Maybe related with Paste()

General
#1

Hi Community,

I am trying to make a model with the code below.
Model1 <- ' f1 =~ aaq1 + aaq2 + aaq3 + aaq4 + aaq5 + aaq6 + aaq7+ aaq8'

It seems possible to make it easy to use a function because there is a pattern in the code. Could you let me know how I can do it?

I tried this but it didn't work.
Model1 <- ' f1 =~ paste0(aaq, [1:8], sep = '+')'

Best,

#2

Perhaps

paste0("aaq", 1:8, collapse = " + ")
#3

Another possible path would use as.formula()

as.formula(paste("~",paste0("aaq", 1:8, collapse = '+')))
~aaq1 + aaq2 + aaq3 + aaq4 + aaq5 + aaq6 + aaq7 + aaq8
1 Like
#4

Ah, much better than my poor effort.

#5

Thank you so much for both of you!
I am trying to run Structural Equation Modeling with Lavaan. Thus, I tried this code below. But when I used "=~" symbol, it doesn't work. Could you let me know how to handle this?

practice <- as.formula(paste("=~", paste0("aaqii", 1:8, collapse = "+")))
#> Error in str2lang(x): <text>:1:1: unexpected '='
#> 1: =
#>     ^
#6

You have *"=~" when FJCC said "~"

Does this help?

#7

Yes, but while "~" symbol is often used to indicate regression, I want to use "=~" symbol, which is used in Structural Equation Modeling.

#8

Remove the "~" and insert the "="?

#9

Thanks for the suggestion, but unfortunately it doesn't work either.

#10

Can you point us to an example in Structural Equation Modeling?

#11

When we say x1 and x2 are predicted by A, we could use the code below.

A =~ x1 + x2

In this case, A is latent variable and x1/x2 are observed variable (i.e., indicator).

#12

Closest I can come, adapting FJCC's example is

(paste("=~",paste0("aaq", 1:8, collapse = '+')))
#13

I might be wrong, but from what I remember lavaan needs a string not a formula. The string can contain many formulae... so @jrkrideau is probably right. You can then add f1 before the =~

paste("f1 =~",paste0("aaq", 1:8, collapse = '+'))
#14

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.