Dsfsadfsdf

Lectura econometría aplicada
Nombre alumno: Álvaro Cartagena Farías
1. Título: Methodological Issues in Cross-Section and Panel Estimates f the Human Resource-Firm Perfomance Link
Autor: Mark A. Huselid and Brian E. Becker
Revista: Industrial Relations

2. Resumen:

3. Objetivos del artículo:

4. Breve descripción del artículo:

5. Principales resultados:

6.Valoración del artículo:

Methodological Issues in Cross-Sectional and Panel Estimates of the Human Resource-Firm Performance Link
Because companies differ in factors such as management ability that may
lead to both high performance work systems and enhanced firm perfor-
mance, conventionalestimates of the effects of human resource (HR)
management practices on firm performance may be biased upward. Al-
ternatively, if HR management practices are measured with error, esti-
mates of their effects on firm performance may be biased downward. We
find that although longitudinal estimates that avoid the first sourceof
bias are substantially smaller than cross-sectional estimates, the former
are strongly influenced by errors in measuring HR management prac-
tices. Based on independent estimates of the measurement error, we
calculate a range of estimates that correct for both biases. We estimate
that a one standard deviation increasein our measure of high perfor-
mance work systems raises the market value of the corporation by ap-
proximately $15,000 per employee.

T HIS STUDY INVESTIGATES SEVERAL METHODOLOGICAL CHAL-

LENGES inherent in survey-based analyses of the impact of highperformance

* The authors' affiliations are, respectively, School of Management and Labor Relations, Rutgers
University, and School of Management, State University of New York at Buffalo. This study was par-
tially funded by the Human Resource Planning Society, the Society for Human Resource Management
(SHRM) Foundation, the School of Management and Labor Relations (SMLR) at RutgersUniversity.
and the SUNY-Buffalo School of Management. The interpretations, conclusions, and recommenda-
tions, however, are ours and do not necessarily represent the positions of these organizations.
We are grateful to Randall Schuler and seminar participants at MIT for their helpful comments on an
earlier version of this article.

INDUSTRIAL RELATIONS , Vol, 35, No. 3 (July1996). © 1996 Regents of the University of California
Published by Blackwell Publishers, 238 Main Street, Cambridge. MA 02142, USA, and 108 Cowley
Road, Oxford, OX4 1JF, UK.

400
Methodological Issues in Cross-Sectional and Panel Estimates / 401

work systemson firm performance.1 Drawing on a national panel survey
of organizational human resource (HR) management systems, we com-
pare the estimated relationship between HR strategy and firm perfor-
mance in both cross-sectional and longitudinal data sets. Prior research
relying on multifirm data sets has typically relied on cross-sectional esti-
mates that are potentially subject toproblems of unobserved firm-level
characteristics, such as the quality of marketing or manufacturing strate-
gies, that might bias the estimated HR strategy-firm performance relation-
ship. Although panel data can mitigate such heterogeneity bias, such data
are even more sensitive to the attenuating effects of error in the measure-
ment of HR management practices. Thus, the...