[R] Anova(car) SS digits

[John Fox]

Dear Tyler,

> -----Original Message-----
> From: r-help-bounces at r-project.org 
> [mailto:r-help-bounces at r-project.org] On Behalf Of Tyler Smith
> Sent: Thursday, November 29, 2007 2:07 PM
> To: r-help at stat.math.ethz.ch
> Subject: [R] Anova(car) SS digits
> 
> Hi,
> 
> When I use Anova(car) to produce type III SS, 'Sum Sq' is reported in
> integers:
> 
> > Anova(bot.lm3, type ="III")
> Anova Table (Type III tests)
> 
> Response: bottemp
>                          Sum Sq  Df    F value  Pr(>F)
> (Intercept)               45295   1 29436.4440 < 2e-16
> fungroup                      3   2     0.8259 0.44006
> numsp.fun                    11   2     3.4503 0.03460
> block                       419   4    68.0017 < 2e-16
> fungroup:numsp.fun            6   4     1.0317 0.39340
> fungroup:block                9   8     0.7429 0.65346
> numsp.fun:block              12   8     0.9501 0.47795
> fungroup:numsp.fun:block     27  16     1.0920 0.36882
> Residuals                   205 133                   
> 
> I have tried specifying digits = 7 in the call to Anova, but 
> that doesn't change anything. The output from another stats 
> program for the same data confirms that the ouptut above is 
> correct, but is rounded to the nearest integer. The dataset 
> is too large to post here, but I can confirm that I get the 
> expected results from the examples in ?Anova, as well as for 
> type = 'II' on my own data. This output, and relevant
> options() and sessionInfo are pasted below. What am I doing wrong?

Anova() creates an object of class "anova" which then gets printed by the
print method for "anova" objects. The reason that the sums of squares for
the type II tests are rounded like this is because of the large value for
the intercept. Although Anova() doesn't take a digits argument,
print.anova() does, and so, e.g., you could use the command

print(Anova(bot.lm3, type ="III"), digits=7)

I hope this helps,
 John

> 
> Thanks,
> 
> Tyler
> 
> >      mod <- lm(conformity ~ fcategory*partner.status, data=Moore,
> +        contrasts=list(fcategory=contr.sum, 
> partner.status=contr.sum))
> >      Anova(mod)
> Anova Table (Type II tests)
> 
> Response: conformity
>                          Sum Sq Df F value   Pr(>F)
> fcategory                 11.61  2  0.2770 0.759564
> partner.status           212.21  1 10.1207 0.002874
> fcategory:partner.status 175.49  2  4.1846 0.022572
> Residuals                817.76 39                 
> >      Anova(mod, type="III")
> Anova Table (Type III tests)
> 
> Response: conformity
>                          Sum Sq Df  F value    Pr(>F)
> (Intercept)              5752.8  1 274.3592 < 2.2e-16
> fcategory                  36.0  2   0.8589  0.431492
> partner.status            239.6  1  11.4250  0.001657
> fcategory:partner.status  175.5  2   4.1846  0.022572
> Residuals                 817.8 39                   
> 
> > Anova(bot.lm3, type ="II")
> Anova Table (Type II tests)
> 
> Response: bottemp
>                          Sum Sq  Df F value  Pr(>F)
> fungroup                   1.87   2  0.6069 0.54656
> numsp.fun                 11.14   2  3.6214 0.02942
> block                    486.47   4 79.0379 < 2e-16
> fungroup:numsp.fun         6.32   4  1.0275 0.39553
> fungroup:block            11.43   8  0.9283 0.49542
> numsp.fun:block           11.29   8  0.9169 0.50473
> fungroup:numsp.fun:block  26.89  16  1.0920 0.36882
> Residuals                204.65 133                
> 
> > options('digits')
> $digits
> [1] 7
> 
> > options('contrasts')
> $contrasts
> [1] "contr.sum"  "contr.poly"
> 
> > sessionInfo()
> R version 2.5.1 (2007-06-27)
> i486-pc-linux-gnu 
> 
> locale:
> 
> LC_CTYPE=en_CA.UTF-8;LC_NUMERIC=C;LC_TIME=en_CA.UTF-8;LC_COLLA
> TE=en_CA.UTF-8;
> LC_MONETARY=en_CA.UTF-8;LC_MESSAGES=en_CA.UTF-8;LC_PAPER=en_CA
> .UTF-8;LC_NAME=C;
> LC_ADDRESS=C;LC_TELEPHONE=C;LC_MEASUREMENT=en_CA.UTF-8;LC_IDEN
> TIFICATION=C
> 
> attached base packages:
> [1] "stats"     "graphics"  "grDevices" "utils"     
> "datasets"  "methods"  
> [7] "base"     
> 
> other attached packages:
>     car
> "1.2-7"
> 
> ______________________________________________
> 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.
>