Bootstrap inference for fixed-effect models

• Tác giả: Ayden Higgins, Koen Jochmans
• Ngôn ngữ: eng
• Ký hiệu phân loại: 511.34 Model theory
• Thông tin xuất bản: 2022
• Bộ sưu tập: Metadata
• ID: 168664

Tóm tắt

The maximum-likelihood estimator of nonlinear panel data models with fixed effects is consistent but asymptotically-biased under rectangular-array asymptotics. The literature has thus far concentrated its effort on devising methods to correct the maximum-likelihood estimator for its bias as a means to salvage standard inferential procedures. Instead, we show that the parametric bootstrap replicates the distribution of the (uncorrected) maximum-likelihood estimator in large samples. This justifies the use of confidence sets constructed via standard bootstrap percentile methods. No adjustment for the presence of bias needs to be made.