Displaying 3 results from an estimated 3 matches for "covlist".
Did you mean:
aovlist
2004 Jan 20
1
evaluation of discriminant functions+multivariate homosce dasticity
...0 || alpha >= 1)
stop('significance level must be between 0 and 1')
g = nlevels(cl) ## Number of groups.
n = table(cl) ## Vector of groups-size.
N = nrow(X)
p = ncol(X)
bandera = 2
if (any(n >= 20)) bandera = 1
## Partition of the group covariance matrices.
covList <- tapply(X, rep(cl, ncol(X)), function(x, nc) cov(matrix(x,
nc=nc)),
ncol(X))
deno = sum(n) - g
suma = array(0, dim=dim(covList[[1]]))
for (k in 1:g)
suma = suma + (n[k] - 1) * covList[[k]]
Sp = suma / deno ## Pooled covariance matrix.
Falta=0
for (k in...
2000 Jan 31
1
Feature requests for princomp(.) : Allow cor() specifications
(all in subject).
If I want to do a PC analysis in a situation with missing data,
I may want to have same flexibility as with "cor(.)",
e.g., I may want
princomp(x, ..., use.obs = "pairwise.complete")
Actually, I may want even more flexibility.
Currently,
princomp(.)
has
if (cor)
cv <- get("cor", envir = .GlobalEnv)(z)
else cv <-
2004 Sep 04
1
Inconsistencies in subassignment (PR#7210)
I have made the 3-d case do the same as the vector case, which is what the
C code clearly intended (a goto label was in the wrong place).
This leaves the bigger question of the right thing to do. I note that data
frames give an error when any indices are NA.
-thomas
On Fri, 3 Sep 2004 ripley@stats.ox.ac.uk wrote:
> Apart from the inconsistencies, there are two clear bugs here:
>
> 1)