A cautionary note concerning a commonly applied eigenanalysis procedure

Article English OPEN
Richman, Michael B. (2011)

Owing to the complex nature of eigenanalysis programming algorithms, most atmospheric science research utilizing empirical orthogonal functions (EOFs), principal component analysis (PCA), or common-factor analysis (CFA) use the “canned” computer programs on statistical packages such as EISPACK, IMSL, SAS, BMDP, etc. These programs usually encourage truncation of the eigenvector series according to some criterion to exclude noise and facilitate data reduction; the EOFs/PCs/CFs retained are then often physically interpreted (with or without further linear transformations) according to which variables have salient magnitudes. Results presented here illustrate that following this type of analysis procedure can lead to the interpretation of coefficients as being physically significant, when they are purely noise. Several checks to avoid such a pitfall are suggested.DOI: 10.1111/j.1600-0889.1988.tb00212.x
  • References (54)
    54 references, page 1 of 6

    Baker, M. B., Caniparoli, D. and Harrison, H . 1981. An analysis of the first year of M A P 3 rain chemistry measurements. Atmos. Enairon. IS,43-55.

    Barnston, A. G . and Livezey, R. E. 1987. Classification, seasonality and persistence of low-frequency atmospheric circulation patterns. Mon. Wea. Rec. 115, 1083-1 126.

    Bartlett, M. S. 1950. Tests of significance in factor analysis. Br. J. Psych. (Stat. See.) 3, 77--85.

    BMDP, 1981. Biomedical computer programs P-series. University of California Press, Berkeley, CA.

    Brier, G. W. and Meltesen, G . T. 1976. Eigenvector analysis for prediction of time series. J. Appl. Meteorol. IS, 1307- 1312.

    Cattell, R. B. 1966. The scree test for the number of factors. Multivar. Behaa. Res. I , 245-276.

    Christensen, W. I. and Bryson, R. A. 1966. An investigation of the potential of component analysis for weather classification. Mon. Wea. Rev. 94, 697- 709.

    Clarkson, D. B. 1979. Estimating the standard errors of rotated factor loadings by jackknifing. Psychometrika 44, 297-314.

    Cohen, S. J . 1983. Classification of 500 m b height anomalies using obliquely rotated principal components. J. Clim. Appl. Meteorol. 22, 1975-1988.

    Craddock, J . M. and Flood, C. R. 1969. Eigenvectors for representing the 500 m b geopotential surface over the northern hemisphere. Q. J. R. Meteorol. Soc. 95, 576-593.

  • Metrics
    No metrics available
Share - Bookmark