Re: Number of factors to be extracted
On Wed, 3 May 2000, Paul Gardner wrote, inter alia: > I can reduce all this to a single maxim: > Factor analysis is an art as well as a science. ^^ I would have written ... "rather than" ... Cheers! -- Don. Donald F. Burrill [EMAIL PROTECTED] 348 Hyde Hall, Plymouth State College, [EMAIL PROTECTED] MSC #29, Plymouth, NH 03264 603-535-2597 184 Nashua Road, Bedford, NH 03110 603-471-7128 === 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: Number of factors to be extracted
I would add another criterion, which is qualitative, and therefore not reducible to a quantitative rule: 3. Use your professional judgement. Does the pattern of factor loadings make sense? For example, if the variables are item scores on a multi-dimensional instrument, can you see a meaningful connection among the items which load highly on a particular factor? The "eigen-value greater than 1" criterion is very arbitrary, and in interpreting a factor analysis matrix of item scores, I often discard numerous factors which meet the eigen-value criterion but fail to make any sense when I apply my judgement to the pattern of loadings. I can reduce all this to a single maxim: Factor analysis is an art as well as a science. Paul Gardner Alex Yu wrote: > > There are several rules. The most popular two are: > > 1. Kasier criterion: retain the factor when eigenvalue is larger than 1 > 2. Scree plot: Basically, it is eyeballing. Plot the number of factors > and the eigenvalue and see where the sharp turn is. > > Hope it helps. > Chong-ho (Alex) Yu, Ph.D., CNE, MCSE > > On Tue, 2 May 2000 [EMAIL PROTECTED] wrote: > > > Would any of you know a rule of thumb for selecting the proper (of > > optimal) number of factors to be extracted from a factor analysis. > > Also, how many variables can there be in such factor (is two variable > > in one factor not enough?). begin:vcard n:Gardner;Dr Paul tel;cell:0412 275 623 tel;fax:Int + 61 3 9905 2779 (Faculty office) tel;home:Int + 61 3 9578 4724 tel;work:Int + 61 3 9905 2854 x-mozilla-html:FALSE adr:;; version:2.1 email;internet:[EMAIL PROTECTED] x-mozilla-cpt:;-29488 fn:Dr Paul Gardner, Reader in Education and Director, Research Degrees, Faculty of Education, Monash University, Vic. Australia 3800 end:vcard
Re: no correlation assumption among X's in MLR
Hi Don, There are times when I realise the rust that has accumulated, and this is one of them. Changing the order of things a little, you (and D&S) are of course quite correct that X variables are typically correlated, and that if they are not the coefficients are the same as if a set of simple regressions are carried out. Coincidentally, I was pointing this out to a class a couple of days ago - but the class is 'not mathematically able', like most these days, so the explanation was not of course at all technical. Rust.. With regard to correlation and collinearity - I have become used to 'explaining' collinearity to my classes in terms only of pairs of explanatory variables, forgetting that the collinearity could involve a set of three or more variables, and this 'pair-wise no collinearity' is, as I understand it, equivalent to 'no linear correlation'. This suggests, incidentally, that 'not collinear' is stronger than 'uncorrelated' (not *linearly* correlated) which doesn't agree with your statement - is this so? It also suggests that 'collinearity' means more than just 'correlated'. A useful way of picturing the situation is that each variable corresponds to an axis, the angles between the axes determined by the correlation coefficient. (I think, very uncertainly, that the correlation coefficient is the cosine of the angle.) If variables are uncorrelated, the axes are orthogonal; if they are perfectly correlated, the axes are identical. If there is a linear combination between variables, the corresponding dimensions collapse to a 'plane'. (This is all happening in k dimensions.) This corresponds to the matrix X'X having rank less than k (for k variables) so leads (as I understand it) to the collinearity problem. In terms of the data, there is unlikely to be total collapse (just as a sample correlation of exactly zero is highly unlikely) but you might get near collapse. For only two variables highly correlated, the axes are nearly indistinguishable; for three variables you will get a very low hill (this is difficult to describe!). The problem then is to decide whether or not to exclude variables - is the hill high enough to count as three variables, or so low that one variabel should be excluded? I think I stand by my original observation, that *in the data* there is always some evidence of collinearity/correlation; if this evidence is strong enough you have to reduce it by reselecting the variables. In your third paragraph you seem to be identifying collinearity with correlation - more precisely, that the problems with collinearity are those of correlation - and to a large extent identifying 'the trouble' that I spoke of. Thanks for helping to chip off some of the rust. I know there is a lot more. Regards, Alan "Donald F. Burrill" wrote: > On Tue, 2 May 2000, Alan McLean wrote: > > > 'No collinearity' *means* the X variables are uncorrelated! > > This is not my understanding. "Uncorrelated" means that the correlation > between two variables is zero, or that the intercorrelations among > several variables are all zero. "Not collinear" means that there is not > a linear dependency lurking among the variables (or some subset of them). > "Uncorrelated" is a much stronger condition than "not collinear". > > > The basic OLS method assumes the variables are uncorrelated > > (as you say). > > Not as presented in, e.g., Draper & Smith; who go to some trouble to > show how one can produce from a set of correlated variables a set of > orthogonal (= mutually uncorrelated) variables, and remark on the > advantages that accrue if the X-matrix is orthogonal. But it is clear > that they expect predictors to be correlated as a general rule. > > > In practice there is usually some correlation, but the estimates are > > reasonably robust to this. If there is *substantial* collinearity you > > are in trouble. > > If there is collinearity _at_all_ you are in trouble; further, if the > correlations among some of the predictors are high enough (= close enough > to unity), a computing system with finite precision may be unable to > detect the difference between a set of variables that are technically not > collinear but are highly correlated, and a set of variables that _are_ > collinear. (E.g., X and X^4 are not collinear; but if the range of X > in the data is, say, 101 to 110, a plot of X^4 vs X will look very much > like a straight line.) For this reason various safety features are > usually built in to regression programs: variables whose tolerance value > with respect to the other predictors is lower than a certain threshold > (or whose variance inflation factor -- the reciprocal of tolerance -- is > above a corresponding threshold) are usually excluded from an analysis; > although it is often possible to override the system defaults if one > thinks it necessary. The existence of such defaults is clear evidence > that at least the persons responsible for system packages expected that > va
Question: Comparing two groups...
I would like to compare two different groups of prisonners on a psychopathy test (PCL-R, for those who like to know). One has been evaluated on the basis of an interview as well as on the basis of their personal and correctional files. The second group has only been evaluated on the basis of their correctional file. I would like to compare the number of times or the proportion that a certains ratings occurs (presence of a psychopathic characteristic). Say, I want to know if, both groups being similar, we have a tendency to rate subjects differently, with these two different methods. For exemple, one of the characteristics is "lying". I would like to know if there are significant differences etween the ratings of these two groups. What are the proportions of subjects rated as "lying". If in the first group it's 50% and in the second 30%, what test should I use to know if these differences are significant? How can I compare these two independent groups, in such a "parallel" design? I've heard that Joseph L. Fliess discusses that question in his "The design and analysis of clinical experiment" book, but I just can't figure out where... Sorry again for my poor english... Bonne journée Jean-Pierre 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: Roy's Largest...What?
On Tue, 02 May 2000 03:42:52 GMT, Mike and Michele Hewitt <[EMAIL PROTECTED]> wrote: > Can anyone tell me the conditions for using Roy's Largest Root for > multivariate repeated measures rather than the Pillai's, Wilks, or > Hotelling's which may be "more conservative and perhaps less powerful". I know about multivariate; I am less sure about your exact context of "multivariate repeated measures" but I think this applies. The different tests have been written as weighted combinations of the eigenvalues. Wilks test spreads the test across all of the roots of the eigen problem. If the "largest root" is what is interesting, then you think the important effects are in the first eigenvector. I usually think the effect will be an obvious, first-eigenvector effect; but I also think that I should be able to define the contrast in advance: So I can do a t-test (say) on an obvious "Summary score" instead of doing an obscure test on an newly defined vector. Since it does not have to reckon on capitalizing on chance, the test on the summary will be more powerful -- unless I have been badly mistaken in defining it. You use Roy's if you think 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 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: Number of factors to be extracted
There are several rules. The most popular two are: 1. Kasier criterion: retain the factor when eigenvalue is larger than 1 2. Scree plot: Basically, it is eyeballing. Plot the number of factors and the eigenvalue and see where the sharp turn is. Hope it helps. Chong-ho (Alex) Yu, Ph.D., CNE, MCSE Instruction and Research Support Information Technology Arizona State University Tempe AZ 85287-0101 Voice: (602)965-7402 Fax: (602)965-6317 Email: [EMAIL PROTECTED] URL:http://seamonkey.ed.asu.edu/~alex/ On Tue, 2 May 2000 [EMAIL PROTECTED] wrote: > Would any of you know a rule of thumb for selecting the proper (of > optimal) number of factors to be extracted from a factor analysis. > Also, how many variables can there be in such factor (is two variable > in one factor not enough?). > > Sorry for my english... > > > 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/ > === > === 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: Statistical Software
As a statistician who works on large class-action lawsuits for various attorneys, I respond by saying that I do all work for these cases in Stata (http://www.stata.com) and I use both DBMS/COPY and Stat/Transfer for import and export issues. The speed, flexibility and power of Stata are, for these purposes, unrivalled in my opinion -- and, in fact, I know of at least one opposing law firm that bought Stata just so they could easily check my work. Rich Goldstein [EMAIL PROTECTED] wrote: > > I'm the original postee, and this is why I asked the question. I'm a > computer analyst for a large law firm. Most of my work is involved in > large class action lawsuit, where I need to gather, organize and store > mounds of data. From time to time I will need to perform some > statistical work on this data. Usually the law firm will contract out > this work, since as an employee I am not qualified to be an expert > witness when it comes to statistical evidence. However my job is a new > position for this law firm and they would like to perform some in house > statistical work not only for comparison to the outside consultants but > for internal questions as well. What type of statistical work I will be > performing is unknown at this time. Hopefully from the type of data I'm > collecting, someone can determine what statistical package is best > suited for my needs. I would ask the consultants we work with, but was > instructed not to. > > Thanks > > 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/ ===
Number of factors to be extracted
Would any of you know a rule of thumb for selecting the proper (of optimal) number of factors to be extracted from a factor analysis. Also, how many variables can there be in such factor (is two variable in one factor not enough?). Sorry for my english... 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 is the logarithmic distribution? (many questions)
Vincent Vinh-Hung wrote: > General question, > I've seen two descriptions of "logarithmic distribution". > One is related to the frequency of digits called Benford's law (digit 1 > occurs more frequently than 2, 2 than 3, etc) whose explanation is that > it is the result of a mixture of distributions. > The other description is a 2-page paragraph The logarithmic distribution > in Kendall and Stuart (1977, The Advanced theory of statistics, Vol 1, > 4th edition, pp 139-140), attributing the derivation to Fisher (1943). > Are these concepts of logarithmic distribution the same or not? > > Second question I would like to ask: Kendall and Stuart give an > example of a distribution of the logarithmic type from Fisher (1943), > "distribution of butterflies in Malaya, with theoretical frequencies > given by the logarithmic distribution" > No. of species Theoretical frequency Observed frequency > 1 135.05 118 > 2 67.33 74 > 3 44.75 44 > 4 33.46 24 > 5 26.69 29 > 6 22.17 22 > 7 18.95 20 > etc ... > From what I've understood, the theoretical frequency was generated > by > - ( q^r ) / ( r * ln(1-q) ) > in which r is the No. of species, q is the probability of the presence > of an attribute. > How was, how can the fit be realized? You will need a value of q first. This will either be estimated from the raw data or assumed by some hypothesis. Once you have this just plug in the value of r you want and multiply the resulting probability by the sum of the observed frequencies. You might also be able to use the theorectical mean q/((q - 1 )*Log[1 - q]) to estimate q by equating it to the sample mean and solving for q. > > > With thanks in advance, > Vincent Vinh-Hung -- Dr Graeme Byrne La Trobe University, Bendigo PO Box 199, Bendigo, 3552 Phone: 61 3 5444 7263 Fax: 61 3 5444 7998 [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: Statistical Software
but, another alternative is to think about not ONE package ... but perhaps 2 ... sure, to become comfortable with both, it takes more time BUT, many packages allow for pretty good inter changeability of worksheets AND ... there are some student editions that would keep the cost down ... i would suspect that for some things you might want to do ... package A might be best ... whereas for other things ... maybe package B would be better ... in fact, there actually are many many ONLINE routines that might be satisfactory for your purposes ... ONCE you discover what these are ... have a look at ... http://members.aol.com/johnp71/javastat.html At 01:34 PM 5/2/00 +, [EMAIL PROTECTED] wrote: > Hopefully from the type of data I'm >collecting, someone can determine what statistical package is best >suited for my needs. I would ask the consultants we work with, but was >instructed not to. > >Thanks === 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: Statistical Software
On Tue, 02 May 2000 13:34:49 GMT, [EMAIL PROTECTED] wrote: >In article <[EMAIL PROTECTED]>, > [EMAIL PROTECTED] (SAlbert) wrote: >> Cheryl makes a good point: the "right" package depends on what the >user wants >> to do. MINITAB might be a good choice -- or SPSS, or any of dozens of >others. >> Is the application area psychology? Biology? Economics? >Meteorology? >> Demography? Chemistry? Do we need regression? Cross-tabs? Time >series? >> Design of Experiments? >> The original question can't have a general answer that's correct >for >> everyone. If the original poster could provide a little more >information about >> needs, we could be a lot more helpful. >> >> Steve Albert >> > >I'm the original postee, and this is why I asked the question. I'm a >computer analyst for a large law firm. Most of my work is involved in >large class action lawsuit, where I need to gather, organize and store >mounds of data. From time to time I will need to perform some >statistical work on this data. Usually the law firm will contract out >this work, since as an employee I am not qualified to be an expert >witness when it comes to statistical evidence. However my job is a new >position for this law firm and they would like to perform some in house >statistical work not only for comparison to the outside consultants but >for internal questions as well. What type of statistical work I will be >performing is unknown at this time. Hopefully from the type of data I'm >collecting, someone can determine what statistical package is best >suited for my needs. I would ask the consultants we work with, but was >instructed not to. > >Thanks > You have two related problems. One is acquire data from various sources. Two is to do some amount of analysis. There are a variety of data translators available. DBMS/Copy etc. There are a variety of statistical packages available. S-Plus, DataDesk, JMP, MiniTab, etc. You have made it sound like the packages directed at exploaroty data analysis will be more likely to meet your needs for a variety of ad hoc first looks in the presence of many data problems. > >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/ ===
Question: References for run charts.
All - I'm looking for references on the analysis of run charts - that is, plots of data arranged in time sequence. They are similar to Shewhart (Control) Charts, but are not as powerful and are typically used when the number of time points is too small for control chart analysis. I have a list of rules which I came across which are used to determine "significant" trends such as runs up or down and runs to the median, but I'm looking for a reference for these rules. If a list member could help, I'd greatly appreciate it. Thanks. Eric Scharin === 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: Statistical Software
In article <[EMAIL PROTECTED]>, [EMAIL PROTECTED] (SAlbert) wrote: > Cheryl makes a good point: the "right" package depends on what the user wants > to do. MINITAB might be a good choice -- or SPSS, or any of dozens of others. > Is the application area psychology? Biology? Economics? Meteorology? > Demography? Chemistry? Do we need regression? Cross-tabs? Time series? > Design of Experiments? > The original question can't have a general answer that's correct for > everyone. If the original poster could provide a little more information about > needs, we could be a lot more helpful. > > Steve Albert > I'm the original postee, and this is why I asked the question. I'm a computer analyst for a large law firm. Most of my work is involved in large class action lawsuit, where I need to gather, organize and store mounds of data. From time to time I will need to perform some statistical work on this data. Usually the law firm will contract out this work, since as an employee I am not qualified to be an expert witness when it comes to statistical evidence. However my job is a new position for this law firm and they would like to perform some in house statistical work not only for comparison to the outside consultants but for internal questions as well. What type of statistical work I will be performing is unknown at this time. Hopefully from the type of data I'm collecting, someone can determine what statistical package is best suited for my needs. I would ask the consultants we work with, but was instructed not to. Thanks 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: Roy's Largest...What?
Tatsuoka, M. (1988), Multivariate Analysis, has a few pages that discusses some of the different situations where one criterion might be preferred over another. rb --- Mike and Michele Hewitt wrote: Hope that got your attention:) Can anyone tell me the conditions for using Roy's Largest Root for multivariate repeated measures rather than the Pillai's, Wilks, or Hotelling's which may be "more conservative and perhaps less powerful". TIA, Mike === 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/ === --- end of quote --- === 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: Statistical Software
In article <[EMAIL PROTECTED]>, [EMAIL PROTECTED] says... > It depends. > What kinds of stat will you do? > How much value do you put on your time? > What disciplines do you work with? > Who can you get help from? > Who will go over you syntax and outputs to check your work? > > If you need to do a great deal of data transformation (e.g., recoding) > and will be dealing with many kinds of data from different sources, > then I would choose SPSS. It has the best human factors in GUI, > consistency of syntax across procedures, vocabulary choice, clarity of > documentation, and clarity of syntax code. > I don't agree with this description of SPSS at all. I would say its syntax is the worst I've seen (compared to SAS, Stata, GLIM, BMDP). SPSS syntax is unnecessarily verbose and certainly not consistent across procedures. SPSS is good at elementary operations such as recode but poor at advanced applications such as arrays, macros. It does have a good GUI and its documentation is excellent. An important advantage is that SPSS is well known, a lot of data is available in SPSS format and text books often contain sample SPSS code. SAS is another of the big players, sample code is common although data in SAS format less so. It's got a much better command syntax than SPSS, very extensive. Unfortunately, SAS is weak at some of the elementary operations such as a recode, assigning value labels. In the 90s, SAS focussed on business solutions and its statistical capabilities stagnated. However, a new version was released this year, maybe they're picking it up again. I've started using Stata recently and it's quite good. It has a very consistent syntax and a wide array of statistical procedures. It's very fast, but less suited to very large datasets. Its macro capabilities are excellent. It's also evolving at a faster rate than SAS or SPSS. An interesting feature is the ability to take the survey design into account, i.e. specify strata or clustering variables. It can do most of what SAS can do with a much smaller footprint and for a lower price. However, enough stat software advocacy. The original poster wanted to extend the statistical capabilities of Excel. There have been posts to this group about a commercial add-in for Excel that will do this, I don't think it's been mentioned in this thread so far. Try a deja-news search. I've seen that NAG also sells statistical add-ins for Excel, see http://www.nag.co.uk/statistical_software.asp. There's also a freeware statistical package "R" which apparently can interface with Excel. See http://www.ci.tuwien.ac.at/R/contents.html. (R is an open source version of S-plus, yet another statistical package). I haven't tried any of these solutions, but I'd be interested in hearing other peoples experiences. John Hendrickx === 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/ ===
Self-Studying Statistics Book
I finished two courses of statistics already. I am looking for a good book that is easy to study by myself during the summer. The level would be after the first two intro-stat classes, maybe like regression analyis... If anyone has any suggestion, I really appreciate. Sincerely, Brian 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: What is the logarithmic distribution? (many questions)
Lognormal I believe most often is used to describe a normal distribution after logarithm transform, while logarithmic distribution in the sense of Kendall-Stuart is else (I didn't really grasp KS' formalism). BTW, I queried how the fit was done because I can't find the same figures as the Fisher 1943 example, assigning q=0.97293 I come with 135.05 (ok), 65.7 (instead of the published 67.33), 42.6 (instead of 44.75), 31.1 (instead of 33.46), etc. Thanks for your suggestion, Vincent Edzo Wisman wrote: > > isn't the lognormal distribution the same as logarithmic? Just guessing. > Else maybe you could look in the direction of exponential distributions. > I am just guessing though... :) > good luck! > Edzo > > "Vincent Vinh-Hung" <[EMAIL PROTECTED]> wrote in message > [EMAIL PROTECTED]">news:[EMAIL PROTECTED]... > > General question, > > I've seen two descriptions of "logarithmic distribution". > > One is related to the frequency of digits called Benford's law (digit 1 === 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/ ===