Poglavlje 10 Eksplanatorne i konfirmatorne analize
U ovom poglavlju biti će riječi o različitim eksplanatornim i konfirmatornim analizama. Faktorske analize (FA - Factor Analysis) i teorija odgovora na zadatke (IRT - Item Response Theory) su grupe analiza, modela i pristupa koji se koriste pri izradi novih instrumenata ili validaciju postojećih instrumenata u društvenim, bihevioralnim, biomedicinskim i čak humanističkim područjima istraživanja.
Uz faktorsku analizu i teoriju odgovora na zadatke, u ovom poglavlju usporedit će se i druge ekplanatorne i konfirmatorne analize koje će dati kritički osvrt pregledom literature i usporedbom vrijednosti primjenom modela u R okruženju.
Središte navedenih analiza su latentne varijable koje predstavljaju neposredno ‘ne mjerljive’ dimenzije koje se ‘kriju’ u pozadini pitanja, čestica, entiteta koji su opažljivi, mjerljivi, na neki način dostupni. Latentne varijable ne mogu se mjeriti direktno, neposredno, već o njima kao svojevrsnim hipotetskim konstrukima zaključujemo temeljem analize čestica, entiteta ili pitanja.
10.1 Analiza glavnih komponenti (PCA)
Despite all these similarities, there is a fundamental difference between them: PCA is a linear combination of variables; Factor Analysis is a measurement model of a latent variable. (https://www.theanalysisfactor.com/the-fundamental-difference-between-principal-component-analysis-and-factor-analysis/)
10.2 Konfirmatorna faktorska analiza
Konfirmatorna faktorska analiza (CFA - confirmatory factor analysis) je vrsta strukturalnog modeliranja (SEM - Structural equation modeling) koja se često koristi u primjenjenim istraživanjima gdje se provjerava odnos između mjerljivih varijabli (čestice upitnika, ukupni rezultati na testu ili dijelovima testa, procjene elemenata ponašanja i sl.) i latentnih varijabli ili faktora (Brown, 2014). Ova vrsta analize se najčešće koristi u postupku provjere nekog mjernog instrumenta, primjerice kada se mjerni instrument (upitnik) koristi u nekoj drugoj zemlji ili kulturi te se želi provjeriti struktura upitnika nakon prijevoda.
Konfirmatorna analiza se koristi zajedno sa metodama provjere pouzdanosti ljestvice. Konfirmatorna analiza doprinosi konvergentnoj i diskriminativnoj valjanosti teorijskih konstrukata koji su u pozadini razvoja i primjene nekog mjernog instrumenta.
Jedan od ponajboljih paketa u R okruženju za primjenu konfirmatorne faktorske analize je lavaan paket (Rosseel et al., 2021).
library(lavaan)## This is lavaan 0.6-9
## lavaan is FREE software! Please report any bugs.##
## Attaching package: 'lavaan'## The following object is masked from 'package:lessR':
##
## cfa## The following object is masked from 'package:psych':
##
## cor2covMjera nepromjenjivosti (measurement invariance) je posebno važna kod razlike između skupina ili grupa u faktorskoj strukturu a koja se često upravo testira kod primjene konfirmatorne faktorske analize. Da li je isti konstrukt ili faktor prisutan kod različitih skupina ispitanika. Ovaj dalje tekst je iz wikipedie. Measurement invariance or measurement equivalence is a statistical property of measurement that indicates that the same construct is being measured across some specified groups. For example, measurement invariance can be used to study whether a given measure is interpreted in a conceptually similar manner by respondents representing different genders or cultural backgrounds. Violations of measurement invariance may preclude meaningful interpretation of measurement data. Tests of measurement invariance are increasingly used in fields such as psychology to supplement evaluation of measurement quality rooted in classical test theory. Measurement invariance is often tested in the framework of multiple-group confirmatory factor analysis (CFA).[2] In the context of structural equation models, including CFA, measurement invariance is often termed factorial invariance. Although there is need for further research on the application of various invariance tests and their respective criteria across diverse testing conditions, two approaches are common among applied researchers. For each model being compared (e.g., Equal form, Equal Intercepts) a χ2 fit statistic is iteratively estimated from the minimization of the difference between the model implied mean and covariance matrices and the observed mean and covariance matrices.[7] As long as the models under comparison are nested, the difference between the χ2 values and their respective degrees of freedom of any two CFA models of varying levels of invariance follows a χ2 distribution (diff χ2) and as such, can be inspected for significance as an indication of whether increasingly restrictive models produce appreciable changes in model-data fit.[7] However, there is some evidence the diff χ2 is sensitive to factors unrelated to changes in invariance targeted constraints (e.g., sample size).[8] As a result, researchers are also recommended to use the difference between the comparative fit index (ΔCFI) of two models specified to investigate measurement invariance. When the difference between the CFIs of two models of varying levels of measurement invariance (e.g., equal forms versus equal loadings) is greater than 0.01, then invariance in likely untenable.[8] It is important to note that the CFI values being subtracted are expected to come from nested models as in the case of diff χ2 testing;[9] however, there is indication that applied researchers rarely take this into consideration when applying the CFI test.