Arbeitspapier

Feasible estimation of linear models with N-fixed effects

In this paper an alternative approach for the estimation of higher-order linear fixed-effects models is described. The strategy relies on the transformation of the data prior to calculating estimations of the model. While the approach is computationally intensive, the hardware requirements for the estimation process are minimal, allowing for the estimation of models with more than two high-order fixed effects for large datasets. An illustration of the implementation is presented using the US Census Bureau Current Population Survey data with four fixed effects.

Language
Englisch

Bibliographic citation
Series: Working Paper ; No. 782

Classification
Wirtschaft
Estimation: General
Single Equation Models; Single Variables: Panel Data Models; Spatio-temporal Models
Subject
Fixed-Effects Models
Two-Step Estimation
Stata

Event
Geistige Schöpfung
(who)
Rios-Avila, Fernando
Event
Veröffentlichung
(who)
Levy Economics Institute of Bard College
(where)
Annandale-on-Hudson, NY
(when)
2013

Handle
Last update
10.03.2025, 11:42 AM CET

Data provider

This object is provided by:
ZBW - Deutsche Zentralbibliothek für Wirtschaftswissenschaften - Leibniz-Informationszentrum Wirtschaft. If you have any questions about the object, please contact the data provider.

Object type

  • Arbeitspapier

Associated

  • Rios-Avila, Fernando
  • Levy Economics Institute of Bard College

Time of origin

  • 2013

Other Objects (12)