Question: EdgeR glm based analysis
0
gravatar for Gordon Smyth
5.9 years ago by
Gordon Smyth39k
Walter and Eliza Hall Institute of Medical Research, Melbourne, Australia
Gordon Smyth39k wrote:
Dear Reema, Yes, you can use the glm based analysis for two groups. The results will be similar to using the exact test, but the p-values will be based on an asymptotic approximation rather than being exact. Best wishes Gordon > Date: Tue, 31 Dec 2013 20:47:31 +0000 > From: Reema Singh <reema28sep at="" gmail.com=""> > To: bioconductor <bioconductor at="" r-project.org="">, Bioconductor mailing > list <bioconductor at="" stat.math.ethz.ch=""> > Subject: [BioC] EdgeR glm based analysis > > Dear All, > > First, wish you all a very happy and prosporous New Year. > > In EdgeR manual[Case Studies section], for two group comparison, generally > exactTest usage is shown, whereas for the multiple group comparison glm > based analysis has been shown. In 1.4 quick start section, use of glm based > analysis for two group comparison is mentioned with an additional use of > design matrix. > > Now my question :- Is it ok to use glm based analysis for two group > comparison? I would appreciate any suggestion. > > > Kind Regards > > > -- > Reema Singh > Postdoctoral Research Assistant > College of Life Sciences > University of Dundee, > Dundee DD1 4HN, Scotland > United Kingdom ______________________________________________________________________ The information in this email is confidential and intend...{{dropped:4}}
edger • 628 views
ADD COMMENTlink modified 5.9 years ago by Reema Singh570 • written 5.9 years ago by Gordon Smyth39k
Answer: EdgeR glm based analysis
0
gravatar for Reema Singh
5.9 years ago by
Reema Singh570
Reema Singh570 wrote:
Dear Prof. Smyth, Thankyou very much for the clasrification. Though, I would like to ask one more question regarding EdgeR. I want to known How to extract the normalized count using EdgeR?. I search though internet and found a reply by Mark ( https://stat.ethz.ch/pipermail/bioconductor/2012-July/046795.html) to use cpm for this purpose, Whereas some also suggest using pseudocount( http://www.biostars.org/p/54817/) and normalized value on lo2 scale( https://stat.ethz.ch/pipermail/bioconductor/2012-March/044311.html). I understand the cpm and log2 based normalizaed count, but couldn't exactly get the concept of pseudocount. So for extracting normalized count shall I go for cpm? Kind Regards On Thu, Jan 2, 2014 at 3:33 AM, Gordon K Smyth <smyth@wehi.edu.au> wrote: > Dear Reema, > > Yes, you can use the glm based analysis for two groups. The results will > be similar to using the exact test, but the p-values will be based on an > asymptotic approximation rather than being exact. > > Best wishes > Gordon > > Date: Tue, 31 Dec 2013 20:47:31 +0000 >> From: Reema Singh <reema28sep@gmail.com> >> To: bioconductor <bioconductor@r-project.org>, Bioconductor mailing >> list <bioconductor@stat.math.ethz.ch> >> Subject: [BioC] EdgeR glm based analysis >> >> Dear All, >> >> First, wish you all a very happy and prosporous New Year. >> >> In EdgeR manual[Case Studies section], for two group comparison, generally >> exactTest usage is shown, whereas for the multiple group comparison glm >> based analysis has been shown. In 1.4 quick start section, use of glm >> based >> analysis for two group comparison is mentioned with an additional use of >> design matrix. >> >> Now my question :- Is it ok to use glm based analysis for two group >> comparison? I would appreciate any suggestion. >> >> >> Kind Regards >> >> >> -- >> Reema Singh >> Postdoctoral Research Assistant >> College of Life Sciences >> University of Dundee, >> Dundee DD1 4HN, Scotland >> United Kingdom >> > > ______________________________________________________________________ > The information in this email is confidential and inte...{{dropped:20}}
ADD COMMENTlink written 5.9 years ago by Reema Singh570
See sections 2.5 (Normalization) and 2.10 of the edgeR User's Guide. Gordon PS. If you ask a new question, better to start a new thread with a new subject. On Thu, 2 Jan 2014, Reema Singh wrote: > Dear Prof. Smyth, > > Thankyou very much for the clasrification. > > Though, I would like to ask one more question regarding EdgeR. I want to > known How to extract the normalized count using EdgeR?. I search though > internet and found a reply by Mark ( > https://stat.ethz.ch/pipermail/bioconductor/2012-July/046795.html) to use > cpm for this purpose, Whereas some also suggest using pseudocount( > http://www.biostars.org/p/54817/) and normalized value on lo2 scale( > https://stat.ethz.ch/pipermail/bioconductor/2012-March/044311.html). I > understand the cpm and log2 based normalizaed count, but couldn't exactly > get the concept of pseudocount. > > So for extracting normalized count shall I go for cpm? > > Kind Regards > > > > > On Thu, Jan 2, 2014 at 3:33 AM, Gordon K Smyth <smyth at="" wehi.edu.au=""> wrote: > >> Dear Reema, >> >> Yes, you can use the glm based analysis for two groups. The results will >> be similar to using the exact test, but the p-values will be based on an >> asymptotic approximation rather than being exact. >> >> Best wishes >> Gordon >> >> Date: Tue, 31 Dec 2013 20:47:31 +0000 >>> From: Reema Singh <reema28sep at="" gmail.com=""> >>> To: bioconductor <bioconductor at="" r-project.org="">, Bioconductor mailing >>> list <bioconductor at="" stat.math.ethz.ch=""> >>> Subject: [BioC] EdgeR glm based analysis >>> >>> Dear All, >>> >>> First, wish you all a very happy and prosporous New Year. >>> >>> In EdgeR manual[Case Studies section], for two group comparison, generally >>> exactTest usage is shown, whereas for the multiple group comparison glm >>> based analysis has been shown. In 1.4 quick start section, use of glm >>> based >>> analysis for two group comparison is mentioned with an additional use of >>> design matrix. >>> >>> Now my question :- Is it ok to use glm based analysis for two group >>> comparison? I would appreciate any suggestion. >>> >>> >>> Kind Regards >>> >>> >>> -- >>> Reema Singh >>> Postdoctoral Research Assistant >>> College of Life Sciences >>> University of Dundee, >>> Dundee DD1 4HN, Scotland >>> United Kingdom >>> >> >> ______________________________________________________________________ >> The information in this email is confidential and intended solely for the >> addressee. >> You must not disclose, forward, print or use it without the permission of >> the sender. >> ______________________________________________________________________ >> > > > > -- > Reema Singh > Postdoctoral Research Assistant > College of Life Sciences > University of Dundee, > Dundee DD1 4HN, Scotland > United Kingdom > ______________________________________________________________________ The information in this email is confidential and intend...{{dropped:4}}
ADD REPLYlink written 5.9 years ago by Gordon Smyth39k
Dear Prof. Smyth, Thank you for the reply. I am really very sorry for asking new question in the this thread. Next time I will Keep this in mind. Kind Regards On Fri, Jan 3, 2014 at 4:05 AM, Gordon K Smyth <smyth@wehi.edu.au> wrote: > See sections 2.5 (Normalization) and 2.10 of the edgeR User's Guide. > > Gordon > > PS. If you ask a new question, better to start a new thread with a new > subject. > > > On Thu, 2 Jan 2014, Reema Singh wrote: > > Dear Prof. Smyth, >> >> Thankyou very much for the clasrification. >> >> Though, I would like to ask one more question regarding EdgeR. I want to >> known How to extract the normalized count using EdgeR?. I search though >> internet and found a reply by Mark ( >> https://stat.ethz.ch/pipermail/bioconductor/2012-July/046795.html) to use >> cpm for this purpose, Whereas some also suggest using pseudocount( >> http://www.biostars.org/p/54817/) and normalized value on lo2 scale( >> https://stat.ethz.ch/pipermail/bioconductor/2012-March/044311.html). I >> understand the cpm and log2 based normalizaed count, but couldn't exactly >> get the concept of pseudocount. >> >> So for extracting normalized count shall I go for cpm? >> >> Kind Regards >> >> >> >> >> On Thu, Jan 2, 2014 at 3:33 AM, Gordon K Smyth <smyth@wehi.edu.au> wrote: >> >> Dear Reema, >>> >>> Yes, you can use the glm based analysis for two groups. The results will >>> be similar to using the exact test, but the p-values will be based on an >>> asymptotic approximation rather than being exact. >>> >>> Best wishes >>> Gordon >>> >>> Date: Tue, 31 Dec 2013 20:47:31 +0000 >>> >>>> From: Reema Singh <reema28sep@gmail.com> >>>> To: bioconductor <bioconductor@r-project.org>, Bioconductor mailing >>>> list <bioconductor@stat.math.ethz.ch> >>>> Subject: [BioC] EdgeR glm based analysis >>>> >>>> Dear All, >>>> >>>> First, wish you all a very happy and prosporous New Year. >>>> >>>> In EdgeR manual[Case Studies section], for two group comparison, >>>> generally >>>> exactTest usage is shown, whereas for the multiple group comparison glm >>>> based analysis has been shown. In 1.4 quick start section, use of glm >>>> based >>>> analysis for two group comparison is mentioned with an additional use of >>>> design matrix. >>>> >>>> Now my question :- Is it ok to use glm based analysis for two group >>>> comparison? I would appreciate any suggestion. >>>> >>>> >>>> Kind Regards >>>> >>>> >>>> -- >>>> Reema Singh >>>> Postdoctoral Research Assistant >>>> College of Life Sciences >>>> University of Dundee, >>>> Dundee DD1 4HN, Scotland >>>> United Kingdom >>>> >>>> >>> ______________________________________________________________________ >>> The information in this email is confidential and intended solely for the >>> addressee. >>> You must not disclose, forward, print or use it without the permission of >>> the sender. >>> ______________________________________________________________________ >>> >>> >> >> >> -- >> Reema Singh >> Postdoctoral Research Assistant >> College of Life Sciences >> University of Dundee, >> Dundee DD1 4HN, Scotland >> United Kingdom >> >> > ______________________________________________________________________ > The information in this email is confidential and inte...{{dropped:20}}
ADD REPLYlink written 5.9 years ago by Reema Singh570
Please log in to add an answer.

Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 16.09
Traffic: 334 users visited in the last hour