Factor Analysis – use of factors as predictor variables

Home Forums Methodspace discussion Factor Analysis – use of factors as predictor variables

Viewing 1 post (of 1 total)
  • Author
  • #2924
    David Kronemyer

    I started off with 32 predictor variables and successfully completed factor analysis to reduce them to four constructs.  No real interest in assigning factor loadings to each one of the predictors.  Rather I want to use the four factor scores as new predictor variables in a regression analysis.  At p. 636 the Field text states this can be done but doesn’t set forth an operational procedure.  What SPSS output does one use?  Are they coefficients, do you have to multiply them by something (what?), or add them together?  Several of the original predictor variables used different measurement scales.  At p. 633 Field says that as a result, different factor scores can’t be compared.  Do you have to normalize them in order to use them as new predictors?  Or is this obviated by using the “Anderson-Rubin method” described at p. 635?  I could use some advice from Jane Superbrain, thanks in advance.  DAVID

Viewing 1 post (of 1 total)
  • You must be logged in to reply to this topic.