Tom Swift and His Electric Factor Analysis Machine

This is an interesting and amusing comment on factor analysis, a technique very closely related to principal component analysis: J. Scott Armstrong, Derivation of Theory by Means of Factor Analysis or Tom Swift and His Electric Factor Analysis Machine, The American Statistician, 1967, 17-21 Link


  1. N. Joseph Potts
    Posted Feb 25, 2005 at 11:38 AM | Permalink

    This article discussed PRINCIPAL FACTOR ANALYSIS explicitly. I make that out to be its subject.
    Secondly, I wonder if the American Statistician might be a suitable forum in which to publish at least some of the findings being arrived at by McIntyre, McKitrick, and friends.

  2. Posted Feb 25, 2005 at 8:56 PM | Permalink

    I had to laugh when reading that “one now gets the impression that the empiricist feels little need for the theorist.” In sci.environment discussion, a fellow thought it was pejorative of me to use the term “multiproxy theorists” in asking the question “Have any of the multiproxy theorists published the results of an investigation into the inherent smearing of variability when combining time series each with its own dating error?”

  3. Posted Feb 25, 2008 at 2:30 PM | Permalink

    Obviously, the data speaks for itself

%d bloggers like this: