Multicollinearity: How common factors cause Type 1 errors in multivariate regression
Abstract
Research Summary : In multivariate regression analyses of correlated variables, we sometimes observe pairs of estimated beta coefficients large in absolute magnitude and opposite in sign. T ‐statistics are also large, suggesting meaningful findings. I found 64 recently published Strategic Management Journal articles with results exhibiting these characteristics. In this article, I demonstrate that such results may be Type 1 errors (false positives): If regressors are correlated via an unobservable common factor, estimated beta coefficients will misleadingly tend toward infinite magnitudes in opposite directions, even if the variables’ real effects are small and of the same sign. Diagnostics such as Variance Inflation Factors (VIF) will misleadingly validate Type 1 errors as legitimate results. After establishing general results via mathematical analysis and simulation, I provide guidelines for detection and mitigation. Managerial Summary : This article demonstrates mathematically how regression analyses with correlated independent variables may generate beta coefficients of opposite sign to the variables’ true effects. To assess the likelihood of this possibility, I propose that: if (a) absolute correlation of two independent variables is about ±0.3 or more (smaller correlations may be problematic for large data sets), (b) the two variables have beta coefficients of opposite sign, if correlated positively, and of the same sign, if correlated negatively, and (c) the bivariate correlation of one independent variable with the dependent variable is of the opposite sign from the beta coefficient, then the beta might be a false positive. To facilitate such analysis, authors should provide complete correlation tables, including dependent variables, interaction terms, and quadratic terms.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The study addresses potential concerns regarding multicollinearity by following the three-step procedure by Kalnins (2018).
“By following the three-step procedure by Kalnins (2018), we address potential concerns regarding multicollinearity.”
From What role do data network effects play for multihoming complements? An empirical analysis of platform complementors’ strategies for consumer value creation (2025) · cites this paper as Kalnins (2018)
Cites
Ridge regression: Biased estimation for nonorthogonal problems
Hoerl, A. E., & Kennard, R. W. (1970) · Technometrics · doi:10.1080/00401706.1970.10488634 · Cited by 9,648 · see citing works
Regression Diagnostics: Identifying Influential Data and Sources of Collinearity
Belsley, D. A., Kuh, E., & Welsch, R. E. (1980) · Wiley Series in Probability and Statistics · doi:10.1002/0471725153 · Cited by 7,297 · see citing works
Stock, J. H., & Watson, M. W. (2002) · Cited by 1,773 · see citing works
NOTES ON THE HISTORY OF CORRELATION
Pearson, K. (1920) · Biometrika · doi:10.1093/biomet/13.1.25 · Cited by 856 · see citing works
Pfarrer, M. D., Pollock, T. G., & Rindova, V. (2010) · Academy of Management Journal · doi:10.5465/amj.2010.54533222 · Cited by 842 · see citing works
The problem of unobservables in strategic management research
Godfrey, P. C., & Hill, C. W. L. (1995) · Strategic Management Journal · doi:10.1002/smj.4250160703 · Cited by 645 · see citing works
Introduction to the Theory and Practice of Econometrics.
Trader, R. L., Judge, G. G., Hill, R. C., Griffiths, W. E., Lütkepohl, H., & Lee, T.-C. (1983) · Journal of the American Statistical Association · doi:10.2307/2288235 · Cited by 499 · see citing works
Mean-Centering Does Not Alleviate Collinearity Problems in Moderated Multiple Regression Models
Echambadi, R., & Hess, J. D. (2007) · Marketing Science · doi:10.1287/mksc.1060.0263 · Cited by 469 · see citing works
A Study of Effects of MultiCollinearity in the Multivariable Analysis.
Yoo, W., Mayberry, R. M., Bae, S., et al. (2014) · PubMed · Cited by 465 · see citing works
Construct measurement in strategic management research: illusion or reality?
Boyd, B., Gove, S., & Hitt, M. A. (2004) · Strategic Management Journal · doi:10.1002/smj.444 · Cited by 345 · see citing works
Statistical Confluence Analysis by means of Complete Regression Systems.
Allen, R. G. D., & Frisch, R. (1935) · The Economic Journal · doi:10.2307/2225583 · Cited by 316 · see citing works
How Customer Portfolio Affects New Product Development in Technology-Based Entrepreneurial Firms
Yli‐Renko, H., & Janakiraman, R. (2008) · Journal of Marketing · doi:10.1509/jmkg.72.5.131 · Cited by 187 · see citing works
Scientific apophenia in strategic management research: Significance tests & mistaken inference
Goldfarb, B. D., & King, A. A. (2015) · Strategic Management Journal · doi:10.1002/smj.2459 · Cited by 138 · see citing works
Correlated measurement error--implications for nutritional epidemiology
Day, N. (2004) · International Journal of Epidemiology · doi:10.1093/ije/dyh138 · Cited by 94 · see citing works
Interviewed by Nicholas M. Kiefer
Goldberger, A. S. (1989) · Econometric Theory · doi:10.1017/s0266466600012299 · Cited by 16 · see citing works
Invariance of results under a common orthogonalization
Mitchell, D. W. (1991) · Journal of Economics and Business · doi:10.1016/0148-6195(91)90018-r · Cited by 14 · see citing works
Some Limits in the Theory of Multicollinearity
Sastry, M. V. R. (1970) · The American Statistician · doi:10.2307/2682295 · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Knorr, C., Erath, M., Saesen, J., Kindermann, B., & Strese, S. (2025) · Electronic Markets · doi:10.1007/s12525-025-00817-4
“By following the three-step procedure by Kalnins (2018), we address potential concerns regarding multicollinearity.”
- Authors
- Kalnins, A.
- Affiliations
- University of Iowa (US)
- Corresponding author
- Kalnins, Arturs
- ORCID
- Kalnins, Arturs
- Venue
- Strategic Management Journal
- Publisher
- Wiley
- Published
- 2018-05-07
- Volume
- 39
- Issue
- 8
- Pages
- 2362-2385
- ISSN
- 0143-2095 (ISSN-L)
- 1097-0266
- OpenAlex
- W2791962711
- Cited by
- 526
- References
- 17
- Citations by year
- 2026: 83 · 2025: 112 · 2024: 106 · 2023: 67 · 2022: 60 · 2021: 45 · 2020: 28 · 2019: 17 · 2018: 6 · 2017: 2
- FWCI
- 19.92
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Strategic Management Journal (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Statistical Methods and Models
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Spatial and Panel Data Analysis
- Keywords
- multicollinearity, type I error, false positives, common factors, variance inflation factor, multivariate regression, correlation tables, regression diagnostics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
