6.2.2.2.1. statsmodels.sandbox.datarich.factormodels.FactorModelUnivariate

class statsmodels.sandbox.datarich.factormodels.FactorModelUnivariate(endog, exog)[source]

Todo: check treatment of const, make it optional ?

add hasconst (0 or 1), needed when selecting nfact+hasconst

options are arguments in calc_factors, should be more public instead cross-validation is slow for large number of observations

__init__(endog, exog)[source]

6.2.2.2.1.1. Methods

__init__(endog, exog)
calc_factors([x, keepdim, addconst]) get factor decomposition of exogenous variables
fit_find_nfact([maxfact, skip_crossval, cv_iter]) estimate the model and selection criteria for up to maxfact factors
fit_fixed_nfact(nfact)
summary_find_nfact() provides a summary for the selection of the number of factors