Re: Chernoff faces

1999-01-17 Thread Rich Ulrich
tats-FAQ. (By 1985 or so, there had been twenty years of stepwise prediction equations in the social sciences that "failed to replicate"; that was noticed, even by the folks who were not strong in math.) -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: stats. question

1999-11-24 Thread Rich Ulrich
rs. However, 5 vs. 5 is not a powerful design. And, as I said, she seems to have in her hands a t-test between means, and not anything more. Comparing ratios is what you do with log-normal -- which is not a good model for counts. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Disadvantage of Non-parametric vs. Parametric Test

1999-12-08 Thread Rich Ulrich
transformation does. If it were proper terminology to say randomization is nonparametric, you would probably want to say bootstrapping is nonparametric, too. (I think some people have done so; but it is not widespread.) -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Scale Reliability

1999-12-10 Thread Rich Ulrich
they tested as consistent, then an alpha of .30 is indication that something went wrong. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

hoax. Was -- Re: [Fwd: [Fwd: EMAIL]]

1999-12-14 Thread Rich Ulrich
will be catastrophe on January 1, owing to a drop of 70% or 85% in world-wide oil production. I will sent that vital discussion on to you, if you need something SERIOUS to worry about. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: ANOVA with proportions

1999-12-15 Thread Rich Ulrich
continuous variables that have been re-expressed as their *rank-transformed values*. That applies for essentiall the same set of models -- multiway, multi-variable, or high R-squared. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: ANOVA with proportions

1999-12-15 Thread Rich Ulrich
rates 0/20=0%. I am not referring just to zero -- if subjects have data based on vastly different Ns, it may be wasteful to lump them based on percents. One approach that seemed useful for some analyses of genotypes was: do separate analyses for different N, and then combine those analyses.

Re: urgent: Mauchly shericity

1999-12-16 Thread Rich Ulrich
Posted also to sci.stat.edu, where the same question appeared. On Thu, 16 Dec 1999 00:03:58 +0100, EikeRietzel [EMAIL PROTECTED] wrote: Hi, I have a very urgent problem concerning GLM (repeated measures). The Mauchly sphericity test prints out: Mauchly-W = 0.000 approx-chi2 = . df = 9

Re: teaching statistical methods by rules?

1999-12-16 Thread Rich Ulrich
to seeing a few examples by Monte Carlo.. But I can't do that myself, for every topic. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Prediction Model Question

1999-12-17 Thread Rich Ulrich
mething*. For one, if it has "effects coding" in my sense, it won't be exactly (-1,0,1).I don't find anything like what you say, in my copy of Kerlinger/Pedhazur (1973) -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Correlation conversion

1999-12-17 Thread Rich Ulrich
eme values, and extreme disagreements, than Spearman's rho is, which (in turn) is less sensitive than r. Or, you could say, tau is more sensitive to having a *lot* of minor disagreements They measure differently, and don't map 1-to-1. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: correlation

1999-12-17 Thread Rich Ulrich
to expect some other sort of correlation. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Factor analysis

1999-12-19 Thread Rich Ulrich
factor structure'? And what is goal is "overcome" supposed to indicate? If there are two factors, you can provide the outcome of your survey as two composite scores instead of just one. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Difference between means

1999-12-21 Thread Rich Ulrich
sons doing the trials. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: chi sq arbitrary sample size

1999-12-21 Thread Rich Ulrich
interfere? I sure would hope that firefighters have at least a little bit of effectiveness, so that for areas that are identical except that some acres have homes (and will be protected), the ones with homes have fewer fires. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib

Re: Prediction Model Question

1999-12-22 Thread Rich Ulrich
that they are not strictly interpretable for most sets of coefficients. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Correlation conversion

1999-12-22 Thread Rich Ulrich
attributing a quote. Well, along with clearing up the attribution, you also may have disabused those readers who could have walked away thinking that the Bible had some lines about Pearson correlations. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

anti-SPAM? was: [Re: Difference of means]

1999-12-22 Thread Rich Ulrich
ewhere, I think that your name is far more likely to be gleaned from websites that you visit.Though, it is possible that some *other* particular newsgroups happen to be a place where Spammers harvest names. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: comparison of kappa coefficients

1999-12-29 Thread Rich Ulrich
; is different, mainly, in that it identifies more or fewer cases, but with complete overlap. Hope this helps, and wasn't too confusing. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Correlation - Constraints on Variables

2000-01-02 Thread Rich Ulrich
uous or discrete, then the test may have that kind of error. With outliers, the test on r will be more accurate if you pretend that you have fewer degrees of freedom -- sometimes, just a couple DF despite a large N. The Cohen/Cohen book on Applied Multiple Regression/Correlation might be helpful fo

Re: Distribution generator for simulator in C++

2000-01-11 Thread Rich Ulrich
spired a guesser your advisor may be. BUT YOU win (and deserve) a reputation as a flake, an unreliable screw-up, if you miss an important, *obvious* issue, even once per 10. Or something like that. And if you knew what was "obvious" then you wouldn't be asking for that advice. --

Re: grades approximated by multinomial?

2000-01-13 Thread Rich Ulrich
For most comparisons, it would probably be more fruitful to look at the Averages. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: help: independence of data

2000-01-13 Thread Rich Ulrich
relational structure is a really big Unknown, which prevents an easy use of bootstrap. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Help: How to analyze weight-loss data

2000-01-17 Thread Rich Ulrich
design? The sets of 42 readings don't serve as a time series for any hypothesis that was mentioned, so averaging is the right way to start. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Prediction Model Question (long)

2000-01-17 Thread Rich Ulrich
t time I want to comment on coefficients. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: Skewed Data Problem

2000-01-19 Thread Rich Ulrich
son, "zero vs one vs other" -- Does this give an ordered set of values/scores for any of the other variables? -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: probability of a boy

2000-01-25 Thread Rich Ulrich
Note, "substantially". Huge datasets haven't been enough, yet. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect

Re: Sig. of correlation and t-test

2000-01-27 Thread Rich Ulrich
e in means. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect for other members of the list send messages that are ina

Re: Likert scale( nonmetric or metric scale)

2000-01-31 Thread Rich Ulrich
0, next-low=2.0, next_a= 2.2, next_b=2.3, next_c=2.5} -- or whatever, to see how the scoring compares to {1,2,3,4,5}. Agresti's textbooks give a detailed example. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html ===

Re: TEST MESSAGE

2000-01-31 Thread Rich Ulrich
it, or it will be gone from them. With a little more difficulty, though, [GOOD] the message is *never* gone, because you can fetch it from DejaNews or ReMarq (assuming it was not posted with X-NoArchive: Yes). Hope this helps. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib

Re: probability of a boy

2000-02-04 Thread Rich Ulrich
In response to, Rich Ulrich wrote: snip Prior to artificial insemination, sperm can be sorted by weight in a centrifuge, since sperm with Y-chromosomes generally weigh less than the X-chromosomes, by the amount of that extra arm. (It was not in that article, but I think I

Re: ANOVA

2000-02-06 Thread Rich Ulrich
nt to test? -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect for other members of the list send messages that are ina

Re: Max R-sq for Binary Data

2000-02-06 Thread Rich Ulrich
in the question more slowly? -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect for other members of the list send messages th

Re: Tukey test in two-way ANOVA

2000-02-07 Thread Rich Ulrich
for the price of one? No. (How much space does your textbook want to devote to this topic?) If the textbook explanation of the logic is not clear, you might try the original references -- where the authors are the experts and have more pages available. -- Rich Ulrich, [EMAIL PROTECTED] http

Re: ANOVA/ MANOVA

2000-02-08 Thread Rich Ulrich
e difference and put it into a new preference-variable, pref_a = (att_a - att_b) ; and test that variable with a t-test. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to ev

Re: ANN vs. nonlinear regression: forecasting

2000-02-11 Thread Rich Ulrich
on. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect for other members of the list send messages that are inappropriate

Re: panel data with binomial dependant variable

2000-02-13 Thread Rich Ulrich
there are covariates for each individual. Look for comparable literature in your own area. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, people lacking respect

Re: Transformations

2000-02-13 Thread Rich Ulrich
h an extreme outlier), such a strategy fails because it over-capitalizes on chance. (Dealing with an outlier is not a trivial matter.) In a large, healthy sample, the ANOVA is robust, or a simpler, intentional transformation can be defended. Also, the Ideal transformation may fall outside of that fami

Re: Bug in SPSS or SYSTAT regression ?

2000-02-24 Thread Rich Ulrich
vention, already, in your area of specialty, then you have enough troubles explaining why you used that regression ... without getting into the details of *that* adjusted R-squared. -- Rich Ulrich, [EMAIL PROTECTED] http://w

Re: Regression question

2000-02-24 Thread Rich Ulrich
this context. When the data are ordered, in a meaningful way, then that is something that might become a factor -- statistically speaking -- in the analysis. You might have to find someone to speak to, with your data in hand, in order to clear up those descriptions. -- Rich Ulrich, [EMAIL PROTECTED

Re: Regression question

2000-02-23 Thread Rich Ulrich
you might want to use the mid-point of the range implied by that categorical response. For two coin-flips, there are 0.25 responses with more heads than 1, 0.25 with fewer, and the midpoint of the category with 1 head is 0.50 -- while 0.75 is the cumulative probability, for 1 or fewer. --

Re: What to study next

2000-03-01 Thread Rich Ulrich
own sorts of statistical designs. To learn what to do in various situations, I think you have to *read*, you have to be exposed to a large number of various situations. You have to read some good examples, and you have to read criticisms which include examples that were not-so-good. -- Rich Ulrich, [EMAIL

Re: Weighted Kappa

2000-03-05 Thread Rich Ulrich
r accuracy: you will vastly reduce your complexity if you designate a modal score, or a "gold standard" of a correct score. Then you will have 16 comparisons instead of 120 (or, does order matter?) -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.ed

Re: Post Hoc Analysis

2000-03-09 Thread Rich Ulrich
On Thu, 09 Mar 2000 20:20:47 GMT, [EMAIL PROTECTED] wrote: ... 1 Independent Variable (Group) 13 Dependent Variables (various IQ and cognitive testing scores) The MANOVA was significant and I wanted to perform post hoc tests on Group. Here then is the caviat: GroupN 1

Re: When *must* use weighted LS?

2000-03-14 Thread Rich Ulrich
would try to clean up my data or justify it, instead of weighting. But there are other areas (certain survey research) where the use of weighting -- for various reasons that probably do not match yours -- is the standard option. Maybe someone else will add to this -- Rich Ulrich, [EMAIL

Re: Multiple Comparison Correction in Multiple Regression

2000-03-17 Thread Rich Ulrich
ferences. (If you are worried about correcting for multiple tests, then you probably *shouldn't* add the variable because it is probably capitallizing on chance.) -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html ===

Re: Multiple Comparison Correction in Multiple Regression

2000-03-19 Thread Rich Ulrich
y about it, but I don't include it in my Hypothesis test -- unless it has been elevated, beforehand, to be a separate aspect of the main hypothesis. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html =

Re: Logistic Regression

2000-03-23 Thread Rich Ulrich
ust as bad an idea as it is for OLS regression. Especially relevant for small N: Note that logistic is even *worse* than OLS about capitalizing on chance. You can read about stepwise, and references, in my stats-FAQ. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/

Re: Sample size: way tooo big?

2000-03-23 Thread Rich Ulrich
CI's as an "effect" when the test is barely at 5%; the range is just LARGE. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less

Re: successive intervals?

2000-03-24 Thread Rich Ulrich
es similar methods under other names which date back to the 1930s. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send ina

Re: Kruskal-Wallis equal variances

2000-03-24 Thread Rich Ulrich
egion. I have made statements on this before. I am still trying to get it all complete and concise. I think I will have a bit to add to the above, on Sunday. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html ===

Re: Pooled Cross-sectionnal time-series regression

2000-03-26 Thread Rich Ulrich
tion about joining various mailing lists. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages.

Re: Sample calculations? :)

2000-03-28 Thread Rich Ulrich
. For any real data, compute the CI of the difference. If your sample is huge, and the difference is small, you might be able to conclude that the 95% CI of the difference is less than XXX, for your small XXX. If you need help in computing a Confidence Interval, please hire a consultant. -- Rich

Re: Sample size: way tooo big?

2000-03-28 Thread Rich Ulrich
, delete, some other topics -- 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 COMPLA

Re: bivariate normal

2000-03-29 Thread Rich Ulrich
en you see it edge-on, as just a single straight line, which similarly fades out, at the extremes. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less

Re: How to subscribe in the List about IRT?

2000-03-29 Thread Rich Ulrich
://www.stattransfer.com/lists.html - has all the advertised stats lists, and automates the subscription process. You'll have to see if anything comes close enough for you. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: request for suggestions regarding meta-analysis

2000-04-04 Thread Rich Ulrich
lysis is like trying to convert your "dollars" for a shopping trip to New York City -- neither rubles nor cartons of cigarettes would be nearly so negotiable in NYC, though they serve a similar function in other parts of the world. -- Rich Ulrich, [EMAIL PROTECTED] http://w

Re: Kolmogorov-Smirnov vs Chi Square

2000-04-04 Thread Rich Ulrich
that does treat them as Ordered, whether you collapse them into categories or not. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful

Re: Kolmogorov-Smirnov vs Chi Square

2000-04-05 Thread Rich Ulrich
st on a good range of "general" alternatives. The last one has a subjective element, since different folks are apt to have their own experiences that they would prefer to see weight given to, of what the general alternatives ought to look like. -- Rich Ulrich, [EMAIL PROTECTED

Re: hyp testing

2000-04-10 Thread Rich Ulrich
show that the amount is definitely less that the Upper limit, and definitely greater than the lower. Basically, you need to construct a Confidence interval on the difference and have it fall completely within the limits. -- Rich Ulri

Re: scientific method

2000-04-12 Thread Rich Ulrich
d the Growth of Knowledge" (Lakatos, ed.). This book happens to be from the proceedings of a symposium devoted to exploring Thomas Kuhn's thesis about revolutions in scientific discovery, and it is a modern classic. -- Rich Ulrich, [EMAIL PROTECTED] http://w

Re: Nonpar Repeated Measures

2000-04-13 Thread Rich Ulrich
-way ANOVA -- safer, I suspect, than anything you can do with ranking as the first step. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful p

Re: normal distribution

2000-04-14 Thread Rich Ulrich
s been dated to Jouffret, 1872 -- who was (particularly) describing the bivariate normal. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less though

Re: Data Mining

2000-04-14 Thread Rich Ulrich
cipation drove their prices up. -- 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 CO

Re: Data Mining

2000-04-17 Thread Rich Ulrich
( how did we get to HERE, from Data Mining?) On 15 Apr 2000 17:50:05 GMT, [EMAIL PROTECTED] (Radford Neal) wrote: In article [EMAIL PROTECTED], Rich Ulrich [EMAIL PROTECTED] wrote: One thing that remains true about stock investment schemes: There may be some overall growth, somewhere

Re: hyp testing -Reply

2000-04-18 Thread Rich Ulrich
right now -- is that of framing questions as hypotheses. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages.

Re: Finding statistical significance between 2 groups with categorical variables

2000-04-18 Thread Rich Ulrich
fair hypothesis, to ask about the presence of (X) and (Y) separately; but you should tell about them, as descriptors. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to

Re: The best effect size

2000-04-18 Thread Rich Ulrich
that he was careful not to overgeneralize about r and d . His levels seem to have *little* to do with your debate, since your studies are a-typical. He is talking about "the usual studies" in Social Sciences. Those are ones that do *not* have a rare, dichotomous occurrence as an outcome. -- Rich

Re: Using ANOVA or Regression to analyze ordinal data?

2000-04-19 Thread Rich Ulrich
e 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 ===

Re: How to compare kappas?

2000-04-20 Thread Rich Ulrich
to define a purpose. In what fashion is something expected to be better or worse? -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful p

Re: power and what it says

2000-04-20 Thread Rich Ulrich
ST 3 lbs? It depends how much of the CI is above 3.0, doesn't it? -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inap

Re: Hypothesis testing and magic - episode 2

2000-04-20 Thread Rich Ulrich
ver stop growing. That seemed to tie in to the rat-life-spans, too. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inap

Re: Using ANOVA or Regression to analyze ordinal data?

2000-04-21 Thread Rich Ulrich
will try to say more, after I have seen it. -- 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

Re: Using ANOVA or Regression to analyze ordinal data?

2000-04-21 Thread Rich Ulrich
On 21 Apr 2000 17:25:01 GMT, [EMAIL PROTECTED] (Wen-Feng Hsiao) wrote: Dear Ulrich, Thanks for your reply. I have obtained a book of Agresti from library -- Statistical Methods for the Social Sciences, 2nd edition. I fortunately locate Section 7.4 titled 'comments concering

Re: Low Reliability.

2000-04-25 Thread Rich Ulrich
. If yours is very narrow question, the answer is that "attentuation" is direct and estimable, and you can look for that word in your table of contents or index. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/

Re: Low Reliability.

2000-04-26 Thread Rich Ulrich
- typographical correction - On Tue, 25 Apr 2000 10:26:02 -0400, Rich Ulrich [EMAIL PROTECTED] wrote: On 24 Apr 2000 07:41:10 -0700, [EMAIL PROTECTED] (Paul W. Jeffries) wrote: Does any one know of good sources--either book chapters or articles--that discuss how low reliability among

Re: Significant negative correlation

2000-04-27 Thread Rich Ulrich
-- by multiplying loadings by minus one when the program detects more signs in the "wrong" direction). If you look at the items and you can't figure why the question is in the "opposite" direction, then maybe you have trouble with your data file, or maybe you really need a pri

Re: Blackjack problem

2000-04-28 Thread Rich Ulrich
with deeper pockets at the start. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Pl

Re: Question about kappa

2000-04-28 Thread Rich Ulrich
design. It entails approximations, so I hope the design is not *too* unbalanced. snip, McGrath sig. snip, Bob Wheeler post; included for no imaginable reason. snip, quoting of Edstat-L message from the bottom of Bob Wheeler's post snip, Edstat-L message -- Rich Ulrich, [EMAIL PROTECTED

Re: Q: error on RMS, __please__ help.

2000-04-30 Thread Rich Ulrich
e discussion). At least it looks like a gaussian, when I histogram it. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people se

Re: Roy's Largest...What?

2000-05-02 Thread Rich Ulrich
k there is a simple effect and (for some reason) you can't describe that in advance. -- Rich Ulrich http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inappro

Re: Statistical Software

2000-05-04 Thread Rich Ulrich
and shorten the output file, using any of three or more different file editors, while I am deciding what to print. snip, about SAS, SPSS, Stata, Excel -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: (none)

2000-05-05 Thread Rich Ulrich
so there's a couple of reasons for you. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inappropriate messages. Pl

Re: bipolar factors

2000-05-10 Thread Rich Ulrich
and-subtracting those high-loading items is not apt to make a very robust total score. I take this as a warning that I may have too many variables for the N, and I should test some smaller subsets. Having more than one or two items with "split-loadings" bothers me the same way. --

Re: Regression Through the Origin

2000-05-12 Thread Rich Ulrich
descriptions of regression. -- 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

Re: misusing stats: examples

2000-05-15 Thread Rich Ulrich
opposed to spending money. I did not realize that the committee might consider themselves on the scientific-cutting edge, having read the BJM. Of course, the non-funding of studies with N *over* 300 is ever-justified because the studies would be too difficult, and/or would cost too

Re: homogeneity of variances - Hartley's F-max

2000-05-16 Thread Rich Ulrich
" ... without taking into account their respective means." -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inap

Re: misusing stats: examples

2000-05-16 Thread Rich Ulrich
nything. This was in the local newspaper. I keep pretty flexible in my expectations for the local newspaper. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to ev

Re: homogeneity of variances - Hartley's F-max

2000-05-17 Thread Rich Ulrich
ld look at them all. With your data rescored as (positive) Difference, you can compute tests within data sets, and between data sets. It sounds as if the ultimate comparison Between data sets might properly use the error term of the "Mean S

Re: obsolete methods?

2000-05-18 Thread Rich Ulrich
u ask their opinions about the president or Congress. But if attitudes are malleable, the measure of personality had to go beyond a simple summation of attitudes, so the previous focus had to change. Does that sound reasonable? -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.ed

Re: Newbie Question

2000-05-19 Thread Rich Ulrich
nse format. -- 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 POSTMA

Re: Distribution Free Tolerance Limits

2000-05-22 Thread Rich Ulrich
berman, Prentice Hall Introduction to Statistical Analysis, 4th Edition, Dixon and Massey, McGraw Hill snip -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to ev

Re: Square root transformation

2000-05-23 Thread Rich Ulrich
ependent variable" when that variable is measured in Counts, then you HAVE to measure it in Counts. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, les

Re: Square root transformation

2000-05-23 Thread Rich Ulrich
On Tue, 23 May 2000 13:49:38 -0700, "G. Anthony Reina" [EMAIL PROTECTED] wrote: Rich Ulrich wrote: me Plus, I've run the multiple regression without the transform and seen only about a 5% difference (not much). - damned

Re: non normal multivariate outlier detection

2000-05-24 Thread Rich Ulrich
h that has been used often, that really makes use of MV settings except for assuming MV normal, and using Mahanalobis Distance. - that I know of. Well, you have to place some faith in your metric for each variable, regardless. Do a nearest-neighbor algorithm, and look for isolates? -- R

Re: correction for attentuation of multiple or canonical correlations

2000-05-24 Thread Rich Ulrich
I can't say what you are comparing, but I think you want to compare directly instead of trying to do adjustments. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone.

Re: Galton

2000-05-26 Thread Rich Ulrich
e recognized that the data did not need to be bivariate Normal. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less thoughtful people send inap

Re: Can I use rank data to do PCA?

2000-05-28 Thread Rich Ulrich
in clinical research and many other places. With dichotomous measures, you might need more, since the correlations are attenuated. With unambiguous structure, you would need less. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html

Re: WHY is heteroscedasticity bad?

2000-06-01 Thread Rich Ulrich
ot;significance" of the correlation depends on the DF. This is not precise, but I maybe it helps ... -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html === This list is open to everyone. Occasionally, less th

Re: standardizing diff rating metrics

2000-06-02 Thread Rich Ulrich
be about your data collection which left these options. The far better technique is to ponder and figure out your scaling/scoring questions before you collect the data. What did you hope to gain by not providing anchors? -- Rich Ulrich, [EMAIL PROTECTED] http://w

  1   2   3   4   5   >