3.4.6. statsmodels.emplike.originregress

This module implements empirical likelihood regression that is forced through the origin.

This is different than regression not forced through the origin because the maximum empirical likelihood estimate is calculated with a vector of ones in the exogenous matrix but restricts the intercept parameter to be 0. This results in significantly more narrow confidence intervals and different parameter estimates.

For notes on regression not forced through the origin, see empirical likelihood methods in the OLSResults class.

3.4.6.1. General References

Owen, A.B. (2001). Empirical Likelihood. Chapman and Hall. p. 82.

3.4.6.2. Functions

add_constant(data[, prepend, has_constant])

This appends a column of ones to an array if prepend==False.

3.4.6.3. Classes

ELOriginRegress(endog, exog)	Empirical Likelihood inference and estimation for linear regression
OLS(endog[, exog, missing, hasconst])	A simple ordinary least squares model.
OriginResults(model, params, est_llr, llf_el)	A Results class for empirical likelihood regression through the origin
RegressionResults(model, params[, ...])	This class summarizes the fit of a linear regression model.