Notice: On March 31, it was **announced** that Statalist is moving from an email list to a **forum**. The old list will shut down on April 23, and its replacement, **statalist.org** is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
ymarchenko@stata.com (Yulia Marchenko, StataCorp LP) |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: st: AW: Artmenu fails to load in Stata 11 |

Date |
Tue, 18 May 2010 16:59:16 -0500 |

Jonathan Kaplan <kaplan.joe@gmail.com> asks how to reproduce a power-curve graph depicted on the Stata website: > I am trying to reproduce the graph displayed in: > > http://www.stata.com/stata10/poweranalysis.html > > I'm able to reproduce the basic data using > > . stpower logrank 0.7, n(100 250 500) hratio(0.1(0.01)0.9) saving(mypower) > > However I cannot figure the correct syntax to produce the graph. Martin Weiss <martin.weiss1@gmx.de> showed a manual way of obtaining a graph after -stpower- (http://www.stata.com/statalist/archive/2010-05/msg01016.html). Jonathan can also use the unofficial command -stpowplot- to obtain power curves for the log-rank test more easily. For example, . stpowplot logrank 0.7, yaxis(power) xaxis(hr) over(n) /// n(100 250 500) hratio(0.1(0.01)0.9) will produce a graph similar to that displayed on the webpage. Following Martin's suggestions, Jonathan can customize the graph to obtain a closer match: /*** begin example ****/ local title Power curves for log-rank test local subtitle (for survival curves of experimental vs. standard treatment) local note1 Assumptions: alpha = 0.05 (two sided); equal number of subjects local note1 `note1' to be assigned to each group; local note2 70% of patients in the control group survive to the end of the study local xtitle Hypothesized effect size (hazard ratio of experimentals vs. controls) stpowplot logrank 0.7, yaxis(power) xaxis(hr) over(n) /// n(100 250 500) hratio(0.1(0.01)0.9) /// title(`title') subtitle(`subtitle') /// note("`note1'" "`note2'") /// xtitle(`xtitle') yline(0.8, lstyle(refline)) /// legend(off) text(.65 .4 "N = 100") /// text(.65 .6 "N = 250") text(.65 .75 "N = 500") /*** end example ****/ Type . findit stpowplot to locate and install this command. -- Yulia ymarchenko@stata.com * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**Follow-Ups**:**RE: st: AW: Artmenu fails to load in Stata 11***From:*"Martin Weiss" <martin.weiss1@gmx.de>

- Prev by Date:
**Re: st: observations differ with lrtest because of interaction terms** - Next by Date:
**RE: st: AW: Artmenu fails to load in Stata 11** - Previous by thread:
**st: st : Pedroni Test** - Next by thread:
**RE: st: AW: Artmenu fails to load in Stata 11** - Index(es):