# [R] explalinig the output of my linear model analysis

Peter Ehlers ehlers at ucalgary.ca
Tue Oct 27 07:58:22 CET 2009

```Ista,

Here's the quote from MASS (the book, 4e, p.142):
"Terms of the form a/x, where a is a factor, are best thought of
as "separate regression models of type 1 + x within the levels
of a."

I'm not answering the OP's question because in my view if one
doesn't understand the output of lm(), then one's knowledge of
statistics is insufficient to warrant using lm(). [I hasten to
add that that may not be true for all functions available in
all R-packages.]
Perhaps somewhat unfortunately, it's become easy to use
computers to produce nonsense. It's a bit like me getting
behind the wheel of a bus and trying to navigate rush hour
traffic in central Paris or London.

Advice to the OP: I don't mean to be unnecessarily critical,
but you should get a stats book and work your way through it.
Dalgaard's 'Intro Stats with R' would be a good start.
If you have questions after that, there are plenty of people

-Peter Ehlers

Ista Zahn wrote:
> I've never seen the "/" used in a formula like that. What does it do?
>
> -Ista
>
> On Mon, Oct 26, 2009 at 8:13 AM, john56 <panatheod at gmail.com> wrote:
>> Hi,
>>
>> I am new in statistics and i manage to make the linear model analysis but i
>> have some difficulties in explaining the results. Can someone help me
>> explalinig the output of my linear model analysis ? My data are with 2
>> variables habitat (e,s) and treatment (a,c,p) with multiple trials within.
>>
>>
>> Call:
>> lm(formula = a\$wild ~ a\$habitat/a\$treatment/a\$trial)
>>
>> Residuals:
>>    Min      1Q  Median      3Q     Max
>> -58.905 -19.958  -5.774  16.693  88.890
>>
>> Coefficients:
>>                                Estimate Std. Error t value Pr(>|t|)
>> (Intercept)                      55.4664     2.0332  27.281  < 2e-16 ***
>> a\$habitats                      -11.9615     2.8753  -4.160 3.26e-05 ***
>> a\$habitate:a\$treatmentc           7.3581     2.8753   2.559  0.01054 *
>> a\$habitats:a\$treatmentc          -4.9803     2.8753  -1.732  0.08335 .
>> a\$habitate:a\$treatmentp         -13.9906     2.8753  -4.866 1.19e-06 ***
>> a\$habitats:a\$treatmentp         -16.1311     2.8753  -5.610 2.17e-08 ***
>> a\$habitate:a\$treatmenta:a\$trial  -0.3204     0.3808  -0.841  0.40030
>> a\$habitats:a\$treatmenta:a\$trial  -0.1319     0.3808  -0.346  0.72905
>> a\$habitate:a\$treatmentc:a\$trial  -1.1250     0.3808  -2.954  0.00316 **
>> a\$habitats:a\$treatmentc:a\$trial  -0.4236     0.3808  -1.112  0.26608
>> a\$habitate:a\$treatmentp:a\$trial  -0.3021     0.3808  -0.793  0.42775
>> a\$habitats:a\$treatmentp:a\$trial  -0.2873     0.3808  -0.754  0.45072
>> ---
>> Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
>>
>> Residual standard error: 26.8 on 3588 degrees of freedom
>> Multiple R-squared: 0.1383,     Adjusted R-squared: 0.1357
>> F-statistic: 52.35 on 11 and 3588 DF,  p-value: < 2.2e-16
>>
>> --
>> View this message in context: http://www.nabble.com/explalinig-the-output-of-my-linear-model-analysis-tp26058610p26058610.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