[R] Intra-Class correlation psych package missing data

[William Revelle]

Ross,
  My apologies, I just discovered your email (from April) to the 
R-help list serve asking about ICC in psych.

ICC does not remove missing data but rather lets the ANOVA handle it. 
It is probably more appropriate work on complete cases (as does the 
icc in the  irr package).
that is

my.data <- na.omit(my.data)
ICC(my.data)


I have just fixed ICC so that it will by default use na.omit and thus 
work on complete cases.    This will be in the psych 1.0.89 release 
which should be ready by this weekend.

Bill





At 4:21 AM -0800 4/8/10, RCulloch wrote:
>Hello R users, and perhaps William Revelle in particular,
>
>I'm curious as to how ICC deals with missing data, so for example you are
>sampling individuals over set periods in time and one individual is missing
>or was not recaptured at that given time point - leading to NA in the
>dataset. My thought was that it should then omit data by individual, but I'm
>not convinced that that is what it is doing?

You are completely correct.

>
>Does anyone know, I have looked at ?ICC but there is no information there,
>apologies if I have missed it in any other help file, I have looked, but to
>no avail!


>
>Thanks in advance,
>
>Ross
>--
>View this message in context: 
>http://n4.nabble.com/Intra-Class-correlation-psych-package-missing-data-tp1773942p1773942.html
>Sent from the R help mailing list archive at Nabble.com.
>
>______________________________________________
>R-help at r-project.org mailing list
>https://stat.ethz.ch/mailman/listinfo/r-help
>PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>and provide commented, minimal, self-contained, reproducible code.