[R] Can I test if there are statistical significance between
(Ted Harding)
ted.harding at nessie.mcc.ac.uk
Sat Jul 21 15:51:55 CEST 2007
On 21Jul07 12:46:46, zhijie zhang wrote:
> Dear Uwe Ligges,
[restructuring the given layout of the data]
Grp1 Grp2 Grp3
Better 16 0 [ 1] 1  17

Good 71 4 [ 10] 6  81

Bad 37 61 [118] 57  155
+
124 65 [129] 64  253
> My hypothesis is if the three groups,that is group1, group2,and
> group3, have the same distributions on coloumns? If not, which
> one is difference from which one?
It is clear that there is no discernible difference between
Group 2 and Group 3. If they are pooled together (totals in
[...] above), it is also clear that there is a very large
difference between [Group 2 + Group 3], or either separately,
and Group 1.
In summary, and in round figures, Groups 2 and 3 have about
90% "Bad", about 10% "Good" and hardly any "Better".
Group 1 has only about 30% "Bad", about 60% "Good", and 10%
"Better".
Formally:
A<cbind(c(16,71,37),c(1,10,118))
A
[,1] [,2]
[1,] 16 1
[2,] 71 10
[3,] 37 118
chisq.test(A)
Pearson's Chisquared test
data: A
Xsquared = 101.4434, df = 2, pvalue = < 2.2e16
cbind(round(chisq.test(A)$expected,1),A)
[,1] [,2] [,3] [,4]
[1,] 8.3 8.7 16 1
[2,] 39.7 41.3 71 10
[3,] 76.0 79.0 37 118
B<cbind(c(0,4,61),c(1,6,57))
B
[,1] [,2]
[1,] 0 1
[2,] 4 6
[3,] 61 57
chisq.test(B,simulate.p.value=TRUE)
Pearson's Chisquared test with simulated pvalue
(based on 2000 replicates)
data: B
Xsquared = 1.5279, df = NA, pvalue = 0.3215
fisher.test(B)
Fisher's Exact Test for Count Data
data: B
pvalue = 0.4247
alternative hypothesis: two.sided
That, with possible refinements for more careful statements
about the proportions in the three outcome classes, is about
all one can say about these data; and it is definite enough!
With the totally noncommittal Pvalue for Group 2 vs Group 3,
and the absolutely decisive Pvalue for Group 1 vs Groups 2&3,
there is no need whatever to bother with "multiple comparison"
complications.
Best wishes,
Ted.
> On 7/20/07, Uwe Ligges <ligges at statistik.unidortmund.de> wrote:
>>
>>
>>
>> zhijie zhang wrote:
>> > Dear friends,
>> > My R*C table is as follow:
>> >
>> >
>> >
>> > better
>> >
>> > good
>> >
>> > bad
>> >
>> > Goup1
>> >
>> > 16
>> >
>> > 71
>> >
>> > 37
>> >
>> > Group2
>> >
>> > 0
>> >
>> > 4
>> >
>> > 61
>> >
>> > Group3
>> >
>> > 1
>> >
>> > 6
>> >
>> > 57
>> >
>> > Can I test if there are statistical significant between Group1
>> > and
>> > Group2, Group2 and Group3, Group1 and Group2, taking into the
>> > multiple
>> > comparisons?
>>
>>
>> So what is you hypothesis? Statistical significance of what it to be
>> tested?
>>
>> Uwe Ligges
>>
>>
>>
>> > The table can be set up using the following program:
>> >
>> > a<matrix(data=c(16,71,37,0,4,61,1,6,57),nrow=3,byrow=TRUE)
>> > Thanks very much.
>> >
>> >
>>
>
>
>
> 
> With Kind Regards,
>
> oooO:::::::::
> (..):::::::::
>:\.(:::Oooo::
>::\_)::(..)::
>:::::::)./:::
>::::::(_/::::
>:::::::::::::
> [***********************************************************************
> ]
> Zhi Jie,Zhang ,PHD
> Tel:862154237149
> Dept. of Epidemiology,School of Public Health,Fudan University
> Address:No. 138 Yi Xue Yuan Road,Shanghai,China
> Postcode:200032
> Email:epistat at gmail.com
> Website: www.statABC.com
> [***********************************************************************
> ]
> oooO:::::::::
> (..):::::::::
> :\.(:::Oooo::
> ::\_)::(..)::
> :::::::)./:::
> ::::::(_/::::
> :::::::::::::

EMail: (Ted Harding) <ted.harding at nessie.mcc.ac.uk>
Faxtoemail: +44 (0)870 094 0861
Date: 21Jul07 Time: 14:51:46
 XFMail 
More information about the Rhelp
mailing list