[bashtage]

GMMFactorModelResults.std_errors stacked the standard errors of the alphas on top of the standard errors of the loadings, and reshaped the vector to one row for each portfolio. Row i of the table then held the alphas of portfolios i(k+1) to i(k+1)+k instead of the alpha and the loadings of portfolio i, where k is the number of factors. The cells of the table were wrong for every model with more than one portfolio, and so were tstats, pvalues and the loadings in full_summary, which are computed from std_errors.

For a model with 6 portfolios and 2 factors, the loading of the first portfolio on the first factor, 0.7037, had a standard error of 0.00143, which is the standard error of the alpha of the second portfolio, where the standard error in cov is 0.0270. Its t-statistic was 491 instead of 26. The alphas and the standard errors of the risk premia were not affected, and neither were the other result classes.

The standard errors of the alphas are now the first column and the standard errors of the loadings of each portfolio follow in the other columns, as they do for LinearFactorModel and TradedFactorModel.

The test compares the table with the standard errors in cov, found from the names of the parameters, and with the standard errors of the alphas. It fails without the change for one and for three factors, with and without a risk-free rate.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 99.59%. Comparing base (6cbd30b) to head (5a72869).
⚠️ Report is 34 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #781      +/-   ##
==========================================
+ Coverage   99.58%   99.59%   +0.01%     
==========================================
  Files         128      128              
  Lines       24188    24452     +264     
  Branches     1809     1822      +13     
==========================================
+ Hits        24087    24353     +266     
+ Misses         40       39       -1     
+ Partials       61       60       -1     

Flag	Coverage Δ
adder	99.57% <100.00%> (+0.01%)	⬆️
subtractor	99.57% <100.00%> (+0.01%)	⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.