jweedon's articles:

Items(29) /3 Next >> Last >|

Modelling strength of correlation 2 15 (3/16/2013 8:24:20 PM) comp.soft-sys.sas Folks, (Gosh it's a very long time since I last posted here!) A medical colleague has longitudinal data concerning 2 biological parameters (let's call them systolic [X] & diastolic [Y] blood pressure): ... Jay

Estimating prevalence in the presence of unreliable classification 1 30 (7/14/2012 8:37:23 PM) comp.soft-sys.sas Hi folks, I'm involved in a study in which 6 raters evaluate 200 human subjects (2 raters per subject, working independently), trying to decide in which of 6 exclusive differential diagnostic categories ea... Jay

Incomplete factorial, what are the estimable effects? 0 13 (11/28/2011 5:16:23 PM) comp.soft-sys.sas Folks, I'm trying to conduct a generalizability study involving 3 factors: Device (3 levels, fixed effect) Rater (5 levels, random effect) Subject (100 levels, random effect) The design is that device & subj... Jay

PROC PLS: Scoring new observations 2 21 (5/27/2011 1:21:59 PM) comp.soft-sys.sas Hi folks, PROC PLS outputs a couple of tables called Parameter Estimates. I can't figure out what these are or how to use them. What I'd like to do is to save some estimated coefficients from the procedure to... Jay

Multicollinearity question 9 244 (11/25/2009 5:57:54 PM) comp.soft-sys.sas Here's a question I haven't seen discussed in the linear regression textbooks I own. Suppose that Y is regressed on X1, X2, X3, with X1 the predictor of interest; X2 & X3 are regarded as "nuisance" covariate... Jay

PROC MIXED covariance structure question 0 33 (2/9/2009 7:44:08 PM) comp.soft-sys.sas Hi folks, I'm trying to emulate traditional ARMA regression methods using PROC MIXED. MIXED provides an explicit AR(1) covariance structure; is there a way to model a moving average MA(1) structure using this ... Jay

Re: SAS 9.2 for Windows x64, first impressions #2 0 11 (11/19/2008 6:09:26 PM) comp.soft-sys.sas On Wed, 19 Nov 2008 06:10:37 -0800 (PST), MacAddict wrote: >On Jul 31, 7:49�pm, Jay Weedon wrote: >> Haven't had a chance to run any serious benchmarks comparing it with >> the 32-bit code, but I was dismayed... Jay

Table lookup puzzle 1 12 (9/5/2008 6:03:34 PM) comp.soft-sys.sas Hi folks, Guess I must be losing my grip of SAS programming, because I can't come up with an efficient solution to this easy-sounding problem. The master dataset A contains two date fields (the dates vary acr... Jay

SAS 9.2 for Windows x64, first impressions 0 11 (8/1/2008 12:49:42 AM) comp.soft-sys.sas Just got it running this week. It took some doing - our account rep had no idea of the administrative details of d/l-ing the 64-bit package (nor apparently do the folks at Contracts, so they're looking just a t... Jay

64-bit SAS: I'm confused 7 31 (4/16/2008 1:53:47 PM) comp.soft-sys.sas Hi folks, I know this sounds like a silly query, but having looked at a bunch of web pages at sas.com I can't seem to distinguish when they're talking about 32-bit SAS running in a 64-bit environment vs 64-bit... Jay

jweedon's replies:

Items(155) /16 Next >> Last >|

pairwise comparisons for >2 levels of strata in proc lifetest 1 22 (9/24/2008 3:56:15 AM) comp.soft-sys.sas I see that usually, proc lifetest does not output pairwise comparisons. Lifereg doesn't seem to either. Is there a way to get the pairwise comparisons from the covariance matrix table for the strata? Any inf... tdardas (19)

Do loop_ Macro 1 22 (9/24/2008 8:18:47 PM) comp.soft-sys.sas I have a data set looks like below. Record Mo12 mo24 mo36 =85. Mo240 1 100 150 160 180 200 2 120 160 180 190 250 3 100 100 100 100 100 For each record, if the amount is greater than 150, then amounts in that m... jiangqiyangfang (18)

Re: Glimmix vs Mixed #4 1 12 (9/25/2008 6:21:19 PM) comp.soft-sys.sas It's also worth pointing out that GLIMMIX uses penalized quasi-likelihood to fit its models, and that's known to produce biased results when you have small cluster sizes. If that's an issue, you might want to ... Eric.Johnson10 (4)

Re: PROC MIXED covariance structure question 1 32 (2/9/2009 8:18:00 PM) comp.soft-sys.sas --- On Mon, 2/9/09, Jay Weedon wrote: > From: Jay Weedon > Subject: PROC MIXED covariance structure question > To: SAS-L@LISTSERV.UGA.EDU > Date: Monday, February 9, 2009, 11:44 AM > Hi folks, > > I'm trying... stringplayer_2 (1472)

LSMEANS oddity 1 22 (4/27/2009 8:48:58 PM) comp.soft-sys.sas Hello all I ran into this oddity at work.... I can't show the real data, but I made up some (see below). In this example, the differences are quite small, but in the data at work they were not so small. Suppo... peterflomconsulting (1176)

Re: Table lookup puzzle #11 1 11 (9/6/2008 8:45:19 PM) comp.soft-sys.sas > Jay, > > Here is the array approach . Hope this meets your million records. Hash > approach may not be faster than this array approach. Let me know how this > meets the SQL method. > > data a; > input id min... muthia.kachirayan (702)

FREQ: Yate's Corrections versus Fisher's Exact 1 13 (9/9/2008 12:35:41 PM) comp.soft-sys.sas Greetings, I am now on our fourth revision of an article. Yes, I said fourth. In my opinion, it is a topic that will force a revolution in medical treatment. Unfortunately, our sample size is small. The ... citam.sasl (448)

Re: Table lookup puzzle Revisited 1 16 (9/17/2008 3:36:29 PM) comp.soft-sys.sas On Tue, Sep 16, 2008 at 6:53 PM, Muthia Kachirayan wrote: > This is based on my responses made to Jay Weedom's post and have further > added some insights to the solution. This should of interest to Jay and >... muthia.kachirayan (702)

Glimmix vs Mixed 1 12 (9/23/2008 9:24:15 PM) comp.soft-sys.sas Hi, I have a normally distributed data with a random variable which means that I should use mixed procedure for analysis. However, I have noticed that some people also use Glimmix for these kind of data. I tho... globalreviewer (6)

LSMEANS from Proc GLM 1 13 (9/24/2008 12:01:47 AM) comp.soft-sys.sas Hello Dear SAS users, Can someone tell how lease square means (lsmeans) from proc glm is calculated? A math formula would be nice... Thank you, claus ... jlee8071 (53)