Volume 6 · PCA, factor analysis, SEM

Most of what psychology measures cannot be measured directly.

Twelve days on latent structure: the correlation matrix as raw material, components and factors, how many to keep, rotation, confirmatory models, SEM and its fit indices, invariance before any group comparison, and the two classification methods. This is the volume psychometric and individual-differences research is built on.

12
days of 45–55 min
4
ways to choose k factors
5
fit indices worth quoting
3
invariance levels to clear
{{ d.badge }} {{ d.meta }}

{{ d.title }}

{{ d.lead }}

{{ s.t }}
{{ b.title }}
{{ s.t }}
The mistake this topic produces
{{ s.t }}
{{ c.eyebrow }}
{{ c.title }}
{{ s.t }}
{{ h.label }}
{{ c.v }}
{{ b.eq }} {{ b.plain }} {{ sy.d }} {{ b.work }}
Do this now · 15 minutes
{{ d.task }}
Reference

{{ rf.title }}

{{ rf.lead }}

{{ h.label }}
{{ c.v }}
Checkpoint

Ten questions before you move on

Factor analysis is the multivariate topic entrance papers ask about most, and invariance is the one reviewers ask about most.

{{ quizCounter }}
{{ quizScore }}
{{ quizQ }}
{{ quizFb }}

Next: volume 7, Psychometrics

Twelve days on measurement you can defend: classical test theory, every reliability coefficient and its myths, validity evidence, item analysis, item response theory, DIF, norms, and building a scale end to end.

Start day 77 →