http://r.789695.n4.nabble.com/lmer-causes-segfault-td2335407.html
in lmer this is pretty crucial if you have factors that are identified by numerical values:
>dummy.data = read.csv("~/tmp/tmp.csv")
>dummy.data$c <- factor(dummy.data$c)
> str(dummy.data)
'data.frame': 4800 obs. of 5 variables:
$ g : Factor w/ 2 levels "1","2": 1 1 1 1 1 1 1 1 1 1 ...
$ s : Factor w/ 24 levels "1","2","3","4",..: 1 1 1 1 1 1 1 1 1 1 ...
$ c : Factor w/ 100 levels "1","2","3","4",..: 1 1 2 2 3 3 4 4 5 5 ...
$ pc: Factor w/ 2 levels " c"," p": 1 2 1 2 1 2 1 2 1 2 ...
$ x : num 0.175 0.511 0.237 0.572 0.306 ...ezANOVA converts numeric values to factors because it knows that everything but the dependent variable must be a factor.
ezANOVA is limited in the number of levels of a factor (roughly 50?)
lmer can take multiple levels, but doesn't give you standard stats.
> library(ez)
>ezPrecis(dummy.data)
Data frame dimensions: 4800 rows, 5 columns
type missing values min max
g factor 1. 1. 1 2
s factor 1. 24 1. 24
c factor 1. 100 1. 100
pc factor 1. 1. c p
x numeric 1. 3848 1. 1The factor (ordered) function creates a factor (ordered factor) from a vector. Factor labels can be speci ed in the optional labels argument. Suppose the spray variable in the InsectSprays data was stored as numeric values 1; 2; : : : ; 6. We convert it back to a factor with factor. > str(sprays <- within(InsectSprays, spray <- as.integer(spray))'data.frame': 72 obs. of 2 variables: $ count: num 10 7 20 14 14 12 10 23 17 20 ... $ spray: int 1 1 1 1 1 1 1 1 1 1 ... > str(sprays <- within(sprays, spray <- factor(spray, + labels = LETTERS[1:6]))) 'data.frame': 72 obs. of 2 variables: $ count: num 10 7 20 14 14 12 10 23 17 20 ... $ spray: Factor w/ 6 levels "A","B","C","D",..: 1 1 1 1 1 1 1 1 1 1 ...
-- Main.DennisNorris - 27 Oct 2010