Choosing a Cross-Country Fama–French Factor Analysis

Summary

The discussion considers how to study international aircraft and defense stock returns using global size, value, and momentum factors across 30 countries from 1980 to 2016. It does not settle whether a panel model with country effects or a time-series model is appropriate; instead, it says the choice depends on the research question and points to international return-predictability research for guidance on cross-country differences.

One answer distinguishes two possible aims. Reconstructing factors for a custom universe tests for cross-sectional factor effects among the selected firms, and requires care with time zones to avoid using information before it was available. If the aim is to test whether the firms have unusual size, value, or momentum exposure relative to their home markets, the suggested approach is to estimate their factor loadings using country-level factors and average those loadings. The thread offers advice rather than an empirical comparison or a complete specification, so it leaves the modeling choice and implementation details unresolved.

Key ideas

• The appropriate model depends on whether the study targets factor effects within the selected firms or their exposure to local market factors.
• Custom factor construction can examine cross-sectional effects within a chosen universe.
• Time-zone alignment matters when constructing factors to prevent look-ahead bias.
• Averaging firms’ loadings on their countries’ factors can summarize their typical size, value, or momentum bias.
• International return-predictability research may help frame cross-country differences.

Tags

# How to run Fama-French four-factor model cross-country panel analysis?


# How to run Fama-French four-factor model cross-country panel analysis?












I am studying asset-pricing of "aircarft & defence" firms' stocks internationally covering 30 countries over 1980-2016. I can derive SMB, HML, and WML factors from Kenneth French's websites for GLOBAL MARKETS. How to conduct this four-factor analysis? Should I do panel analysis and account country-fixed effects, or just time-series analysis with global factors. Please advice.

## Answer by user22485 (score 2)

https://quant.stackexchange.com/a/40913

I think a useful paper would be Rapach et al. (2013), International Stock Return Predictability what is the role of the united states? They detail cross country differences in a lot of detail and tell you what you need to consider. In terms of time differences etc. It is also an easy to paper to digest and there is a summary on CFA digest.

## Answer by lehalle (score 1)

https://quant.stackexchange.com/a/40447

What you try to do is not clear.

- If you want to reimplement FF factors on a custom universe, you can do it (but paying attention to timezones to not include future information in your data). But be careful: your result will only show you if there is a cross-sectional Factorial effect inside your firms.

- May be you want in reality see if your firms have a specific loading according to FF factors of their countries. I.e. do your aircarft & defence firms have a bias in terms of Size, Value or Momentum? In such a case just take their loadings and average them.

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.