Package index

Estimation

FGLS estimators and their options.

fgls()

Feasible GLS for serial correlation and/or heteroskedasticity

serial_fgls()

Feasible GLS for serially correlated errors (Perron and González-Coya, 2026)

lasso_fgls()

Feasible GLS under heteroskedasticity of unknown form (González-Coya and Perron, 2024)

fgls_control()

Advanced options for fgls

Working with fits

summary(<fgls>) print(<summary.fgls>)

Summarize an fgls fit

vcov(<fgls>) confint(<fgls>) residuals(<fgls>) fitted(<fgls>) predict(<fgls>) nobs(<fgls>) df.residual(<fgls>) formula(<fgls>) model.matrix(<fgls>) model.frame(<fgls>) terms(<fgls>) print(<fgls>)

Methods for fgls fits

plot(<fgls>)

Diagnostic plots for fgls fits

compare_fgls()

Compare fits side by side

tidy(<fgls>) glance(<fgls>) augment(<fgls>)

Tidy, glance and augment fgls fits

Benchmarks

OLS with HAC/HC standard errors, Cochrane-Orcutt, Durbin, infeasible and hybrid GLS.

ols_robust() cochrane_orcutt() durbin_estimator() infeasible_gls() hybrid_gls()

Benchmark estimators

Diagnostics

test_predetermined() print(<fgls_predetermined>)

Test whether lags of the regressors are missing (pre-determinedness)

adf_test() print(<fgls_adf>)

Augmented Dickey-Fuller test (screening)

weight_diagnostics() ar_roots() nonexogeneity_share()

Diagnostics of an fgls fit

Candidate covariates

make_dictionary()

Candidate covariates for the skedastic function

Simulation designs of the papers

simulate_serial() simulate_hetero() simulate_combined() simulate_predictive()

Simulate the designs of the papers

Package and conditions

fgls-package

fgls: Feasible GLS for serial correlation and heteroskedasticity

fgls-conditions

Conditions signaled by fgls