Joint conditional MLE beta-AR(k) regression (betark) yields better-calibrated ITSA inference for bounded outcomes than quasi-binomial GLM with Newey–West HAC SEs, though Type I error stays high under AR(3) high persistence.
Multiple-group (controlled) interrupted time series analysis with higher-order au- toregressive errors: A simulation study comparing Newey–West and Prais–Winsten methods
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Beta Regression with Autoregressive Errors for Interrupted Time Series Analysis of Proportion and Rate Outcomes: A Simulation Study
Joint conditional MLE beta-AR(k) regression (betark) yields better-calibrated ITSA inference for bounded outcomes than quasi-binomial GLM with Newey–West HAC SEs, though Type I error stays high under AR(3) high persistence.