# [R] Error in 1:object\$rank : NA/NaN argument

From: Steffen Katzner <steffen.katzner_at_mail.gwdg.de>
Date: Sun 22 Jan 2006 - 22:28:35 EST

can anybody help with the following error message:

Error in 1:object\$rank : NA/NaN argument

I get it with comparisons of single means in an ANOVA. Example data below.

Thanks, Steffen

seven subjects participated in each of 6 conditions (intervals).

> subject = factor(rep(c(1:7), each = 6))
> interval = factor(rep(c(1:6), 7))

```+ 2.5957, 1.5666, 1.1984, 1.2761, 1.0022, 0.8597,
+ 3.9819, 3.1506, 1.5824, 1.7400, 1.4248, 0.6519,
+ 2.2521, 1.5248, 1.1209, 1.2193, 1.1994, 2.0910,
+ 2.4661, 1.3863, 1.3591, 0.9163, 1.3976, 1.7471,
+ 3.2486, 1.9492, 2.4228, 1.1276, 1.2836, 0.9814,
+ 1.7148, 1.7278, 2.7433, 1.4924, 1.0992, 0.7821)

```

> con

```[1,]    1    0    0    0    0
[2,]   -1    1    0    0    0
[3,]    0   -1    1    0    0
[4,]    0    0   -1    1    0
[5,]    0    0    0   -1    1
[6,]    0    0    0    0   -1

```

> summary(aovRes)

Df Sum Sq Mean Sq F value Pr(>F) Residuals 6 2.48531 0.41422

Error: subject:interval

Df Sum Sq Mean Sq F value Pr(>F) interval 5 13.8174 2.7635 8.7178 3.417e-05 *** Residuals 30 9.5098 0.3170

```---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

but if I want to look at the contrasts, something has gone wrong:

summary.aov(aovRes, split=list(interval = list("i1 vs i2" = 1, "i2 vs
i3" = 2, "i3 vs i4" = 3, "i4 vs i5" = 4, "i5 vs i6" = 5)))

Error in 1:object\$rank : NA/NaN argument

> aovRes\$contrasts

NULL

______________________________________________
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help