Re: Software for robust stats?
Minitab is a very good Windows integrated soft with some robust statistics (non parametrics and robust rebression) and has a powerfull programmation language (a lot of these macros are avaliable from the net). And moreover... it's not expensive, even for student :-)) (as I am). But I am not really sure, as I can see in cited softwares in publications, that Minitab is recognised but perhaps am I wrong?? For specific utilisations, some soft exists: for exemple by Rouseeuw PROGRESS for robust regression... Hope this helps -- === Dr SAULEAU Erik-A. DIM -- Etablissement Public de Santé Alsace Nord 141, Ave de Strasbourg 67170 Brumath Tel : 03-88-64-61-81 E-Mail: [EMAIL PROTECTED] -- Centre Hospitalier d'Erstein 13, Route de Krafft BP F 67151 Erstein Cedex E-Mail: [EMAIL PROTECTED] === [EMAIL PROTECTED] a écrit dans le message : 8dj5g7$5er$[EMAIL PROTECTED] Hi, I'm a grad student in social science. My use of satistics software has been limited to SPSS because its simple user interface allowed me to easily do some simple non-parametric tests. But now, I am interested in trying some resistant analysis techniques I have read about, but they don't seem to be included in our lab version of SPSS 9.0. I guess I will have to program in the routines myself. If I have to do this, are there any suggestions as to which software package would be most appropriate to use? I was planning to buy a student version of SPSS or SAS, but since I will have to write routines, perhaps it would be better for me to stick to what I am familiar with: Maple and Excel. Thanks, Wendell Sent via Deja.com http://www.deja.com/ Before you buy. === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
Re: What's the Mahanalobis distance?
It's a good definition for the MD, but for outliers identification MD is not robust because of masking and swamping phenomena: outliers could have low MD and high MD means not in each cases outliers. See eg Barnet V, Lewis T. (1994). Outliers in statistical data. John Wiley and Sons, New-York., Rousseew PJ, Leroy AM. (1987). Robust regression and outlier detection. John Wiley and Sons, New-York. or works about robust distances. -- === Dr SAULEAU Erik-A. DIM -- Etablissement Public de Santé Alsace Nord 141, Ave de Strasbourg 67170 Brumath Tel : 03-88-64-61-81 E-Mail: [EMAIL PROTECTED] -- Centre Hospitalier d'Erstein 13, Route de Krafft BP F 67151 Erstein Cedex E-Mail: [EMAIL PROTECTED] === Lorenzo Camprini [EMAIL PROTECTED] a écrit dans le message : [EMAIL PROTECTED] Teo ha scritto nel messaggio... Anyone knows in what consist the Mahanalobis distance?? I have to measure the distance between two histograms... from the StatSoft website (Glossary): "Mahalanobis distance. One can think of the independent variables (in a regression equation) as defining a multidimensional space in which each observation can be plotted. Also, one can plot a point representing the means for all independent variables. This "mean point" in the multidimensional space is also called the centroid. The Mahalanobis distance is the distance of a case from the centroid in the multidimensional space, defined by the correlated independent variables (if the independent variables are uncorrelated, it is the same as the simple Euclidean distance). Thus, this measure provides an indication of whether or not an observation is an outlier with respect to the independent variable values." Proper citation: StatSoft, Inc. (1999). Electronic Statistics Textbook. Tulsa, OK: StatSoft. WEB: http://www.statsoft.com/textbook/stathome.html. Lorenzo Camprini === computer programmer, technical assistant in electronics for computer science in a college-level school === Email: [EMAIL PROTECTED] === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
Re: split half reliability
At 12:55 PM 4/19/00 +1000, you wrote: >Paul R Swank wrote: >> >> High alpha can be obtained when not all items are highly intercorrelated >> with all the other items but it requires having enough items. Lack of item >> homogeneity will certainly be greater problem with short scales. With >> respect to the Spearman-Brown, I don't recommend it. I prefer the >> Guttman-Flanagan split half which is just a special case of alpha for two >> items. >> >I would agree with everything you've said here, but I still would press >you to explain what, exactly, you mean, when you use the term >"homogeneity". Item homogeneity means essentially tau equivalent items. That is, each item has expected value of tau plus a constant. Thus, they are all measuring the same construct. >I'm not familiar with the Guttmann-Flanagan formula, and I'd be pleased >if you would describe it. From your description, it sounds like the >following: >rel = 1 - H/T >where H = sum of the variances of the two split half scores >T = variance of total test scores. >Is that correct? Exactly. The Guttman-Flanagan split half requires the halves to be essentially tau equivalent rather than parallel as the Spearman-Brown correction requires. > >The question I raised earlier about how one splits the scale into halves >still remains. And your response raises another question: why do you >prefer G-F to Sp-Brown? What is the criterion for "better" here? Because of its reduced assumptions (essentially tau equivalent halves instead of parallel) means the GF split half is not inflated. That is, GF SB. They are only equal when the variances of the halves are equal. Again, having essentially tau equivalent halves is somethimes easier to justify than essentially equivalent items. > >I'll be away from work for the next eight days, back on Friday 28 April. > >Best wishes, thanks for the discussion, >Paul Gardner > >Attachment Converted: "d:\paul\email\attach\Paul.Gardner2.vcf" > Paul R. Swank, PhD. Advanced Quantitative Methodologist UT-Houston School of Nursing Center for Nursing Research Phone (713)500-2031 Fax (713) 500-2033 === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
density of integral(RV(t)~f(t), 0..T, dt)
Does anyone know if there's an answer to the following problem: I'm given a function of time Y(t), with the property that all values of Y are random variables which are drawn from a time dependent distribution with known time dependent density f(t). I.e. the probability that Y(t)x is Integral(f(t),-inf..x,dt): d/dx P( Y(t) x ) = f(t) With these facts given, is there anything that can be said about the distribution of Integral(Y(tau), 0..t, dtau) ?? or its density function? Is there a nice expression for that in terms of the known density f(t) in general? or maybe with specific assumptions about f? (E.g. Gaussian with mean(t) and var(t)) I'd greatly appreciate answers to any of these questions or any references that might deal with this problem. Thanks, Thomas Burg Dept. of Physics, Swiss Federal Institute of Technology [EMAIL PROTECTED] === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
Using ANOVA or Regression to analyze ordinal data?
Dear all, I am confused by the following question: The 5-point scale is obvious ordinal scale, while the bipolar scale can be interval scale. However, we usually use analyses such as ANOVA, Regression, etc. to analyze the collected 5-point data. Is there any reasoning behind it? Please indicate me references, if possible. Thanks for your help! Wen-Feng === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
density of integral(RV(t)~f(t), 0..T, dt)
Can't be done without knowledge of the joint distributions of Y(t1), Y(t2),..., Y(t). Jon Cryer --- Text of forwarded message --- X-Authentication-Warning: jse.stat.ncsu.edu: majordom set sender to [EMAIL PROTECTED] using -f To: [EMAIL PROTECTED] Date: Wed, 19 Apr 2000 16:46:32 +0200 From: Thomas Peter Burg [EMAIL PROTECTED] Organization: University of Illinois at Urbana-Champaign Reply-To: [EMAIL PROTECTED] Subject: density of integral(RV(t)~f(t), 0..T, dt) Sender: [EMAIL PROTECTED] Precedence: bulk Does anyone know if there's an answer to the following problem: I'm given a function of time Y(t), with the property that all values of Y are random variables which are drawn from a time dependent distribution with known time dependent density f(t). I.e. the probability that Y(t)x is Integral(f(t),-inf..x,dt): d/dx P( Y(t) x ) = f(t) With these facts given, is there anything that can be said about the distribution of Integral(Y(tau), 0..t, dtau) ?? or its density function? Is there a nice expression for that in terms of the known density f(t) in general? or maybe with specific assumptions about f? (E.g. Gaussian with mean(t) and var(t)) I'd greatly appreciate answers to any of these questions or any references that might deal with this problem. Thanks, Thomas Burg Dept. of Physics, Swiss Federal Institute of Technology [EMAIL PROTECTED] === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ === _ - | \ Jon Cryer[EMAIL PROTECTED] ( ) Department of Statistics http://www.stat.uiowa.edu\ \_ University and Actuarial Science office 319-335-0819 \ * \ of Iowa The University of Iowa dept. 319-335-0706\ / Hawkeyes Iowa City, IA 52242FAX319-335-3017 | ) - V === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
Re: Software for robust stats?
In article 8dj5g7$5er$[EMAIL PROTECTED], wende598@my- deja.com says... Hi, I'm a grad student in social science. My use of satistics software has been limited to SPSS because its simple user interface allowed me to easily do some simple non-parametric tests. But now, I am interested in trying some resistant analysis techniques I have read about, but they don't seem to be included in our lab version of SPSS 9.0. Splus (www.mathsoft.com) has many robust techniques and they have a new beta library on usable robust methods. ez === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
amigos-ML: Teste - Para apagar !
__ "Alexandre Martins Lima" [EMAIL PROTECTED] Wrote: ___ Teste --- * Mailing list dos amigos * Para receber informações da lista envie uma mensagem para [EMAIL PROTECTED] * Com o comando help no corpo da mensagem === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
Re: Using ANOVA or Regression to analyze ordinal data?
On 19 Apr 2000 16:30:07 GMT, [EMAIL PROTECTED] (Wen-Feng Hsiao) wrote: The 5-point scale is obvious ordinal scale, while the bipolar scale can be interval scale. However, we usually use analyses such as ANOVA, Regression, etc. to analyze the collected 5-point data. Is there any reasoning behind it? Please indicate me references, if possible. If a 5-point scale was created or adapted for a study with any attention to detail, then it will be pretty close to "equal interval" by intention, and probably by result. If a scale has only 5 points, then there will be a whole lot of ties when you apply the rank-order transformation. If you read your statistical texts closely, you will see that they raise some doubts about using ranks when there are ties. Agresti has a good example of alternative, competing scorings for a few derived categories, in each of his books on categorical analyses. I think you have been exposed to the prejudices of a few Experimentalists in psychology and education, who were overly-impressed--for a little while, about 30 or 40 years ago--with the miracles of "nonparametric analyses which don't need any assumptions!" A 5-point scale happens to be "ordinal" which is a word that impressed a few people; but it is not well suited to rank-transforming (the ad-hoc solution for ties is not great). There were few (no?) credible sources that ever recommended ranking the 5-point scores, as far as I know--and I have asked about this before. So, statisticians have not considered the question especially noteworthy. (And, I am curious, Do recent Experimental Design texts say anything?) -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
effect size
is there a standard error ... for an effect size? as an example ... say you were looking at differences between means between control and treatment ... and, the effect size came out to be ... for sake of argument ... .3 ... in favor of the treatment is there (in this case) some standard error ... that could be used to judge this value in terms of sampling error? and if so, how would one go about calculating it? === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
power and what it says
let's say that one designs a simple experiment about the effectiveness of a weight change program ... you set your sights on a power of .7 ... (beta therefore being .3) ... select a two tailed alpha of .05 ... because the situation is such that this program could actually make you gain weight though you hope that it will help you lose weight now, let's assume that you want to detect an effect of 3 pounds ... either gain or loss ... and you therefore go about estimating the n needed to achieve this goal of being able to reject the null with a p of .7 ... if in fact the null is not true ... and the gap between the null and the center of the treatment effect distribution being 3 ... now, what if you execute your study rigorously with the n you estimated you would need ... and then reject the null with a p = .02 (for illustration purposes only) ... at the moment, don't worry if it is a gain or loss ... just that you reject the null here is my question (you were wondering when i would get to it, right?) WHAT CAN WE SAY, BASED ON THIS REJECTION OF THE NULL, about the treatment effect being 3 lbs OR more ... ? what confidence do we have that the treatment effect is AT LEAST 3 lbs? === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
Early bird registration-StatHealth Conference
Our sincere apologies for cross posting! Thank-you. --- This is a reminder for an early bird registration for the STATISTICS AND HEALTH CONFERENCE, June 11-13, 2000, Edmonton, Canada. DEADLINE FOR REGISTRATION AND HOTEL ACCOMMODATION: May 1, 2000 = REGISTRATION DETAILS are available directly from: http://www.stat.ualberta.ca/~brg/conference/registration.html MAJOR THEMES INCLUDE: Spatial mapping and small area estimation Meta analysis and errors in estimation Genetic Epidemiology and Methods Cost, Cost effectiveness and decision analysis Hierarchical models: New developments Correlated data in health research INVITED SPEAKERS: Professor Bradley Efron (Stanford); Professor M. Daniels (Iowa State). Professor Lawson (Aberdeen); Professor K-Y Liang (Johns Hopkins); Professor C. McCulloch (Cornell); Professor S-L Normand (Harvard); Professor JNK Rao (Carleton); Professor L. Waller (Emory); Professor K. Morgan (McGill); Professor S. Walter (McMaster); Professor C. Dean (Simon Fraser); Professor C. Gatsonis (Brown); Dr. J. Gentleman (NCHS); Professor S. Bull (Toronto); Professor S. Greenland (UCLA); Professor P. Heagerty (Washington); Professor Moher (Ottawa); Professor H. Bryant (Calgary); Professor J. Berlin (Pennsylvania); Professor W. Manning (Chicago); Professor MC Wang (Johns Hopkins). FOR OTHER DETAILS, SEE: http://www.stat.ualberta.ca/~brg/conf.html == Biostatistics Research Group, Statistics Centre, Mathematical Sciences 632 Central Academic Bldg. University of Alberta Edmonton, AB, T6G 2G1 Webpage: http://www.stat.ualberta.ca/~brg Tel: 780-492-3396Fax: 780-492-6826 == === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===
Re: density of integral(RV(t)~f(t), 0..T, dt)
In article [EMAIL PROTECTED], Thomas Peter Burg [EMAIL PROTECTED] wrote: Does anyone know if there's an answer to the following problem: I'm given a function of time Y(t), with the property that all values of Y are random variables which are drawn from a time dependent distribution with known time dependent density f(t). I.e. the probability that Y(t)x is Integral(f(t),-inf..x,dt): d/dx P( Y(t) x ) = f(t) With these facts given, is there anything that can be said about the distribution of Integral(Y(tau), 0..t, dtau) ?? or its density function? With the information given, all that can be stated is that the expected value of the integral is the integral of the expected value. The Y(t) had better be independent, or if the integral makes sense, it is going to be a constant almost surely. So to do anything with the distribution, it will be necessary to know the nature of the dependence. Is there a nice expression for that in terms of the known density f(t) in general? or maybe with specific assumptions about f? (E.g. Gaussian with mean(t) and var(t)) One also would need the covariance cov(t,u). If there is a reasonable amount of measurability, the variance of the integral is the double integral of the covariance function. If the joint distributions are normal, the integral will also be normal. But one still needs the covariance function, not just the variances. However, for general distributions, more information is needed to do anything about the distribution. Simple answers are not always forthcoming. -- This address is for information only. I do not claim that these views are those of the Statistics Department or of Purdue University. Herman Rubin, Dept. of Statistics, Purdue Univ., West Lafayette IN47907-1399 [EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558 === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Please DO NOT COMPLAIN TO THE POSTMASTER about these messages because the postmaster has no way of controlling them, and excessive complaints will result in termination of the list. For information about this list, including information about the problem of inappropriate messages and information about how to unsubscribe, please see the web page at http://jse.stat.ncsu.edu/ ===