Abstract
In this article we deal with the problem of stability of the conclusions from principal components analysis over repeated samples. We define a measure of stability for each component and investigate some of the measures properties. We then obtain the maximum likelihood estimators (MLEs) of the measures, and derive their joint limiting distributions. The MLEs of the measures turn out to be asymptotically unbiased and jointly have the multivariate normal distribution. Modified estimators are also found to reduce the amount of bias in the MLEs. To facilitate interpretation of the measures we define stability confidence level as coverage probability, and associate with each measure a stability confidence level to describe the measure in terms of probability. Finally, we investigate the stability of the components via a simulation study and compare the performance of the MLEs and the modified estimators in terms of bias and precision.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Al-Kandari NM, Jolliffe IT (2001) Variable selection and interpretation of covariance principal components. Commun Stat Simul Comput 30(2):339–354
Anderson GA (1965) An asymptotic expansion for the distribution of the latent roots of the estimated covariance matrix. Ann Math Stat 36:1153–1173
Daudin JJ, Duby C, Trecourt P (1988) Stability of principal component analysis studied by the Bootstrap method. Statistics 19:241–258
Daudin JJ, Duby C, Trecourt P (1989) PCA stability studied by the Bootstrap and the infinitesmal Jackknife method. Statistics 20:255–270
Dudzinski ML, Norris JM, Chmura JT, Edwards CBH (1975) Repeatability of principal components in samples: normal and non-normal data sets compared. J Multivariate Behav Res 10:109–113
Green BF (1977) Parameter sensitivity in multivariate methods. J Multivariate Behav Res 12:263–287
Hand DJ, Daly F, Lunn AD, McConway KJ, Ostrowski E (eds) (1994) A Handbook of small data sets. Chapman & Hall, London, p 303
Jackson EJ (1991) A user’s guide to principal components. Wiley, New York
Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, Heidelberg
Krzanowski WJ (1984) Sensitivity of principal components. J R Stat Soc Ser B 46(3):558–563
Manly BFJ (1986) Multivariate statistical methods: a primer. Chapman & Hall, New York, p 11
Mardia KV, Kent JT, Bibby JM (1979) Multivariate analysis. Academic, New York
Morrison DF (1990) Multivariate statistical methods, 3rd edn. McGraw-Hill, New York
Sinha AR, Buchanan BS (1995) Assessing the stability of principal components using regression. Psychometrika 60(3):355–369
Tanaka Y (1988) Sensitivity analysis in principal component analysis: influence on the subspace spanned by principal components. Commun Stat Theory Methods 17(9):3157–3175
Author information
Authors and Affiliations
Corresponding author
Additional information
This work was sponsored by a grant from the Office of Vice-President for Research at Kuwait University under project number SS049.
Rights and permissions
About this article
Cite this article
Al-Ibrahim, A.H., Al-Kandari, N.M. Stability of principal components. Computational Statistics 23, 153–171 (2008). https://doi.org/10.1007/s00180-007-0082-8
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-007-0082-8