Re: [R] gsDesign Pocock & OBF boundary
Sorry it didn 't work again. I am on yahoo mail, and just found a switch to change from Rick text to Plain text, so here it goes again: I am learning to use the gsDesign package. I have a question about Pocock and OBF boundary. As far as I can understand, these 2 boundaries require equal spacing between interim analyses (maybe this is not correct?). But looks like I can still use gsDesign to run an analysis based on unequal spacing: > library(gsDesign) > gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock') Symmetric two-sided group sequential design with 90 % power and 5 % Type I Error. Spending computations assume trial stops if a bound is crossed. Sample Size Analysis Ratio* Z Nominal p Spend 1 0.796 1.82 0.0346 0.0346 2 1.061 1.82 0.0346 0.0154 Total 0.0500 ++ alpha spending: Pocock boundary. * Sample size ratio compared to fixed design with no interim Can anyone share some light whether the above analysis is still valid? Or for unequal spacing, I have to use Lan-Demet’s error spending function approximations? Thank you, From: Jeff Newmiller <jdnew...@dcn.davis.ca.us> oject.org>; Berend Hasselman <b...@xs4all.nl> Cc: R-help Mailing List <r-help@r-project.org> Sent: Sunday, September 24, 2017 12:41 AM Subject: Re: [R] gsDesign Pocock & OBF boundary Still failed. The first secret is in your email program settings, to use Plain Text format (at least for emails you send to this mailing list). The second secret tool to use is the reprex package to let you verify that your code example will do on our computers what it is doing on your computer before you send it to us. That will also involve giving us some sample data or referencing some data already available to us in a relevant package. See [1], [2] and [3] for more discussion of how to succeed at communicating on the Internet regarding R. [1] http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example [2] http://adv-r.had.co.nz/Reproducibility.html [3] https://cran.r-project.org/web/packages/reprex/index.html (read the vignette) -- Sent from my phone. Please excuse my brevity. On September 23, 2017 9:53:05 PM PDT, array chip via R-help <r-help@r-project.org> wrote: >Sorry for messed up text. Here it goes again: >I am learning to use the gsDesign package. >I have a question about Pocock and OBF boundary. As far as I can >understand, these 2 boundaries require equal spacing between interim >analyses (maybe this is not correct?). But looks like I can still use >gsDesign to run an analysis based on unequal spacing: >> gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock') >Symmetric two-sided group sequential design with 90 %power and 5 % Type >I Error.Spending computations assume trial stops if a bound is >crossed. Sample Size Analysis Ratio* Z Nominal p >Spend1 0.796 1.820.0346 0.03462 1.061 1.82 >0.0346 0.0154Total 0.0500 ++alpha spending: >Pocock boundary.*Sample size ratio compared to fixed design with no >interim >Can anyone share some light whether the above analysis is still valid? >Or for unequal spacing, I have to use Lan-Demet’s error spending >function approximations? Thank you, > > > > From: Berend Hasselman <b...@xs4all.nl> >Cc: R-help Mailing List <r-help@r-project.org> > Sent: Friday, September 22, 2017 11:46 PM > Subject: Re: [R] gsDesign Pocock & OBF boundary > > >> On 23 Sep 2017, at 01:32, array chip via R-help ><r-help@r-project.org> wrote: >> >> Hi, >> >> I am learning to use your gsDesign package! I have a question about >Pocock and OBF boundary. As far as Iunderstand, these 2 boundaries >require equal spacing between interim analyses(maybe this is not >correct?). But I can still use gsDesign to run an analysisbased on >unequal spacing: >gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock')Symmetrictwo-sided >group sequential design with90 %power and 5 % Type I >Error.Spendingcomputations assume trial stops if a bound is crossed. > Sample Size AnalysisRatio* Z Nominal p Spend >1 0.796 1.820.0346 0.03462 1.061 1.820.0346 0.0154 >Total 0.0500 ++alpha >spending:Pocockboundary.*Sample size ratio compared to fixed design >with no interim Can anyone share some light whether the above analysis >is stillvalid? Or for unequal spacing, I have to use Lan-Demet’s error >spendingfunction approximations? Thank you, >> [[alternative HTML version deleted]] >> > >Your example code is a complete mess. >Do NOT post in html. This is a pl
Re: [R] gsDesign Pocock & OBF boundary
Still failed. The first secret is in your email program settings, to use Plain Text format (at least for emails you send to this mailing list). The second secret tool to use is the reprex package to let you verify that your code example will do on our computers what it is doing on your computer before you send it to us. That will also involve giving us some sample data or referencing some data already available to us in a relevant package. See [1], [2] and [3] for more discussion of how to succeed at communicating on the Internet regarding R. [1] http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example [2] http://adv-r.had.co.nz/Reproducibility.html [3] https://cran.r-project.org/web/packages/reprex/index.html (read the vignette) -- Sent from my phone. Please excuse my brevity. On September 23, 2017 9:53:05 PM PDT, array chip via R-help <r-help@r-project.org> wrote: >Sorry for messed up text. Here it goes again: >I am learning to use the gsDesign package. >I have a question about Pocock and OBF boundary. As far as I can >understand, these 2 boundaries require equal spacing between interim >analyses (maybe this is not correct?). But looks like I can still use >gsDesign to run an analysis based on unequal spacing: >> gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock') >Symmetric two-sided group sequential design with 90 %power and 5 % Type >I Error.Spending computations assume trial stops if a bound is >crossed. Sample Size Analysis Ratio* Z Nominal p >Spend 1 0.796 1.82 0.0346 0.0346 2 1.061 1.82 >0.0346 0.0154 Total 0.0500 ++alpha spending: >Pocock boundary.*Sample size ratio compared to fixed design with no >interim >Can anyone share some light whether the above analysis is still valid? >Or for unequal spacing, I have to use Lan-Demet’s error spending >function approximations? Thank you, > > > > From: Berend Hasselman <b...@xs4all.nl> > To: array chip <arrayprof...@yahoo.com> >Cc: R-help Mailing List <r-help@r-project.org> > Sent: Friday, September 22, 2017 11:46 PM > Subject: Re: [R] gsDesign Pocock & OBF boundary > > >> On 23 Sep 2017, at 01:32, array chip via R-help ><r-help@r-project.org> wrote: >> >> Hi, >> >> I am learning to use your gsDesign package! I have a question about >Pocock and OBF boundary. As far as Iunderstand, these 2 boundaries >require equal spacing between interim analyses(maybe this is not >correct?). But I can still use gsDesign to run an analysisbased on >unequal spacing: >gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock')Symmetrictwo-sided >group sequential design with90 %power and 5 % Type I >Error.Spendingcomputations assume trial stops if a bound is crossed. > Sample Size AnalysisRatio* Z Nominal p Spend >1 0.796 1.82 0.0346 0.0346 2 1.061 1.82 0.0346 0.0154 >Total 0.0500 ++alpha >spending:Pocockboundary.*Sample size ratio compared to fixed design >with no interim Can anyone share some light whether the above analysis >is stillvalid? Or for unequal spacing, I have to use Lan-Demet’s error >spendingfunction approximations? Thank you, >> [[alternative HTML version deleted]] >> > >Your example code is a complete mess. >Do NOT post in html. This is a plain text mailing list. >Read the Posting Guide (https://www.r-project.org/posting-guide.html). > >Berend Hasselman] > >> __ >> R-help@r-project.org 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. > > > > [[alternative HTML version deleted]] > >__ >R-help@r-project.org 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. __ R-help@r-project.org 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.
Re: [R] gsDesign Pocock & OBF boundary
Sorry for messed up text. Here it goes again: I am learning to use the gsDesign package. I have a question about Pocock and OBF boundary. As far as I can understand, these 2 boundaries require equal spacing between interim analyses (maybe this is not correct?). But looks like I can still use gsDesign to run an analysis based on unequal spacing: > gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock') Symmetric two-sided group sequential design with 90 %power and 5 % Type I Error.Spending computations assume trial stops if a bound is crossed. Sample Size Analysis Ratio* Z Nominal p Spend 1 0.796 1.82 0.0346 0.0346 2 1.061 1.82 0.0346 0.0154 Total 0.0500 ++alpha spending: Pocock boundary.*Sample size ratio compared to fixed design with no interim Can anyone share some light whether the above analysis is still valid? Or for unequal spacing, I have to use Lan-Demet’s error spending function approximations? Thank you, From: Berend Hasselman <b...@xs4all.nl> To: array chip <arrayprof...@yahoo.com> Cc: R-help Mailing List <r-help@r-project.org> Sent: Friday, September 22, 2017 11:46 PM Subject: Re: [R] gsDesign Pocock & OBF boundary > On 23 Sep 2017, at 01:32, array chip via R-help <r-help@r-project.org> wrote: > > Hi, > > I am learning to use your gsDesign package! I have a question about Pocock > and OBF boundary. As far as Iunderstand, these 2 boundaries require equal > spacing between interim analyses(maybe this is not correct?). But I can still > use gsDesign to run an analysisbased on unequal spacing: > gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock')Symmetrictwo-sided > group sequential design with90 %power and 5 % Type I > Error.Spendingcomputations assume trial stops if a bound is crossed. > Sample Size AnalysisRatio* Z Nominal p Spend 1 0.796 > 1.82 0.0346 0.0346 2 1.061 1.82 0.0346 0.0154 Total > 0.0500 ++alpha spending:Pocockboundary.*Sample size ratio > compared to fixed design with no interim Can anyone share some light whether > the above analysis is stillvalid? Or for unequal spacing, I have to use > Lan-Demet’s error spendingfunction approximations? Thank you, > [[alternative HTML version deleted]] > Your example code is a complete mess. Do NOT post in html. This is a plain text mailing list. Read the Posting Guide (https://www.r-project.org/posting-guide.html). Berend Hasselman] > __ > R-help@r-project.org 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. [[alternative HTML version deleted]] __ R-help@r-project.org 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.
Re: [R] gsDesign Pocock & OBF boundary
> On 23 Sep 2017, at 01:32, array chip via R-helpwrote: > > Hi, > > I am learning to use your gsDesign package! I have a question about Pocock > and OBF boundary. As far as Iunderstand, these 2 boundaries require equal > spacing between interim analyses(maybe this is not correct?). But I can still > use gsDesign to run an analysisbased on unequal spacing: > gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock')Symmetrictwo-sided > group sequential design with90 %power and 5 % Type I > Error.Spendingcomputations assume trial stops if a bound is crossed. > Sample Size AnalysisRatio* Z Nominal p Spend1 0.796 > 1.820.0346 0.03462 1.061 1.820.0346 0.0154Total > 0.0500 ++alpha spending:Pocockboundary.*Sample size ratio > compared to fixed design with no interim Can anyone share some light whether > the above analysis is stillvalid? Or for unequal spacing, I have to use > Lan-Demet’s error spendingfunction approximations? Thank you, > [[alternative HTML version deleted]] > Your example code is a complete mess. Do NOT post in html. This is a plain text mailing list. Read the Posting Guide (https://www.r-project.org/posting-guide.html). Berend Hasselman] > __ > R-help@r-project.org 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. __ R-help@r-project.org 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.
[R] gsDesign Pocock & OBF boundary
Hi, I am learning to use your gsDesign package! I have a question about Pocock and OBF boundary. As far as Iunderstand, these 2 boundaries require equal spacing between interim analyses(maybe this is not correct?). But I can still use gsDesign to run an analysisbased on unequal spacing: gsDesign(k=2,test.type=2,timing=c(0.75,1),alpha=0.05,sfu='Pocock')Symmetrictwo-sided group sequential design with90 %power and 5 % Type I Error.Spendingcomputations assume trial stops if a bound is crossed. Sample Size AnalysisRatio* Z Nominal p Spend1 0.796 1.82 0.0346 0.03462 1.061 1.82 0.0346 0.0154Total 0.0500 ++alpha spending:Pocockboundary.*Sample size ratio compared to fixed design with no interim Can anyone share some light whether the above analysis is stillvalid? Or for unequal spacing, I have to use Lan-Demet’s error spendingfunction approximations? Thank you, [[alternative HTML version deleted]] __ R-help@r-project.org 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.
Re: [R] gsDesign
Hi Dongli, Questions about usage of specific contributed packages are best directed toward the package maintainer/author first, as they are likely the best sources of information, and they don't necessarily subscribe to or keep up with the daily deluge of R-help messages. (In this particular case, I'm quite sure the package maintainer for gsDesign doesn't keep up with R-help.) Best, Andy -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Dongli Zhou Sent: Monday, November 14, 2011 6:13 PM To: Marc Schwartz Cc: r-help@r-project.org Subject: Re: [R] gsDesign Hi, Marc, Thank you very much for the reply. I'm using the gsDesign function to create an object of type gsDesign. But the inputs do not include the 'ratio' argument. Dongli On Nov 14, 2011, at 5:50 PM, Marc Schwartz marc_schwa...@me.com wrote: On Nov 14, 2011, at 4:11 PM, Dongli Zhou wrote: I'm trying to use gsDesign for a noninferiority trial with binary endpoint. Did anyone know how to specify the trial with different sample sizes for two treatment groups? Thanks in advance! Hi, Presuming that you are using the nBinomial() function, see the 'ratio' argument, which defines the desired sample size ratio between the two groups. See ?nBinomial and the examples there, which does include one using the 'ratio' argument. HTH, Marc Schwartz __ R-help@r-project.org mailing list 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. Notice: This e-mail message, together with any attachme...{{dropped:11}} __ R-help@r-project.org mailing list 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.
Re: [R] gsDesign
Hi Dongli, Sorry for the delay in following up. You might want to read the dsDesignManual.pdf document, which is available in the 'inst/doc' folder in the package source tarball on CRAN, or in the package 'doc' directory in your R installation. Use: system.file(package = gsDesign) to get the package top directory for your installation. The above file will be in the 'doc' sub-directory from there. It has more extensive worked examples than the default package manual. Simple non-inferiority example from ?nBinomial, with 2:1 ratio: n.Fix - nBinomial(p1 = .677, p2 = .677, delta0 = 0.07, ratio = 2) n.Fix [1] 2056.671 # Adjust that *up* to an integer multiple of 3 n.Fix - 2058 # Change 'outtype' to 2 if you want to see per arm sample sizes # eg: nBinomial(p1 = .677, p2 = .677, delta0 = 0.07, ratio = 2, outtype = 2) $n1 [1] 685.5569 $n2 [1] 1371.114 # Simple default GS design using the fixed study design sample size from above, # which is not yet adjusted for interim analyses gsDesign(n.fix = n.Fix) Asymmetric two-sided group sequential design with 90 % power and 2.5 % Type I Error. Upper bound spending computations assume trial continues if lower bound is crossed. Lower bounds Upper bounds- Analysis NZ Nominal p Spend+ Z Nominal p Spend++ 1 734 -0.240.4057 0.0148 3.010.0013 0.0013 2 1468 0.940.8267 0.0289 2.550.0054 0.0049 3 2202 2.000.9772 0.0563 2.000.0228 0.0188 Total 0.1000 0.0250 + lower bound beta spending (under H1): Hwang-Shih-DeCani spending function with gamma = -2 ++ alpha spending: Hwang-Shih-DeCani spending function with gamma = -4 Boundary crossing probabilities and expected sample size assume any cross stops the trial Upper boundary (power or Type I Error) Analysis Theta 1 2 3 Total E{N} 0. 0.0013 0.0049 0.0171 0.0233 1286.0 0.0715 0.1412 0.4403 0.3185 0.9000 1628.4 Lower boundary (futility or Type II Error) Analysis Theta 1 2 3 Total 0. 0.4057 0.4290 0.1420 0.9767 0.0715 0.0148 0.0289 0.0563 0.1000 So rather than needing 2058 from the fixed design, you actually need 2202 (1468 in one arm and 734 in the other). I would urge you to read the manual I reference above and as Andy has noted in his reply, contact Keaven directly for further assistance with this package. HTH, Marc On Nov 14, 2011, at 5:13 PM, Dongli Zhou wrote: Hi, Marc, Thank you very much for the reply. I'm using the gsDesign function to create an object of type gsDesign. But the inputs do not include the 'ratio' argument. Dongli On Nov 14, 2011, at 5:50 PM, Marc Schwartz marc_schwa...@me.com wrote: On Nov 14, 2011, at 4:11 PM, Dongli Zhou wrote: I'm trying to use gsDesign for a noninferiority trial with binary endpoint. Did anyone know how to specify the trial with different sample sizes for two treatment groups? Thanks in advance! Hi, Presuming that you are using the nBinomial() function, see the 'ratio' argument, which defines the desired sample size ratio between the two groups. See ?nBinomial and the examples there, which does include one using the 'ratio' argument. HTH, Marc Schwartz __ R-help@r-project.org mailing list 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.
Re: [R] gsDesign
Thank you so much for the help! It is really appreciated! Dongli On Nov 15, 2011, at 9:19 AM, Marc Schwartz marc_schwa...@me.com wrote: Hi Dongli, Sorry for the delay in following up. You might want to read the dsDesignManual.pdf document, which is available in the 'inst/doc' folder in the package source tarball on CRAN, or in the package 'doc' directory in your R installation. Use: system.file(package = gsDesign) to get the package top directory for your installation. The above file will be in the 'doc' sub-directory from there. It has more extensive worked examples than the default package manual. Simple non-inferiority example from ?nBinomial, with 2:1 ratio: n.Fix - nBinomial(p1 = .677, p2 = .677, delta0 = 0.07, ratio = 2) n.Fix [1] 2056.671 # Adjust that *up* to an integer multiple of 3 n.Fix - 2058 # Change 'outtype' to 2 if you want to see per arm sample sizes # eg: nBinomial(p1 = .677, p2 = .677, delta0 = 0.07, ratio = 2, outtype = 2) $n1 [1] 685.5569 $n2 [1] 1371.114 # Simple default GS design using the fixed study design sample size from above, # which is not yet adjusted for interim analyses gsDesign(n.fix = n.Fix) Asymmetric two-sided group sequential design with 90 % power and 2.5 % Type I Error. Upper bound spending computations assume trial continues if lower bound is crossed. Lower bounds Upper bounds- Analysis NZ Nominal p Spend+ Z Nominal p Spend++ 1 734 -0.240.4057 0.0148 3.010.0013 0.0013 2 1468 0.940.8267 0.0289 2.550.0054 0.0049 3 2202 2.000.9772 0.0563 2.000.0228 0.0188 Total 0.1000 0.0250 + lower bound beta spending (under H1): Hwang-Shih-DeCani spending function with gamma = -2 ++ alpha spending: Hwang-Shih-DeCani spending function with gamma = -4 Boundary crossing probabilities and expected sample size assume any cross stops the trial Upper boundary (power or Type I Error) Analysis Theta 1 2 3 Total E{N} 0. 0.0013 0.0049 0.0171 0.0233 1286.0 0.0715 0.1412 0.4403 0.3185 0.9000 1628.4 Lower boundary (futility or Type II Error) Analysis Theta 1 2 3 Total 0. 0.4057 0.4290 0.1420 0.9767 0.0715 0.0148 0.0289 0.0563 0.1000 So rather than needing 2058 from the fixed design, you actually need 2202 (1468 in one arm and 734 in the other). I would urge you to read the manual I reference above and as Andy has noted in his reply, contact Keaven directly for further assistance with this package. HTH, Marc On Nov 14, 2011, at 5:13 PM, Dongli Zhou wrote: Hi, Marc, Thank you very much for the reply. I'm using the gsDesign function to create an object of type gsDesign. But the inputs do not include the 'ratio' argument. Dongli On Nov 14, 2011, at 5:50 PM, Marc Schwartz marc_schwa...@me.com wrote: On Nov 14, 2011, at 4:11 PM, Dongli Zhou wrote: I'm trying to use gsDesign for a noninferiority trial with binary endpoint. Did anyone know how to specify the trial with different sample sizes for two treatment groups? Thanks in advance! Hi, Presuming that you are using the nBinomial() function, see the 'ratio' argument, which defines the desired sample size ratio between the two groups. See ?nBinomial and the examples there, which does include one using the 'ratio' argument. HTH, Marc Schwartz __ R-help@r-project.org mailing list 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.
[R] gsDesign
I'm trying to use gsDesign for a noninferiority trial with binary endpoint. Did anyone know how to specify the trial with different sample sizes for two treatment groups? Thanks in advance! [[alternative HTML version deleted]] __ R-help@r-project.org mailing list 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.
Re: [R] gsDesign
On Nov 14, 2011, at 4:11 PM, Dongli Zhou wrote: I'm trying to use gsDesign for a noninferiority trial with binary endpoint. Did anyone know how to specify the trial with different sample sizes for two treatment groups? Thanks in advance! Hi, Presuming that you are using the nBinomial() function, see the 'ratio' argument, which defines the desired sample size ratio between the two groups. See ?nBinomial and the examples there, which does include one using the 'ratio' argument. HTH, Marc Schwartz __ R-help@r-project.org mailing list 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.
Re: [R] gsDesign
Hi, Marc, Thank you very much for the reply. I'm using the gsDesign function to create an object of type gsDesign. But the inputs do not include the 'ratio' argument. Dongli On Nov 14, 2011, at 5:50 PM, Marc Schwartz marc_schwa...@me.com wrote: On Nov 14, 2011, at 4:11 PM, Dongli Zhou wrote: I'm trying to use gsDesign for a noninferiority trial with binary endpoint. Did anyone know how to specify the trial with different sample sizes for two treatment groups? Thanks in advance! Hi, Presuming that you are using the nBinomial() function, see the 'ratio' argument, which defines the desired sample size ratio between the two groups. See ?nBinomial and the examples there, which does include one using the 'ratio' argument. HTH, Marc Schwartz __ R-help@r-project.org mailing list 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.