Re: [R] How to do bootstrap for the complex sample design?

there are no design-unbiased estimators of the standard error, so as others have said you need external data. -thomas -- Thomas Lumley Professor of Biostatistics University of Auckland __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo

Re: [R] interpretation of coefficients in survreg AND obtaining the hazard function for an individual given a set of predictors

as the baseline hazard. The baseline hazard is the hazard when all your covariates are equal to zero, and this depends on how you parametrize. In mwa, zero is grade2=low, in mwb, zero is grade2=high, so the hazard at zero has to be different in the two cases. -thomas -- Thomas Lumley

Re: [R] Re : interpretation of coefficients in survreg AND obtaining the hazard function for an individual given a set of predictors

, and this depends on how you parametrize.  In mwa, zero is grade2=low, in mwb, zero is grade2=high, so the hazard at zero has to be different in the two cases.     -thomas -- Thomas Lumley Professor of Biostatistics University of Auckland __ R

Re: [R] svydesign syntax

, the second describes the two phases of sampling that give first the whole database and then your subsample. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch

Re: [R] svydesign syntax and deviance!

asymptotically have a known distribution and this gives the Rao-Scott 'working deviance' tests. These tests are widely used for loglinear models but also apply to generalized linear models and the Cox model. The function regTermTest() does Rao-Scott tests with the method=LRT option. -thomas Thomas

Re: [R] Function to Define a Function

- function(type=c(one,two)) { type - match.arg(type) switch(type, one= function(x,N0,r) N0*exp(x*r) , two=function(x,N0,r,K) (N0*K)/(N0+(K-N0)*exp(-x*r)) , ) } -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle

Re: [R] svydesign syntax and deviance!

need to choose with the two models it is correct to use the deviance from glm model for the svyglm. No. It isn't correct to use the deviance at all. The deviance is based on the likelihood for independent sampling, and that is not what you have. -thomas Thomas Lumley Professor

Re: [R] multicore mclapply error

Java and rjava, and it wouldn't be altogether surprising if the connection to Java or the Java environment reacted badly to being forked. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org

Re: [R] Bug in t.test?

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. Thomas Lumley Professor of Biostatistics University of Washington, Seattle

Re: [R] Bug in t.test?

, or even better, paired=~variable.name. Relying on data frame ordering seems a really bad idea. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman

Re: [R] Weird differing results when using the Wilcoxon-test

, minimal, self-contained, reproducible code. Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R

Re: [R] svyquantile w/ svyby is returning an error

=FALSE) stype statistic1 statistic2 E E512615 H H482593 M M518611 The help page does say svyquantile needs ci=TRUE or keep.var=FALSE. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle

Re: [R] Regex exercise

On Fri, 20 Aug 2010, Bert Gunter wrote: Given the string (entered, say, at a readline prompt): 1 2 -5, 3- 6 4 8 5-7 10 ## only integers will be entered Presumably only non-negative integers (Special note to Thomas Lumley: This seems one of the few instances where eval(parse..)) may

Re: [R] Help on glm and optim

is to reparametrize and use the log scale rather than the scale as a parameter. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read

Re: [R] limit on read.socket?

the data stream is over. This could be some sort of 'end of transmission' marker or a count of the number of bytes or lines to be expected. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org

Re: [R] coxph and ordinal variables?

them. options(contrasts=c(contr.treatment,contr.treatment)) It's like the Good Old Days when you had to use options() to tell S-PLUS not to use Helmert contrasts. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle

Re: [R] Counting occurances of a letter by a factor

://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman

Re: [R] Counting occurances of a letter by a factor

. (Or force the factor to include all three levels) I would force the factor to include all three levels. -thomas Brian -Original Message- From: Thomas Lumley [mailto:tlum...@u.washington.edu] Sent: Friday, September 10, 2010 3:22 PM To: Davis, Brian Cc: Phil Spector; r-help@r-project.org

Re: [R] relative risk regression with survey data

to explain. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ 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

Re: [R] Creating publication-quality plots for use in Microsoft Word

need. Work out how big you want the graph to be, and use PNG with enough pixels to get at least 300dpi at that final size. You'll need to set the pointsize argument and it will help to set the resolution argument. -thomas Thomas Lumley Professor of Biostatistics University of Washington

Re: [R] relative risk regression with survey data

distributions for fixed and random design matrices can be very different, because a random design matrix means that the estimated edge of the parameter space moves from one realization to another. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle

Re: [R] glm: formula vs character

parent.frame(), but in more complex cases it is different. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting

[R] Arrrr.

Ahoy maties, As I'm sure everyone is aware, today (ISOdate(2010,9,19)) is International Talk Like A Pirate Day. I hope Arrr-help and Arrr-devel, and the whole of the Arrr community will be observing the day properly. __ R-help@r-project.org

Re: [R] Depletion of small p values upon iterative testing of identical normal distributions

= -0.065, s = 0.0837) { x - rnorm(6, m, s) y - rnorm(6, m, s) t.test(x, y, var.equal=TRUE)$p.value } ev.pvals - replicate(1e5, one.test()) and the problem is solved. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle

Re: [R] interpreting one-way anova tables

in using n vs n-p vs n1+n2-2 in denominators - different approximations to the denominator degrees of freedom. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https

Re: [R] support for caron (hacek) symbol

created a graph and put it at http://faculty.washington.edu/tlumley/czech.png with text using carons that Wikipedia tells me is Czech. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org

Re: [R] support for caron (hacek) symbol

and R 2.11.1. R is using a UTF-8 locale. You probably need Cairo and Pango, and you may well need to install some more fonts. There is some documentation in the R Installation and Administration manual. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle

Re: [R] puzzle with integrate over infinite range

() function to find all the mass. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ 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

Re: [R] Function to find prime numbers

to create a vector of small primes and use my_array %in% smallprimes. For example, the first 1000 primes are at http://primes.utm.edu/lists/small/1000.txt and the first 1 are on the same site. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum

Re: [R] svy / weighted regression

/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. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] post-hoc test with kruskal.test()

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. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity

Re: [R] How to run Shapiro-Wilk test for each grouped

from a unique normal distribution, and only one normality test on the residuals is necessary (no need for a loop). Or, as some of us would say, *no* normality test on the residuals is necessary, which is even simpler. -thomas Thomas Lumley Assoc. Professor, Biostatistics

Re: [R] glmer with non integer weights

this in the quasilikelihood chapter in McCullagh and Nelder, where the observations are the proportion of damage on a set of leaves. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] Any chance R will ever get beyond the 2^31-1 vector size limit?

__ 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. Thomas Lumley Assoc. Professor

Re: [R] Weights in binomial glm

-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https

Re: [R] plotting RR, 95% CI as table and figure in same plot

) __ 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. Thomas Lumley Assoc

Re: [R] nls for piecewise linear regression not converging to least square

. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting

Re: [R] Results from clogit out of range?

. __ 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. Thomas Lumley Assoc

Re: [R] Generating a model fitness when score using svyglm?

, the deviance returned by svyglm() is scaled to the sample size, so if the survey design isn't informative it should be more or less in the same ballpark as a deviance from an independent sample, and the usual BIC calculation might give somewhat helpful results. -thomas Thomas Lumley

Re: [R] Generating a model fitness score when using svyglm?

, then applying the same formula to svyglm() output will give a reasonable approximation to the same thing, but I wouldn't put much weight in small differences. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington

Re: [R] nnclust: nnfind() distance metric?

/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list

Re: [R] median of two groups

-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. Thomas Lumley Assoc. Professor, Biostatistics tlum

Re: [R] Dimensions on svychisq on svydesign

the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] (svy)glm and weights question

to regression modelling, but the principles are the same. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch

Re: [R] survey package: weights used in svycoxph()

(). -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide

Re: [R] survey package: weights used in svycoxph()

, the weighted mean $\bar Z$ is changed to include both the risk weights $r$ and the external weights $w$. [Mayo Clinic Biostatistics technical report #52, section 6.2.2] Don't see a section 6.2.2 in this technical report. Sorry, #58 -thomas Thomas Lumley Assoc. Professor

Re: [R] Using svychisq inside user-defined function

- NAToUnkown(Table, unknown = ) Colnames(Table) - c(T, Male (%), Male (n), Female (%), Female (n), p-value) Table } con3 - mkMyCrossTable(data$con, con, Constituency) Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] esthetics --- extending the lm command to fixed effects?

of the arguments in a modelling call silently treated as formulas was a bad decision, although it must have looked user-friendly at the time. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] offlist Re: Svy function doesn't work nested in user-defined function

, but it's really easier just to work with the formula. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https

Re: [R] WHO Anthro growth curve macros and R

to discover the source code of the software, without prior permission from WHO. I'm assuming that simply echoing the .ssc file to the screen doesn't violate this, but anything that would make the functions usable probably would. -thomas Thomas Lumley Assoc. Professor

Re: [R] problem with 'svyby' function from SURVEY package

Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http

Re: [R] using string as variable name in model

, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting

Re: [R] calibration and validation for svycoxph

functions like the ones Frank Harrell provides, though. Incidentally, sending two messages in quick succession like this is not a good strategy for getting help. -thomas On Wed, 9 Jun 2010, R user wrote: Hello, This post is for Dr. Thomas Lumley or anybody familiar with the survey package. I

Re: [R] Simulating a Poisson Process in R by calling C Code over .Call

) is almost as good. Yet another approach is to take advantage of the memoryless property of the Poisson process: set tau to some reasonable length, then if it fill up, return and call the function again to handle the remainder of the duration. -thomas Thomas Lumley Assoc

Re: [R] help biglm.big.matrix; problem with weights

(Reg) Has sombody an idea, what my error is? No, but it would help if you said exactly what the error message was for this code. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] S3 generics need identical signature?

, and that requires you to specify arguments to the generic function. For example, I have written quite a few functions of the form foo - function(formula, data, ...) UseMethod(foo, data) -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.edu

Re: [R] Wilcoxon signed rank test and its requirements

these distinctions. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read

Re: [R] Some questions about R's modelling algebra

':' for their '.' and '^' for their '**'. I think the algebra is the same. -thomas Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http

Re: [R] unable to get bigglm working, ATTN: Thomas Lumley

. -- View this message in context: http://r.789695.n4.nabble.com/unable-to-get-bigglm-working-ATTN-Thomas-Lumley-tp2276524p2276524.html Sent from the R help mailing list archive at Nabble.com. __ R-help@r-project.org mailing list https://stat.ethz.ch

Re: [R] Visualization of coefficients

, reproducible code. Thomas Lumley Professor of Biostatistics University of Washington, Seattle __ 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

Re: [R] advice/opinion on - vs = in teaching R

mechanism to determine whether the assignment happens. That would be very hard to do in two lines of code. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] advice/opinion on - vs = in teaching R

or does it matter, please? I would say to use = if you are teaching people familiar with C or Java, and to use - otherwise. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] weighting (survey) data

to write my own functions for all of them is really scaring me ;)) The survey package covers quite a wide range of analyses. Can you be more specific about what you think is missing? -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.edu

Re: [R] weighting (survey) data

() in the survey package. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r

Re: [R] weighting (survey) data

On Sun, 17 Jan 2010, Vera wrote: 2010/1/16 Thomas Lumley tlum...@u.washington.edu: On Sat, 16 Jan 2010, Vera wrote: Thanks for your help so far, everyone. Thomas: I haven't looked very deep into the survey package yet, so I don't know if what I'm looking for is actually missing or if I just

Re: [R] advice/opinion on - vs = in teaching R

On Mon, 18 Jan 2010, S Ellison wrote: Thomas Lumley tlum...@u.washington.edu 15/01/2010 16:07 Which should I use or does it matter, please? I would say to use = if you are teaching people familiar with C or Java, and to use - otherwise. Nothing like an option to induce polarisation

Re: [R] Server hanging despite efforts to correct memory limits

read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] Predict polynomial problem

as the value '20', so any further evaluations get poly(x,20). This is reminiscent of the way macro languages work... Yes, bquote() was written to mimic the backquote macro in Lisp, hence its name. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum

Re: [R] Sampling theory

is that you lose the opportunity to use bias corrections that are only available for simple cases. The forthcoming version 3.19 (later this week) has nicer output for the population variance, but the computations are still the same. -thomas Thomas Lumley Assoc. Professor

Re: [R] Sata and R users GLM methods translation

=binomial(probit). -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read

Re: [R] plotting additive ns components

additive components (the estimates of the two additive terms on the RHS) ?termplot. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r

Re: [R] large integers in R

mentioned, having the integer type be 64-bit means that it wouldn't match the Fortran default INTEGER type or the C int on most platforms, which are 32-bit. Calling C code would become more difficult. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum

Re: [R] Constrained vector permutation

valid permutations this way. It does not appear straightforward to ensure that all valid permutations are sampled with equal probability, which I thought was part of the specification of the problem. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum

Re: [R] (With trepidation): Evaluating expressions with sub expressions again

lines of pure R (it just doesn't solve your particular problem because it substitutes for .() rather than for b). -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] Weighted SD

have pointed out from time to time, it depends on what the weights are for -- are they precision weights, which lm() can handle, or sampling weights, which it can't? -tomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington

Re: [R] subset function unexpected behavior

to* mask one in the global environment. subset() can't fail to mask variables further up the search path, so it doesn't ever warn. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle

Re: [R] iterative regressions, adding a new line of data each, time

by Alan Miller. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do

Re: [R] color blending and transparency

on paper to see it more clearly). -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help

Re: [R] color blending and transparency

, a function of n). Also, for PDF and SVG we are basically limited to models that PDF implements automatically, since it isn't feasible to work out which objects overlap and adjust their colors that way. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum

Re: [R] Random number quality

') __ 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. Thomas Lumley Assoc. Professor

Re: [R] using a variable name stored in another variable?

... It's also FAQ 7.21. Not quite as famous as 7.31, but still a good vintage. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing

[R] [R-pkgs] survey 3.20

. The NEWS file has a more detailed list of additions and changes. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle ___ R-packages mailing list r-packa...@r

Re: [R] WMF conversion...

/posting-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list

Re: [R] cluster/distance large matrix (fwd)

On Thu, 11 Feb 2010, Christian Hennig wrote: It is well know that hierarchical methods are problematic with too large dissimilarity matrices; even if you resolve the memory problem, the number of operations required is enormous. There is at least one exception to this. Single-linkage

Re: [R] R ANOVA gives diferent results than SPSS

. Either you specified a different model or different tests for the same model in the two systems, or you are interpreting the output incorrectly, or the results are different. Without more detail it is hard to be sure, but the first two possibilities seem more likely. -thomas Thomas Lumley

Re: [R] difftime result for days not an integer?

: 0.958 is 23/24. Would you just round off? Yes, or use as.Date() if you only want to consider whole days R as.Date('2004-08-05')-as.Date('2001-01-03') Time difference of 1310 days -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.edu

Re: [R] expression() help

]) or quote(Average~PM[10]) seem to work. There is an example of the first style in ?plotmath. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r

Re: [R] R 64-bit memory.limit() is max of ?

that scale slower than linearly in the sample size will get very painful. -thomas Thomas Lumley Assoc. Professor, Biostatistics tlum...@u.washington.eduUniversity of Washington, Seattle __ R-help@r-project.org mailing list

Re: [R] survey package question

and their SEs be computed for subgroups? You can also use subset(), which is what svyby() does internally svyquantile(~api00, quantile=c(0.25,0.5,0.75), subset(dclus1, stype==E)) 0.25 0.5 0.75 api00 553 652 729 -thomas Thomas Lumley Assoc. Professor

Re: [R] Number - Fraction

-Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Thomas Lumley Sent: Thursday, September 13, 2007 11:34 AM To: Mauro Arnoldi Cc: r-help@r-project.org Subject: Re: [R] Number - Fraction On Thu, 13 Sep

Re: [R] Robust or Sandwich estimates in lmer2

or for the marginal variance. -thomas Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED] University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do

Re: [R] Package Survey

) --- [[alternative HTML version deleted]] Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED] University of Washington, Seattle__ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help

Re: [R] Package Survey

,cvpct)) ** Citando Thomas Lumley [EMAIL PROTECTED]: This message uses a character set that is not supported by the Internet Service. To view the original message content, open the attached message. If the text doesn't display correctly, save

Re: [R] weighting question

On Mon, 24 Sep 2007, eugen pircalabelu wrote: Hi R-users, Can anyone tell me where can i find info about they way how post stratification weights are calculated when i have an already stratified survey design, especially in Survey Package (but any theoretical material would do me just

Re: [R] center option of basehaz in survfit

On Thu, 27 Sep 2007, David Koons wrote: I have a very general question about what the centering option in basehaz does to factors. (basehaz computes the baseline cumulative hazard for a coxph object using the Breslow estimator). Lets say I'm interested in a survival model with two

Re: [R] Idioms for empty dataframes

, and then order(t1$bob) integer(0) more or less as you expected. -thomas Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED] University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch

Re: [R] plot from source file

-goettingen.de __ 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. Thomas Lumley

Re: [R] continue for loop in case of erros

-guide.html and provide commented, minimal, self-contained, reproducible code. Thomas Lumley Assoc. Professor, Biostatistics [EMAIL PROTECTED] University of Washington, Seattle __ R-help@r-project.org mailing list https://stat.ethz.ch

Re: [R] Summary vs fivenum results for Q3

for fivenum(), which doesn't use the word quartile at all. Everyone agrees that the third quartile (and the upper hinge) should be somewhere between the 24th and 25th of 32 observations, but not on which point in this interval should be chosen. -thomas Thomas Lumley Assoc

Re: [R] some question about partial prediction in survival

On Sun, 14 Oct 2007, coldeyes.Rhelp wrote: Hi there: i got a problem to get the prediction from a model recently. for example if i use a survival analysis to predict the risk. i use the code like below: i found the the prediction is not equal to (coef * x + coef * sex) , could someone help

  1   2   3   4   5   6   >