User: robert.maughan

Reputation:
0
Status:
New User
Last seen:
2 years, 11 months ago
Joined:
4 years, 5 months ago
Email:
r*************@ucdconnect.ie

Profile information, website and location are not shown for new users.

This helps us discourage the inappropriate use of our site.

Posts by robert.maughan

<prev • 7 results • page 1 of 1 • next >
0
votes
5
answers
2.7k
views
5
answers
Answer: A: LIMMA: interpreting interaction terms in an unbalanced factorial design with rep
... Apologies Aaron, I didn't get an email alert to this so didn't see your response. There are actually two covariates, baseline viral load and total cholesterol. Since there's a few analyses going on lets just take the example of 3 treatment groups with baseline and week 2 measurements. So the design ...
written 4.1 years ago by robert.maughan0
0
votes
5
answers
2.7k
views
5
answers
Answer: A: LIMMA: interpreting interaction terms in an unbalanced factorial design with rep
... Hi Aaron, I've opted for your suggested approach and I think it's serving me well, many thanks for that. I have another problem however. Since this is a non-randomised study there are continuous covariates which I would like to adjust/control for. From reading the support questions here, I've seen ...
written 4.1 years ago by robert.maughan0
0
votes
5
answers
2.7k
views
5
answers
Answer: A: LIMMA: interpreting interaction terms in an unbalanced factorial design with rep
... Many thanks Aaron, I'll go through what you've suggested and give it a try and will report back. Thanks, Rob ...
written 4.2 years ago by robert.maughan0
0
votes
5
answers
2.7k
views
5
answers
Answer: A: LIMMA: interpreting interaction terms in an unbalanced factorial design with rep
... Hi Aaron, Thanks for the helpful response. I absolutely agree that blocking for patient by actually including it in the model is a better approach than the duplicateCorrelation method. I believe that I went with duplicateCorrelation due to difficulties in getting a fullrank matrix. Also you're su ...
written 4.2 years ago by robert.maughan0
0
votes
5
answers
2.7k
views
5
answers
Comment: C: LIMMA: interpreting interaction terms in an unbalanced factorial design with rep
... Hi Aaron, Thanks for your reply. Yes you're correct that was an oversight on my part, at the end of the study we only had usable samples from 24 subjects although 25 were recruited. For simplicity's sake let's take the total number of subjects as 24. Again for the sake of the example I gave lets s ...
written 4.2 years ago by robert.maughan0
5
votes
5
answers
2.7k
views
5
answers
LIMMA: interpreting interaction terms in an unbalanced factorial design with repeated measures
... Dear all, I have searched for quite a while for questions relating to the following but couldn't find anything. I am trying to analyse gene expression data from quite a challenging study design. The study was a non-randomised study in which 25 subjects were treated with a combination of two drugs ...
0
votes
2
answers
2.1k
views
2
answers
Answer: A: RNAseq multifactor experiment limma design with patient and batch effects
... Hi Aaron,  I am struggling with a similar experimental setup as cfreije above. Following your suggested model above for estimating the differences within patients using: design <- model.matrix(~0+PatientID+Time:Disease,sample.metadata) design <- design[,-match(c("Time1:DiseaseA", "Time1:Di ...
written 4.5 years ago by robert.maughan0

Latest awards to robert.maughan


Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 16.09
Traffic: 317 users visited in the last hour