Creates a function for initializing latent class model by dichotomizing via mean over all responses
blcInitializeSplitDichotomizeUsingMean(threshold = 0.5, fuzz = 0.95)
Mean threshold for determining class
“fuzz” factor for producing imperfectly clustered subjects
Creates a function
f(x) that will take a data matrix
initialize a weight matrix for a two-class latent class model.
Here, a simple threshold will be applied to the mean over all item responses.
blcTree for example of using “blcInitializeSplit...” to create starting values.
f(x) (see Details.)