- 1. bootstrap difference in means (score: 1)
- Author: "Bernd Puschner" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Wed, 2 Jun 2004 15:39:45 +0200
- Dear S-PLUS users, it is straightforward to bootstrap a mean, but I can't bootstrap a difference of means (same variable, two groups of different N), supposedly just because because the groups are no
- /archives/html/s-news/2004-06/msg00008.html (6,695 bytes)
- 2. skewed distribution in lme (score: 1)
- Author: "Bernd Puschner" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Wed, 5 May 2004 09:56:22 +0200
- Dear S+ users, with version 6.0, I calculated a lme model on course of patient satisfaction using an unbalanced data set (2.267 observations of 654 subjects): zuf.lme <- lme(data = zuf, random = ~tim
- /archives/html/s-news/2004-05/msg00023.html (6,983 bytes)
- 3. testing random effects (score: 1)
- Author: "Bernd Puschner" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Mon, 10 May 2004 14:16:01 +0200
- Dear S-Plus users, in a lme model, how can I test random effects for significance? In model summary, I only get e.g. StdDev Corr (Intercept) 0.48741379 (Inter time 0.01109815 -0.229 Residual 0.295018
- /archives/html/s-news/2004-05/msg00038.html (6,696 bytes)
- 4. Structural Equation Modeling in S Plus (score: 1)
- Author: "Bernd Puschner" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Fri, 26 Mar 2004 11:30:38 +0100
- Dear S-Plus users, a long time ago someone asked about structural equation modelling in S-Plus (see below), no one anwered. Any news on this? Thanks Bernd -- To: s-news@wubios.wustl.edu Subject: [S]
- /archives/html/s-news/2004-03/msg00202.html (6,985 bytes)
- 5. summary " Structural Equation Modeling in S+" (score: 1)
- Author: "Bernd Puschner" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Mon, 29 Mar 2004 12:46:27 +0200
- Dear S+ users, thanks to Dimitris Rizopoulos, John Fox, Harry Southworth, Bill Shipley, and Spencer Graves. They all pointed to John's SEM package (sem) in R with which I will try my luck. Bernd
- /archives/html/s-news/2004-03/msg00234.html (6,610 bytes)
- 6. t (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Wed, 28 Jan 2004 11:17:10 +0100
- Dear S-Plus users, we are planning a multicenter randomized clinical trial on the effect of a new discharge planning protocol (primary outcome rehospitalization) in patients suffering from schizophre
- /archives/html/s-news/2004-01/msg00158.html (7,568 bytes)
- 7. time-variant predictor in lme (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Wed, 19 Nov 2003 13:14:08 +0100
- e
- /archives/html/s-news/2003-11/msg00119.html (8,853 bytes)
- 8. meaning of p-value in lme (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Fri, 12 Sep 2003 10:35:17 +0200
- dear s-plus users, probably stupid question: in a lme-model (unbalanced longitudinal data: oqsd is symptom distress measured repeatedly over two years and in.therm is time in psychotherapy at each me
- /archives/html/s-news/2003-09/msg00070.html (7,618 bytes)
- 9. summary lme (intercept) and new question (df in lme) (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Mon, 15 Sep 2003 16:51:59 +0200
- dear s-plus users, thanks to douglas bates, bert gunter, and manuela huso for answering my question about the meaning of the intercept's p-value in lme. the answer is: The p-value is for the (margina
- /archives/html/s-news/2003-09/msg00094.html (8,480 bytes)
- 10. no p-values (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Wed, 16 Jul 2003 15:15:53 +0200
- dear s-plus users, when computing a logistic regression model, either via glm or menuBinomialGlm, the summary of the model provides coefficients and their standard errors and t-values, but for some r
- /archives/html/s-news/2003-07/msg00111.html (7,196 bytes)
- 11. summary "no p-values" (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Fri, 18 Jul 2003 13:07:13 +0200
- dear s-plus users, thanks to brian ripley, hugh jones, spencer graves, pedram sendi, and harry southworth for taking time to answer my question. prof. ripley wrote: There is a very good reason! t-val
- /archives/html/s-news/2003-07/msg00133.html (7,786 bytes)
- 12. lag down (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Mon, 16 Jun 2003 16:20:53 +0200
- dear s-plus users, can't figure out a solution to a simple problem. i have a data frame with one observation (x) per subject (id) id x 1 2 1 NA 2 1 2 NA 3 2 3 NA how do i "lag down" the observation p
- /archives/html/s-news/2003-06/msg00094.html (6,923 bytes)
- 13. summary lag down (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Tue, 17 Jun 2003 10:58:04 +0200
- thanks a lot to sundar, dimitris, brad, ted, james, peng, and peter. i tried all the answers (see below, some comments included). bernd data <- data.frame(id=rep(1:10, each=2), x=sample(1:10, 20, rep
- /archives/html/s-news/2003-06/msg00106.html (9,296 bytes)
- 14. acceptability curves (score: 1)
- Author: "Bernd Puschner" <bernd.puschner@bkh-guenzburg.de>
- Date: Wed, 14 May 2003 12:06:29 +0100
- l
- /archives/html/s-news/2003-05/msg00055.html (6,588 bytes)
- 15. interaction in lme (score: 1)
- Author: "Puschner, Bernd" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Tue, 22 May 2007 11:08:55 +0200
- Dear all, I have a lme model with in.studm = time since beginning of observation, and sc10m = psychological impairment. I want to know the interaction of phase1f (factor 0,1) and anf.kosm (continuous
- /archives/html/s-news/2007-05/msg00021.html (7,733 bytes)
- 16. cluster in lme (score: 1)
- Author: "Puschner, Bernd" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Fri, 27 Jul 2007 11:44:20 +0200
- dear all, i am analyzing data of a cluster-randomized trial via lme. when calling a.lme <- lme(data = emm.stat, random = ~weeks | code, fixed = v6.a ~ weeks * as.factor(group.fi), na.action = na.omit
- /archives/html/s-news/2007-07/msg00032.html (6,668 bytes)
- 17. Re: cluster in lme (score: 1)
- Author: "Puschner, Bernd" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Wed, 31 Oct 2007 16:35:57 +0100
- dear all, the solution to the problem is a slash. emm.statc.lme <- lme(data = emm.stat, random = ~weeks | tn.mainc / code, fixed = oq.tot ~ weeks, na.action = na.omit) summary(emm.statc.lme) then has
- /archives/html/s-news/2007-10/msg00067.html (8,732 bytes)
- 18. multiple r squared in lm (score: 1)
- Author: "Puschner, Bernd" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Tue, 11 Mar 2008 11:45:30 +0100
- -99,"non-detect","normal")),
- /archives/html/s-news/2008-03/msg00025.html (10,752 bytes)
- 19. adjusted r squared in regression model (score: 1)
- Author: "Puschner, Bernd" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Tue, 11 Mar 2008 11:50:41 +0100
- dear all, this has been discussed previously, but I couldn't find an answer in the s-news-archives: how do I get adjusted r squared (in addition to the Multiple R-Squared) in a lm model? preferably w
- /archives/html/s-news/2008-03/msg00026.html (6,331 bytes)
- 20. lme count data (score: 1)
- Author: "Puschner, Bernd" <Bernd.Puschner@bkh-guenzburg.de>
- Date: Mon, 31 Aug 2009 15:33:27 +0200
- dear all, i have a randomized controlled trial with outcome data on the 2 groups (intervention vs. control ) assessed at 4 measurement points. now the main outcome variable is count data (hospital st
- /archives/html/s-news/2009-08/msg00018.html (6,352 bytes)
This search system is powered by
Namazu