linearmodels.panel.results.PanelModelComparison

class PanelModelComparison(results, *, precision='tstats', stars=False)

Comparison of multiple models

Parameters:

results{list, dict}

Set of results to compare. If a dict, the keys will be used as model names.

precision{“tstats”,”std_errors”, “std-errors”, “pvalues”}

Estimator precision estimator to include in the comparison output. Default is “tstats”.

starsbool

Add stars based on the p-value of the coefficient where 1, 2 and 3-stars correspond to p-values of 10%, 5% and 1%, respectively.

Attributes:

cov_estimator

Covariance estimator descriptions

estimator_method

Estimation methods

f_statistic

F-statistics and P-values

nobs

Parameters for all models

params

Parameters for all models

pvalues

Parameter p-vals for all models

rsquared

Coefficients of determination (R**2)

rsquared_between

Coefficients of determination (R**2)

rsquared_overall

Coefficients of determination (R**2)

rsquared_within

Coefficients of determination (R**2)

std_errors

Parameter standard errors for all models

summary

Model estimation summary.

tstats

Parameter t-stats for all models

Methods

Properties

cov_estimator	Covariance estimator descriptions
estimator_method	Estimation methods
f_statistic	F-statistics and P-values
nobs	Parameters for all models
params	Parameters for all models
pvalues	Parameter p-vals for all models
rsquared	Coefficients of determination (R**2)
rsquared_between	Coefficients of determination (R**2)
rsquared_overall	Coefficients of determination (R**2)
rsquared_within	Coefficients of determination (R**2)
std_errors	Parameter standard errors for all models
summary	Model estimation summary.
tstats	Parameter t-stats for all models