Glance at an estimatr object
# S3 method for lm_robust
glance(x, ...)# S3 method for lh_robust
glance(x, ...)
# S3 method for iv_robust
glance(x, ...)
# S3 method for difference_in_means
glance(x, ...)
# S3 method for horvitz_thompson
glance(x, ...)
For glance.lm_robust, a data.frame with columns:
the \(R^2\), $$R^2 = 1 - Sum(e[i]^2) / Sum((y[i] - y^*)^2),$$ where \(y^*\) is the mean of \(y[i]\) if there is an intercept and zero otherwise, and \(e[i]\) is the ith residual.
the \(R^2\) but penalized for having more parameters, rank
the standard error type specified by the user
the value of the F-statistic
p-value from the F test
residual degrees of freedom
the number of observations used
For glance.lh_robust, we glance the lm_robust component only. You can access the linear hypotheses as a data.frame directy from the lh component of the lh_robust object
For glance.iv_robust, a data.frame with columns:
The \(R^2\) of the second stage regression
The \(R^2\) but penalized for having more parameters, rank
residual degrees of freedom
the number of observations used
the standard error type specified by the user
the value of the F-statistic
p-value from the F test
the value of the first stage F-statistic, useful for the weak instruments test; only reported if there is only one endogenous variable
p-value from the first-stage F test, a test of weak instruments; only reported if there is only one endogenous variable
the value of the F-statistic for the test of endogeneity; often called the Wu-Hausman statistic, with robust standard errors, we employ the regression based test
p-value from the F-test for endogeneity
the value of the chi-squared statistic for the test of instrument correlation with the error term; only reported with overidentification
p-value from the chi-squared test; only reported with overidentification
For glance.difference_in_means, a data.frame with columns:
the design used, and therefore the estimator used
the degrees of freedom
the number of observations used
the number of blocks, if used
the number of clusters, if used
the second, "treatment", condition
the first, "control", condition
For glance.horvitz_thompson, a data.frame with columns:
the number of observations used
the type of standard error estimator used
the second, "treatment", condition
the first, "control", condition
An object returned by one of the estimators
extra arguments (not used)
generics::glance(), lm_robust(), lm_lin(), iv_robust(), difference_in_means(), horvitz_thompson()