[R] Levene's test output

Fri Jun 21 13:25:34 CEST 2013

```Hello,

Just to add to the last post, you can try to get that p-value using what
that output gives you:

df1 <- 1
df2 <- 356
F_stat <- 10.948
pf(F_stat, df1, df2, lower.tail = FALSE) # same value

Hope this helps,

Em 21-06-2013 12:11, Rui Barradas escreveu:
> Hello,
>
> The Pr(>F) is a regular p-value, with the usual meaning.
>
>
> Em 21-06-2013 11:05, pieter escreveu:
>> k.
>> Thanks.
>> Sorry i'm not the biggest statician, but I still find the output write
>> out not the clearest of all. Anyway, that is probably a personal
>> problem. :-)
>>
>> Just one question. the Pr(>F) is just the regular p value, right? so
>> above the treshold means equal variance?
>>
>> Thanks alot.
>>
>> Pieter
>>
>> On vr 21 jun 2013 11:56:06 CEST, Rui Barradas wrote:
>>> Hello,
>>>
>>> You need to know what is the Levene test, that output is as clear as
>>> water. 75 + 283 == 358. Minus two groups gives 356.
>>> See
>>>
>>> http://en.wikipedia.org/wiki/Levene%27s_test
>>>
>>> Hope this helps,
>>>
>>>
>>> Em 21-06-2013 09:12, pieter escreveu:
>>>> Hey,
>>>> I don't really get the output of the performed Levene's test.
>>>> So in short.
>>>> two data sets, one with 75 elements, one with 283.
>>>> And I want to check whether they have the same variance.
>>>>
>>>> I did a LeveneTest
>>>> And this is the output:
>>>>
>>>> Levene's Test for Homogeneity of Variance (center = median)
>>>>          Df F value   Pr(>F)
>>>> group   1  10.948 0.001033 **
>>>>         356
>>>> ---
>>>> Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
>>>>
>>>> So I would think that H0 is being rejected? for everything except
>>>> 99.9%?
>>>> But what does the 356 mean?
>>>> Is this test performed correctly? group is a vector with 1's and 2's
>>>> appointing the two datasets...
>>>>
>>>>
>>>>
>>>>     [[alternative HTML version deleted]]
>>>>
>>>> ______________________________________________
>>>> R-help at r-project.org mailing list
>>>> https://stat.ethz.ch/mailman/listinfo/r-help
>>>> http://www.R-project.org/posting-guide.html
>>>> and provide commented, minimal, self-contained, reproducible code.
>>>>
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help