Nonparametric multiple comparison
Hi All, How reliable is Dunnett's comparison (w/control) when applied to ranked data ? This appears to be an ad hoc nonparametric multiple comparison with a test statistic based on group rank sums in place of group means and a standard error of sqrt[n(np)(np+1))/6] My guess is that it's unstable for small samples I found reference to it in Zar, Biostatistical Analysis (1974) (only edition in our library) The standard error is cited to Wilcoxon and Wilcox (1964)(rare ?) Why 6 instead of 12 ? thanks, Al Barron Metuchen, NJ __ Do You Yahoo!? Yahoo! Sports - sign up for Fantasy Baseball http://sportsyahoocom = Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at http://jsestatncsuedu/ =
NJ Stat Conference: Deming Applied Statistics, Dec 10-13
ANNOUNCING... The 57th Annual Deming Conference on Applied Statistics Atlantic City, New Jersey December 10-13, 2001 For details, registration costs, etc. see http://nimbus.ocis.temple.edu/~kghosh/deming01/ The Program will include: == Regression Modeling Strategies Professor Frank E. Harrell Jr. University of Virginia Modeling Variance and Covariance Structure in Mixed Linear Models Professor Ramon C. Littell University of Florida 1:00-4:00 Bayesian Computation and its Application to Non-linear Classification and Regression Professor Bani K. Mallick Texas AM University Analysis of Covariance: Repeated Measures and Some Other Interesting Applications Professor George A. Milliken Statistical Methods for Clinical Trials Mark X. Norleans, M.D., Ph.D. The National Cancer Institute Experiments: Planning, Analysis and Parameter Design Optimization Professor Jeff Wu University of Michigan 1:00-4:00 Sequential Clinical Trials: Design, Monitoring Analysis Vlad Dragalin, PhD GlaxoSmithKline Multiple Comparisons for Making Decisions Professor Jason C. Hsu Ohio State University Simultaneous Monitoring and Adjustment Professor J. Stuart Hunter Princeton University Applied Logistic Regression Professor Stanley A. Lemeshow Ohio State University 1:00-4:00 Permutation Methods: A Distance Function Approach Professor Paul W. Mielke, Jr. Colorado State University Approaches to the Analysis of Microarray Data and Related Issues Profs Elisabetta Manduchi and Warren Ewens University of Pennsylvania Experimental Design and the Statistical Analysis of Spotted Microarrays Professor Kathleen Kerr University of Washington Challenges Posed by the Human Genome Project Professor Warren Gish Washington University in St. Louis Measurement Error in Nonlinear Models Professor David Ruppert Cornell University __ Do You Yahoo!? Find the one for you at Yahoo! Personals http://personals.yahoo.com = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Conference: Deming Applied Statistics, NJ, Dec 10-13
ANNOUNCING... The 57th Annual Deming Conference on Applied Statistics Atlantic City, New Jersey December 10-13, 2001 For details, registration costs, etc. see http://nimbus.ocis.temple.edu/~kghosh/deming01/ The Program will include: == Regression Modeling Strategies Professor Frank E. Harrell Jr. University of Virginia Modeling Variance and Covariance Structure in Mixed Linear Models Professor Ramon C. Littell University of Florida 1:00-4:00 Bayesian Computation and its Application to Non-linear Classification and Regression Professor Bani K. Mallick Texas AM University Analysis of Covariance: Repeated Measures and Some Other Interesting Applications Professor George A. Milliken Statistical Methods for Clinical Trials Mark X. Norleans, M.D., Ph.D. The National Cancer Institute Experiments: Planning, Analysis and Parameter Design Optimization Professor Jeff Wu University of Michigan 1:00-4:00 Sequential Clinical Trials: Design, Monitoring Analysis Vlad Dragalin, PhD GlaxoSmithKline Multiple Comparisons for Making Decisions Professor Jason C. Hsu Ohio State University Simultaneous Monitoring and Adjustment Professor J. Stuart Hunter Princeton University Applied Logistic Regression Professor Stanley A. Lemeshow Ohio State University 1:00-4:00 Permutation Methods: A Distance Function Approach Professor Paul W. Mielke, Jr. Colorado State University Approaches to the Analysis of Microarray Data and Related Issues Profs Elisabetta Manduchi and Warren Ewens University of Pennsylvania Experimental Design and the Statistical Analysis of Spotted Microarrays Professor Kathleen Kerr University of Washington Challenges Posed by the Human Genome Project Professor Warren Gish Washington University in St. Louis Measurement Error in Nonlinear Models Professor David Ruppert Cornell University __ Do You Yahoo!? Find a job, post your resume. http://careers.yahoo.com = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Education is a national security issue
I'd like to share the following article in honor of those who perished a month ago in the Sept. 11 terrorist attacks. Knowing that there are positive and constructive options to follow is reassuring that there is hope for our children. Al = Thursday, October 11, 2001 U.S. education secretary calls for high science and math goals. Rod Paige spoke during a conference at Penn. Education is a national security issue, he said. By Connie Langland INQUIRER STAFF WRITER U.S. Secretary of Education Rod Paige said yesterday that creating a national education system that sets high standards in math, science and other basic skills is an essential part of building a strong nation. Education is a national security issue, Paige told education researchers from six nations who are meeting in Philadelphia. Paige credited former Gov. Tom Ridge for emphasizing education. Ridge left the office for the cabinet-level post of director for homeland security. The events of Sept. 11 have had a great effect on all of us, but it has not deterred us from our goal to create an education system that will leave no child behind, Paige said. We will not be content with educating just some children, he said. Every child must learn and do well. The education secretary - former superintendent of the Houston system - endorsed the efforts of the researchers gathered at the Six Nation Education Research Project Conference, which is being held by the University of Pennsylvania's Graduate School of Education. He lauded their efforts to identify the resources and research that create teaching methods that work - and don't work. He said those studies would benefit educational efforts here and throughout the world. For seven years, researchers from China, Germany, Japan, Singapore, Switzerland and the United States have studied how nations perform in such areas as math and science education, vocational education and higher education, and what variables contribute to strong or poor performances. In mathematics, setting high standards is key, said Erling Boe, professor of education in the Graduate School of Education at Penn, who, with colleagues at Penn and Pennsylvania State University, studied how countries teach math and science. Students do better in math in countries that are tough on math students, said Boe, noting that when asked whether they do well in math, students in those countries tend to disagree. In countries with lax academic standards in math and science, he said, students often have the opinion that they are good in those subjects. Of about 40 countries, the United States ranks in the middle in math and science achievement, according to international studies. Yesterday afternoon, Paige visited Conestoga High School in Berwyn, Chester County, to observe the start-up of an Internet-based education portal that will link teachers, parents and students in four states - Pennsylvania, New Jersey, Delaware and Maryland. __ Do You Yahoo!? Make a great connection at Yahoo! Personals. http://personals.yahoo.com = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
saddlepoint
I've begun looking at saddlepoint approximation, in particular, for the distribution tail. I've also taken a peak at Laplace approximations. This stuff appears to be rather analytical. Does anyone have any examples, maybe some with SAS or S code? thanks, Al Barron Metuchen, NJ __ Do You Yahoo!? NEW from Yahoo! GeoCities - quick and easy web site hosting, just $8.95/month. http://geocities.yahoo.com/ps/info1 = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Deming Applied Stat Conf.,NJ, Dec 10-13
ANNOUNCING... The 57th Annual Deming Comnference on Applied Statistics Atlantic City, New Jersey December 10-13, 2001 For details, registration costs, etc. see http://nimbus.ocis.temple.edu/~kghosh/deming01/ The Program will include: == Regression Modeling Strategies Professor Frank E. Harrell Jr. University of Virginia Modeling Variance and Covariance Structure in Mixed Linear Models Professor Ramon C. Littell University of Florida 1:00-4:00 Bayesian Computation and its Application to Non-linear Classification and Regression Professor Bani K. Mallick Texas AM University Analysis of Covariance: Repeated Measures and Some Other Interesting Applications Professor George A. Milliken Statistical Methods for Clinical Trials Mark X. Norleans, M.D., Ph.D. The National Cancer Institute Experiments: Planning, Analysis and Parameter Design Optimization Professor Jeff Wu University of Michigan 1:00-4:00 Sequential Clinical Trials: Design, Monitoring Analysis Vlad Dragalin, PhD GlaxoSmithKline Multiple Comparisons for Making Decisions Professor Jason C. Hsu Ohio State University Simultaneous Monitoring and Adjustment Professor J. Stuart Hunter Princeton University Applied Logistic Regression Professor Stanley A. Lemeshow Ohio State University 1:00-4:00 Permutation Methods: A Distance Function Approach Professor Paul W. Mielke, Jr. Colorado State University Approaches to the Analysis of Microarray Data and Related Issues Profs Elisabetta Manduchi and Warren Ewens University of Pennsylvania Experimental Design and the Statistical Analysis of Spotted Microarrays Professor Kathleen Kerr University of Washington Challenges Posed by the Human Genome Project Professor Warren Gish Washington University in St. Louis Measurement Error in Nonlinear Models Professor David Ruppert Cornell University __ Do You Yahoo!? NEW from Yahoo! GeoCities - quick and easy web site hosting, just $8.95/month. http://geocities.yahoo.com/ps/info1 = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
nonlinear regression comparison
Guess what folks, after reviewing my assay data closely, it occured to me that it is relatively nonlinear. So I've been reviewing some notes from a short course on applied nonlinear regression taught by George Milliken. While these may not be available to most of you, he cites a related ref. in Milliken and DeBruin (1978)A procedure to test hypotheses for nonlinear models, Comm.Stat.Theor. Meth.,A(71):65-79. Al = Date: Fri, 13 Jul 2001 11:26:00 -0700 (PDT) From: Alfred Barron [EMAIL PROTECTED] Subject: parallel-line assay I have to compare treatment dose-response assay data. This can be done using regression as in Finney's book (among other references). However, I understand that non-parametric tests for the parallelism of 2 regression lines was coded in SAS in the late 70s. While I have some old proc matrix code described in SAS SUGI 4 (1979) to do it, does anyone have something more current that is online somewhere or that they could share ? My study involves bacterial strains measured under different treatment conditions. thanks, Al Barron Metuchen, NJ __ Do You Yahoo!? Get personalized email addresses from Yahoo! Mail http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
parallel-line assay
I have to compare treatment dose-response assay data. This can be done using regression as in Finney's book (among other references). However, I understand that non-parametric tests for the parallelism of 2 regression lines was coded in SAS in the late 70s. While I have some old proc matrix code described in SAS SUGI 4 (1979) to do it, does anyone have something more current that is online somewhere or that they could share ? My study involves bacterial strains measured under different treatment conditions. thanks, Al Barron Metuchen, NJ __ Do You Yahoo!? Get personalized email addresses from Yahoo! Mail http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
teaching probability statistics
Karen, I'm forwarding your request to the edstat list. You may also want to look into the AP statistics list. Look these up using www.google.com by using the search words AP Statistics. Al === Date: 30 May 01 21:41:32 -0400 (EDT) From: Karen Rigsby [EMAIL PROTECTED] Subject: teaching probability statistics I am doing a research paper on teaching probability and statistics and am interested in the results of your study. Is that posted anywhere on the web? Thank you. = Alfred M. Barron NonClinical Biostatistics R. W. Johnson Pharmaceutical Research Institute 1000 Route 202, OMP Rm. G-35 Raritan, NJ 08869 [908] 704-4102 [EMAIL PROTECTED] = __ Do You Yahoo!? Get personalized email addresses from Yahoo! Mail - only $35 a year! http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
ANOVA and regression
The relation between ANOVA and regression goes to the heart of the linear model; they are, at once, both inter-connected aspects of the linear model. In fact, one could interpret ANOVA as regression on indicator variables. If you want to go further, one could contrast linear modeling ingeneral with experimental design as well. Again, both are inter-connected. This perspective is outlined well in the Kutner, Neter, Wasserman books on linear models. There there are 2 or 3 versions on the market, in various editions. The current one is called Applied Linear Statistical Models. A more theoretical approach can be found in Searle's Linear Models. No false placebo effect here ! Al === Alfred M. Barron NonClinical Biostatistics R. W. Johnson Pharmaceutical Research Institute 1000 Route 202, OMP Rm. G-35 Raritan, NJ 08869 [908] 704-4102 [EMAIL PROTECTED] === __ Do You Yahoo!? Get personalized email addresses from Yahoo! Mail - only $35 a year! http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
multivariate normality
May I suggest you email the authors of the SAS book "Applied Multivariate Statistics with SAS Software" that describes the MV macro. Al Barron, Metuchen, NJ __ Do You Yahoo!? Get email at your own domain with Yahoo! Mail. http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
multivariate normality
May I suggest you email the authors of the SAS book on Applied Multivariate Statistics that describes the MV macro. Al Barron, Metuchen, NJ __ Do You Yahoo!? Get email at your own domain with Yahoo! Mail. http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Election Data
I'd like to model some past voter data to help assess voter trends (predict election outcomes ?) and preferences. Does anyone have any references ? Texts and websites would be approciated. Is most of this done using some form of logistic regression ? Al Barron Metuchen, NJ __ Do You Yahoo!? Get email at your own domain with Yahoo! Mail. http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =
Time to an event (retirement)
Hi everyone, The event I'm interested in is an estimate of time to retirement (or attrition) of our staff. A brief subset of my data looks like, SUB AGE HIRED RETIRED ACTIVE 150 09/15/7006/15/90 0 245 09/12/7506/15/92 0 352 09/13/72 .1 455 09/15/70 .1 535 09/17/90 .1 ...etc... The variables are SUB (subject), AGE, HIRED (date hired), RETIRED (date retired or quit), and ACTIVE (0=retired, 1=employed). This appears to be fairly standard data. Could anyone suggest a working model in SAS ? I'm considering PROC LIFEREG with Allison's PREDICT macro (as described in his 1995 book). Maybe use age as a covariate... Any suggestions on this ? Is this in the published literature ? Survival analysis is new to me. For the curious, I'm trying to get a rough estimate of the number of people taking retirement this year for our budget planning. I'm on the local Board of Education. thanks, Al Barron Metuchen, NJ __ Do You Yahoo!? Get email at your own domain with Yahoo! Mail. http://personal.mail.yahoo.com/ = Instructions for joining and leaving this list and remarks about the problem of INAPPROPRIATE MESSAGES are available at http://jse.stat.ncsu.edu/ =