviously, it can’t be both.
Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.