Natural feeling domain-specific language for building structural equation models in R for estimation by covariance-based methods (like LISREL/Lavaan) or partial least squares (like SmartPLS)
58
stars
19
forks
source link
Significance of correlations between constructs #334
I would like to calculate the significance level of the correlations between constructs.
With the command "___$validity$fl_criteria" I do get the correlations between the construct but without significance level.
(I do know that the superior method of investigating discriminant validity using the HTMT criterion allows for bootstrap.)
As it seems that "seminr" does not run bootstrap for the correlations between LV, I have found on a forum for "smartpls" a workaround which suggest to copy the standardized LV scores and do the analysis with another program (https://forum.smartpls.com/viewtopic.php?t=2487).
Now, the question:
How can I generate/calculate the standardized LV scores for my variables?
I have tried the function "construct_scores" (which may be totally unrelated to what I need), but the results always show NULL.
On another note: If I want to investigate difference in the levels of constructs between two samples using ANCOVAs, is the value for a construct the average of the items measuring the constructs (Construct1_1 = 5, Construct1_2 = 4 and Construct1_3 = 3 --> Construct_1 = 4) or do I need to account for different factors such as weighting and such?
Thank you so much in advance for taking the time to answer my questions!
As I am super new to SEM PLS, the questions also might be a little "stupid".
Hello,
I would like to calculate the significance level of the correlations between constructs.
With the command "___$validity$fl_criteria" I do get the correlations between the construct but without significance level. (I do know that the superior method of investigating discriminant validity using the HTMT criterion allows for bootstrap.)
As it seems that "seminr" does not run bootstrap for the correlations between LV, I have found on a forum for "smartpls" a workaround which suggest to copy the standardized LV scores and do the analysis with another program (https://forum.smartpls.com/viewtopic.php?t=2487).
Now, the question: How can I generate/calculate the standardized LV scores for my variables? I have tried the function "construct_scores" (which may be totally unrelated to what I need), but the results always show NULL.
On another note: If I want to investigate difference in the levels of constructs between two samples using ANCOVAs, is the value for a construct the average of the items measuring the constructs (Construct1_1 = 5, Construct1_2 = 4 and Construct1_3 = 3 --> Construct_1 = 4) or do I need to account for different factors such as weighting and such?
Thank you so much in advance for taking the time to answer my questions! As I am super new to SEM PLS, the questions also might be a little "stupid".
Cheers, zayuen