[R] EM unsupervised clustering

[Federico Calboli]

Dimitris Rizopoulos wrote:
> you could also have a look at function lca() from package `e1071' that 
> performs a latent class analysis, e.g.,
> 
> fit1 <- lca(data, 2)

I tried but I got:

 > lca(data, 2)
Error in matrix(0, 2^nvar, nvar) : matrix: invalid 'nrow' value (too large or NA)
In addition: Warning message:
NAs introduced by coercion in: matrix(0, 2^nvar, nvar)

and dim(mat) is 110 and 109.

I am puzzled.

Cheers,

Fede


-- 
Federico C. F. Calboli
Department of Epidemiology and Public Health
Imperial College, St Mary's Campus
Norfolk Place, London W2 1PG

Tel  +44 (0)20 7594 1602     Fax (+44) 020 7594 3193

f.calboli [.a.t] imperial.ac.uk
f.calboli [.a.t] gmail.com