Hi, I'm currently trying to plot a CFA in which an Acquiescence factor is modeled across three correlated substantive dimensions. I've set the Acquiescence and substantive factors to be uncorrelated and would like to omit these paths, but not the correlations between the substantive factors, from the plot. Is there a way to do this? I've copied code for the model and plot below.
Hi, I'm currently trying to plot a CFA in which an Acquiescence factor is modeled across three correlated substantive dimensions. I've set the Acquiescence and substantive factors to be uncorrelated and would like to omit these paths, but not the correlations between the substantive factors, from the plot. Is there a way to do this? I've copied code for the model and plot below.
Model:
multi2acq_mod <- 'system =~ EPO7 + EPO10; antisusp =~ EPO1R + EPO2R + EPO3R + EPO4R + EPO6R + EPO8 + EPO11; prevent =~ EPO5R + EPO9; acq =~ a*EPO1R + a*EPO2R + a*EPO3R + a*EPO4R + a*EPO5R + a*EPO6R + a*EPO7 + a*EPO8 + a*EPO9 + a*EPO10 + a*EPO11; acq ~~ 0*system + 0*antisusp + 0*prevent'Plot:
layout <- matrix(c(0.8,1,seq(-1.15,0.05,.2),.4,.6,0.9,-0.5,0.5,0, 0,0,0,0,0,0,0,0,0,0,0,2,2,2,-3), ncol=2,nrow=15,byrow=FALSE) labs <- c(paste0("item",c(7,10,1,2,3,4,6,8,11,5,9)),"System","Anti-Sus-\npension","Pre-\nvention","Acqui-\nescence") semPaths(multi2acq_cfa,layout=layout,what="path",style="lisrel", whatLabels="no",edge.color="black",residScale=5, fixedStyle=c("black","solid"),freeStyle=c("black","solid"), nodeLabels=labs)And here is the figure it produces: