Mail Archive Search: <+from:katkih@mail.nih.gov>

Results:

References: [ +from:katkih@mail.nih.gov: 7 ]

Total 7 documents matching your query.

1. [S] Deviance residuals in Cox models (score: 1): Author: "Katki, Hormuzd (NCI)" <katkih@mail.nih.gov>; Date: Fri, 22 Sep 2000 20:14:07 -0400; Hi. In the SPlus 2k Vol. 2 manual on page 267 where it discusses how to identify poorly predicted subjects in a Cox model, it says "Recent experience has shown that deviance residuals do not work wel; /archives/html/s-news/2000-09/msg00161.html (7,499 bytes)
2. [S] Efficient computation of diagonal of hat matrix for smoothing spl ines (score: 1): Author: "Katki, Hormuzd (NCI)" <katkih@mail.nih.gov>; Date: Thu, 20 Jul 2000 14:44:54 -0400; Hello. Hastie and Tibshirani's GAM book says "...algorithms are available to compute S_ii (diagonal of smoother hat matrix) for the cubic smoothing spline in O(n) operations..." but they don't give a; /archives/html/s-news/2000-07/msg00148.html (7,816 bytes)
3. [S] problems with residuals.coxph() with weights (score: 1): Author: "Katki, Hormuzd (NCI)" <katkih@mail.nih.gov>; Date: Thu, 27 Jul 2000 22:04:41 -0400; Hello. I have 2 questions about using residuals.coxph() with 1. Weighted martingale residuals crashes: Call: coxph(formula = Surv(tim.87, aids.87) ~ evrld, data = macs, weights = seroage, subset = ti; /archives/html/s-news/2000-07/msg00220.html (9,278 bytes)
4. [S] Confidence intervals for mixed effects (lme) parameters (score: 1): Author: "Katki, Hormuzd (NCI)" <katkih@mail.nih.gov>; Date: Tue, 19 Oct 1999 14:12:35 -0400; Hello. Consider a Normal linear mixed effects model where the intercept has both a fixed effect and random effect. I want to make a confidence interval for the total intercept=fixed-effect-intercept; /archives/html/s-news/1999-10/msg00164.html (8,206 bytes)
5. [S] looping with crosstabs command (score: 1): Author: "Katki, Hormuzd (NCI)" <katkih@mail.nih.gov>; Date: Wed, 21 Jul 1999 12:07:55 -0400; Hi. I've noticed some problems when running the crosstabs command inside a loop. What am I doing wrong? 1. SPlus crashes if the looping variable is a part of the crosstabs statement: for (flag in c(4; /archives/html/s-news/1999-07/msg00164.html (7,659 bytes)
6. [S] Logistic Regression Model Selection in S-Plus (score: 1): Author: "Katki, Hormuzd (NCI)" <katkih@mail.nih.gov>; Date: Wed, 7 Apr 1999 13:45:46 -0400; Dear S-Plus users, The issue is how to select the optimal # of knots for covariates represented as cubic splines in a logistic regression. The goal is to determine the relationship between probabilit; /archives/html/s-news/1999-04/msg00040.html (9,121 bytes)
7. [S] Cox PH model for case-cohort studies (score: 1): Author: "Katki, Hormuzd (NCI)" <katkih@mail.nih.gov>; Date: Tue, 27 Apr 1999 16:07:28 -0400; Hello. Has anyone written an SPlus function for a Cox PH model for case-cohort studies that computes the correct estimate of the variance of the relative-risk ratio in case of late entry (in the mann; /archives/html/s-news/1999-04/msg00256.html (7,313 bytes)

Current List: 1 - 7
Page: [1]