Talk:Factor analysis/Archives/2017

Standard deviation formula
In the section "Mathematical model of the same example", the formula given for the standard deviation is
 * $$\sigma_a^2=\tfrac{1}{N_i}\sum_i (x_{ai}-\mu_a)^2$$

In particular, we're dividing by the number of samples $$N_i$$. However to get an unbiased estimate of the standard deviation of the distribution, one should rather divide by one less $$N_i-1$$ (since the average $$\mu_a$$ used in the calculation was computed from the same set of samples). The difference would of course be rather small (e.g. 1000 versus 999) in the typical case with this method, so it probably makes little practical difference, but what is theoretically correct? Further down it is claimed that the $$z$$ vector has unit length, which would not follow if dividing by $$N_i-1$$ instead. Is it standard practice with Factor Analysis to use the stated normalization to improve the linear algebra, even if that means employing a slightly biased estimate of the standard deviation? It is probably no big deal, but could warrant a remark. 130.243.68.90 (talk) 13:30, 8 March 2017 (UTC)

Possible typo??
I wonder if there is a missing comma in this sentence:

"Factor analysis is not used to any significant degree in physics, biology and chemistry but is used very heavily in psychometrics personality theories, marketing, product management, operations research and finance."

amd maybe it should read:

"Factor analysis is not used to any significant degree in physics, biology and chemistry but is used very heavily in psychometrics, personality theories, marketing, product management, operations research and finance."

External links modified
Hello fellow Wikipedians,

I have just added archive links to 1 one external link on Factor analysis. Please take a moment to review my edit. If necessary, add after the link to keep me from modifying it. Alternatively, you can add to keep me off the page altogether. I made the following changes:
 * Added archive http://web.archive.org/web/20040818062948/http://comp9.psych.cornell.edu:80/Darlington/factor.htm to http://comp9.psych.cornell.edu/Darlington/factor.htm

When you have finished reviewing my changes, please set the checked parameter below to true or failed to let others know (documentation at Sourcecheck).

Cheers.—cyberbot II  Talk to my owner :Online 04:13, 28 February 2016 (UTC)

External links modified
Hello fellow Wikipedians,

I have just added archive links to 1 one external link on Factor analysis. Please take a moment to review my edit. If necessary, add after the link to keep me from modifying it. Alternatively, you can add to keep me off the page altogether. I made the following changes:
 * Added archive http://web.archive.org/web/20040818062948/http://comp9.psych.cornell.edu:80/Darlington/factor.htm to http://comp9.psych.cornell.edu/Darlington/factor.htm

When you have finished reviewing my changes, please set the checked parameter below to true or failed to let others know (documentation at Sourcecheck).

Cheers.—cyberbot II  Talk to my owner :Online 04:13, 28 February 2016 (UTC)