Abstract
Podsakoff and Todor (1985) proposed partialling the first principal component from observed correlations as a procedure for controlling method variance. Using mathematical derivations and Monte Carlo simulation, we found that this procedure is biased. Partialling out the first principal component introduces a negative bias into the resulting correlations that seriously compromises subsequent analysis. Moreover, the extent of bias is not reduced by increasing sample size; however, it is inversely proportional to the number of variables. Therefore, partialling the first principal component is not recommended. Researchers are encouraged to collect data with multiple methods whenever feasible.
Keywords
Principal component analysisVariance (accounting)Monte Carlo methodStatisticsFactor analysisComponent (thermodynamics)EconometricsVariance componentsSample (material)MathematicsChemistryChromatographyEconomics
Affiliated Institutions
Related Publications
Common Method Bias in PLS-SEM
The author discusses common method bias in the context of structural equation modeling employing the partial least squares method (PLS-SEM). Two datasets were created through a ...
The Effects of Overextraction on Factor and Component Analysis
The effects of overextracting factors and components within and between the methods of maximum likelihood factor analysis (MLFA) and principal component analysis (PCA) were exam...
An Introduction to Multivariate Statistical Analysis
Preface to the Third Edition.Preface to the Second Edition.Preface to the First Edition.1. Introduction.2. The Multivariate Normal Distribution.3. Estimation of the Mean Vector ...
Comments on the NIPALS algorithm
Abstract The Non‐linear Iterative Partial Least Squares (NIPALS) algorithm is used in principal component analysis to decompose a data matrix into score vectors and eigenvectors...
Estimation and Tests of Significance in Factor Analysis
A distinction is drawn between the method of principal components developed by Hotelling and the common factor analysis discussed in psychological literature both from the point...
Publication Info
- Year
- 1986
- Type
- article
- Volume
- 12
- Issue
- 4
- Pages
- 525-530
- Citations
- 99
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
99
OpenAlex
Cite This
Edward R. Kemery,
William P. Dunlap
(1986).
Partialling Factor Scores Does Not Control Method Variance: A Reply to Podsakoff and Todor.
Journal of Management
, 12
(4)
, 525-530.
https://doi.org/10.1177/014920638601200407
Identifiers
- DOI
- 10.1177/014920638601200407