Beruflich Dokumente
Kultur Dokumente
World View of PC vs. CF Choosing between PC and CF PAF -- most common kind of CF Communality & Communality Estimation Common Factor Scores
We measure variables
The goal of factoring is data reduction determine the # of kinds of information in the variables build a PC for each
A persons values on these latent constructs causes their scores on any measured variable(s) any variable has two parts common part -- caused by values of the latent constructs unique part -- not related to any latent construct (error)
the variables
CFs are linear combinations of the common parts of the measured variables that capture the underlying constructs
measures adding, subtraction, multiplication vocabulary, reading speed, reading comprehension politeness, listening skills, sharing skills
Each measure is produced by a weighted combination of the latent constructs, plus something unique to that measure . . .
= = = =
.5*IQ +.8*Math + 0*Reading + 0*Social + Ua .5*IQ +.8*Math + 0*Reading + 0*Social + Us .5*IQ + 0*Math + .8*Reading + 0*Social + Uv .4*IQ + 0*Math + 0*Reading +.8*Social + Up
adding subtraction multiplication vocabulary reading speed reading comp politeness listening skills sharing skills
.6 .6 .6 .6 .6 .6
Axis tells us that the factors are extracted from a reduced correlation matrix
diagonals < 1.00 diagonals = the estimated communality of each variable reflecting that not all of the variance of that variable is produced by the set of latent variables So, factors extracted from the reduced R will reveal the latent variables
The researcher selects the procedure based on their purpose for the factor analysis !!
Note how the definition shifts from variance shared with the latent constructs to variance shared with the other variables in the set !!
Huh?!!? The idea is pretty simple (and elegant) If the communality estimates are correct, then they will be returned from the factor analysis ! So, start with a best guess of the communalities, and iterate until the estimates are stable Note: This takes advantages of the self-correcting nature of this iterative process the initial estimates have very little effect on the final communalities (R2 really easy to calculate) starting with the PC communalities tends to work quickly Note: This process assumes the latent constructs are adequately represented by the variable set !!
Problems estimating communalities in a CF analysis failure to converge usually this can be solved by increasing the number of iterations allowed (=1000) Heywood case > 1.00 During iteration communality estimates can become larger than 1.00 However no more than all of a variables variance can be common variance! Usual solutions Use the solution from the previous iteration Drop the offending variable If other variables are threatening to Heywood consider aggregating them together into a single variable
Maximum Likelihood method of Common Factoring If assumptions of interval measurement and normal distribution are well-met, ML works somewhat better than PAF & vice versa ML is an extraction technique the rotational techniques discussed for PC and PAF all apply to ML factors ML is a common factoring technique issue of factor score estimation are the same as for PAF Proponents of ML exploratory factoring emphasize ML estimation procedures are most the common in confirmatory factoring, latent class measurement, structural models & the generalized linear model ML estimation permits an internally consistent set of significance tests e.g., # factors decisions.