comparing variances/distributions

classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

comparing variances/distributions

anikaM
Hello,

I have p values from two distributions, Pold and Pnew
> head(m)
   CHR     POS     MARKER   Pnew   Pold
1:   1  785989  rs2980300 0.1419 0.9521
2:   1 1130727 rs10907175 0.1022 0.4750
3:   1 1156131  rs2887286 0.3698 0.5289
4:   1 1158631  rs6603781 0.1929 0.2554
5:   1 1211292  rs6685064 0.6054 0.2954
6:   1 1478153  rs3766180 0.6511 0.5542
...

In order to compare those two distributions (QQ plots shown in attach)
does it make sense to use:

var.test(m$Pold, m$Pnew, alternative = "two.sided")

    F test to compare two variances

data:  m$Pold and m$Pnew
F = 0.99937, num df = 1454159, denom df = 1454159, p-value = 0.7057
alternative hypothesis: true ratio of variances is not equal to 1
95 percent confidence interval:
 0.9970808 1.0016750
sample estimates:
ratio of variances
         0.9993739


Or some other test makes more sense?

Thanks
Ana

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.

qq-plots.pdf (355K) Download Attachment
Reply | Threaded
Open this post in threaded view
|

Re: comparing variances/distributions

Michael Dewey-3
Dear Ana

This really depends on your scientific question. The two techniques you
have shown do different things and there must be many more which could
be applied.

Michael

On 17/06/2020 20:57, Ana Marija wrote:

> Hello,
>
> I have p values from two distributions, Pold and Pnew
>> head(m)
>     CHR     POS     MARKER   Pnew   Pold
> 1:   1  785989  rs2980300 0.1419 0.9521
> 2:   1 1130727 rs10907175 0.1022 0.4750
> 3:   1 1156131  rs2887286 0.3698 0.5289
> 4:   1 1158631  rs6603781 0.1929 0.2554
> 5:   1 1211292  rs6685064 0.6054 0.2954
> 6:   1 1478153  rs3766180 0.6511 0.5542
> ...
>
> In order to compare those two distributions (QQ plots shown in attach)
> does it make sense to use:
>
> var.test(m$Pold, m$Pnew, alternative = "two.sided")
>
>      F test to compare two variances
>
> data:  m$Pold and m$Pnew
> F = 0.99937, num df = 1454159, denom df = 1454159, p-value = 0.7057
> alternative hypothesis: true ratio of variances is not equal to 1
> 95 percent confidence interval:
>   0.9970808 1.0016750
> sample estimates:
> ratio of variances
>           0.9993739
>
>
> Or some other test makes more sense?
>
> Thanks
> Ana
>
>
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> 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.
>

--
Michael
http://www.dewey.myzen.co.uk/home.html

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
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.