Content deleted Content added
Added footnote about latent trait analysis (LTA) being used interchangeably with item response theory (IRT). Also gave citation for this in the footnote itself |
Add "citation needed" template to "there may be a psychometrical latent variable, but not a psychological psychometric variable." |
||
Line 31:
In [[factor analysis]] and [[latent trait analysis]]{{refn|group=note|name=LTAandIRT| The terms "latent trait analysis" and "item response theory" are often used interchangeably.<ref>{{Cite web |first=John |last=Uebersax |title=Latent Trait Analysis and Item Response Theory (IRT) Models |url=http://www.john-uebersax.com/stat/lta.htm |url-status=live |archive-url=https://web.archive.org/web/20221101072029/http://www.john-uebersax.com/stat/lta.htm |archive-date=2022-11-01 |access-date=2022-11-01 |website=John-Uebersax.com |language=en-US}}</ref>}} the latent variables are treated as continuous [[normal distribution|normally distributed]] variables, and in latent profile analysis and latent class analysis as from a [[multinomial distribution]].<ref>{{cite book |last=Everitt |first=BS |title=An Introduction to Latent Variables Models |year=1984 |publisher=Chapman & Hall |isbn=0-412-25310-0 }}</ref> The manifest variables in factor analysis and latent profile analysis are continuous and in most cases, their conditional distribution given the latent variables is assumed to be normal. In latent trait analysis and latent class analysis, the manifest variables are discrete. These variables could be dichotomous, ordinal or nominal variables. Their conditional distributions are assumed to be binomial or multinomial.
Because the distribution of a continuous latent variable can be approximated by a discrete distribution, the distinction between continuous and discrete variables turns out not to be fundamental at all. Therefore, there may be a psychometrical latent variable, but not a [[psychology|psychological]] psychometric variable.{{Citation needed|date=November 2022}}
==See also==
| |||