Question indicator reliability in JASP

Liesbeth

Hi there,

I'm reading Todd et al. (2017) and their best practice recommendations for SEM, and they mention indicator reliability: 'refers to the proportion of variance in each measured variable that is accounted for by the latent factor it supposedly represents (O’Rourke & Hatcher, 2013). Calculating IR is straightforward as it merely involves squaring the standardized factor loading for each measured variable'.

I was just wondering if this would be the same as Rsquared in JASP, when doing a SEM analysis?

Also they refer to average variance extracted (AVE) as a way to measure discriminant validity; and I was wondering if there is a function in JASP for SEM models that can do that?

Thanks in advance for your help.

EJ

I've asked our SEM expert for advice (sorry about the tardy responses, I've been absorbed by the demands of online teaching, only catching up now...)

E.J.

evankesteren

Hi Liesbeth,

yes, you are correct - the R^2 value for each indicator is the proportion of variance accounted for by the latent factor (if the latent factor is the only thing this indicator is predicted by, otherwise it's just the proportion of variance explained)

Erik-Jan

Liesbeth

Thanks!