## User: Storey, John D.

Reputation:
60
Status:
Trusted
Location:
United States
Last seen:
4 weeks ago
Joined:
5 years, 5 months ago
Email:
j******@princeton.edu

#### Posts by Storey, John D.

<prev • 13 results • page 1 of 2 • next >
0
78
views
0
... Estimating FDRs or q-values requires that p-values resulting from a true null hypothesis follow the Uniform(0,1) distribution, which is the usual requirement in hypothesis testing. If you have 129K p-values and the maximum p-value is 0.000352731, then this property is not true for your p-values. It ...
written 28 days ago by Storey, John D.60
3
620
views
3
... Since you have so few tests, I recommend using the lrt() function instead of odp() which will simply performs a t-test or F-test.  All you need to do is add lambda=0 as an argument and it will be passed to qvalue(): lrt(de_obj_TimeSeries, lambda=0) Setting lambda=0 yields the Benjamini-Hochberg ...
written 20 months ago by Storey, John D.60
3
620
views
3
... Since you have so few tests, I recommend using the lrt() function instead of odp() which will simply performs a t-test or F-test.  All you need to do is add lambda=0 as an argument and it will be passed to qvalue(): lrt(de_obj_TimeSeries, lambda=0) Setting lambda=0 yields the Benjamini-Hochberg e ...
written 20 months ago by Storey, John D.60
1
1.4k
views
1
... You don't have enough p-values to warrant estimating pi0, so include the argument lambda=0. ...
written 20 months ago by Storey, John D.60
2
440
views
2
... You're correct that q-values will eventually be smaller than p-values when pi0 < 1.  See: https://github.com/StoreyLab/qvalue#frequently-asked-questions There are finite sample results (meaning even for a small number of p-values) that show when the q-value estimates are conservative in Storey, ...
written 2.3 years ago by Storey, John D.60
1
988
views
1
... It's a red flag that your largest p-value 0.795.  The assumption is that true null p-values are Uniform(0,1), so the largest p-value should be close to 1 when this assumption is met and there are a reasonable number of tests being performed. From FAQ #1 (https://github.com/StoreyLab/qvalue/blob/mas ...
written 2.8 years ago by Storey, John D.60
2
2.6k
views
2
... Your error indicates there is a problem with the stringi package, which is not used by the qvalue package. ...
written 3.5 years ago by Storey, John D.60
2
752
views
2
Comment: C: Problem testing qvalue 2.0.0
... Please don't hesitate to ask any additional questions if you have them.  I recommend doing a clean installation of the latest version of qvalue from Bioconductor. ...
written 4.2 years ago by Storey, John D.60
2
752
views
2
... The code you use above isn't in the current vignette.  In version 2.0.0, the object hedenfalk is now a list.  Try: > library(qvalue) > data(hedenfalk) > ?hedenfalk > names(hedenfalk) [1] "p" "stat" "stat0" > length(hedenfalk$p) [1] 3170 > hist(hedenfalk$p)   ...
written 4.2 years ago by Storey, John D.60
4
1.5k
views
4
... I'm not the author of decideTests, so I'm not sure what it does.  However, qvalue can be used to determine significance cut-offs once p-values are obtained using the qvalue functions as demonstrated in the qvalue package's vignette.  With regards to q-values sometimes being smaller than p-values, th ...
written 4.4 years ago by Storey, John D.60

#### Latest awards to Storey, John D.

No awards yet. Soon to come :-)

Content
Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.