[R] CircStats and Anova
Hi, If I have two sets of directional data (in radians) and want to compare them with a multifactorial anova. Is it even legitimate to compare circular data with an anova? The books I've picked up from the library don't really say, but it looks unlikely. If it is allowable, is my having stored the data as circular (X = as.circular(A)) something the aov() function will take into account, assuming the anova would be somewhat different for directional information? Thanks in advance, Adrienne [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] testing equality of covariance matrices
Dear R-mailers, I would like to test for equality of population covariance matrices. But I can't find a R tool to do so. I saw, that other people had the same question, but I could not find an answer to it, I would appreciate to know the missed link. Thank you, b.w. K. Steinmann __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] what means Best sample in clustering using Clara?
Amir Safari wrote: Hi All, Can some body tell what means Best Sample in clustering using Clara? ?clara.object tells you: sample: labels or case numbers of the observations in the best sample, that is, the sample used by the clara algorithm for the final partition. Uwe Ligges Best Regards, - [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Job Opportunity: Statistical Guru CC 083
BTW: I am looking for a wife that is very intelligent, earns at least 300,000$ a year, is less than 25 years old, is a real beauty, happily cooks, cleans, and works in the garden, and is never moody, of course. She would have the great opportunity to solve one of the most complex challenges facing human life today: Marrying me, a guy working 12 hours a day, only talking about statistics and alike, looking tired, frequently beeing ill, a couple of years older, always moody, not even remembering his own birthday. Of course, I will not send any answers on your inquiries if I like your photo and you have sent me at least 10,000$. Uwe Ligges Don Alexander wrote: Do you consider yourself a cutting edge statistical expert with a penchant for applying your broad theoretical background to solving some of the most complex statistical challenges facing human health today? Does the idea of working for an emerging company who has a strong management team, financial backing and world class scientific advisors appeal to you? If so, read on... Our client is a drug development platform technology company whose patent pending intellectual property is poised to dramatically impact both drug discovery and development processes. The ultimate benefit to the drug development process will be to identify safer compounds for development, shorten the time for drugs to get to market and identify diagnostic markers for earlier disease detection. This technology will increase the success rate, decrease the time to market and stopdevelopment of products before critical investments are lost. Responsibilities: Independently develop novel statistical approaches to a variety of data types. Provide statistical support for all data-mining efforts, platform Quality Control, and data monitoring. Produce statistical programs as needed. Qualifications: Ph.D. or Masters in Statistics At least 8 years of experience Prior experience in R, S, SAS and/or S-plus and Design of Experiments (DOE) Prior Data Mining knowledge (PLS, neural networks, OLAP, etc.) Breadth of statistical approaches (Q Value/false discovery rate, P Value, Bayesian, Frequentist, Monte Carlo Methods, multivariate data analysis, logistic regression, chi-squared, Random Forest (RF) predictors) Prior experience in a Life Sciences research and development environment Bioinformatics knowledge preferable Ability to lead or direct the work of others Characteristics: Naturally creative, with a broad background Self starter Assertive with a positive outlook and performance oriented attitude Passion, energy, personal drive and motivation Outstanding communication skills, a strategic mindset, an ability to interface at an executive level and a polished presence are required As a professional search firm, we will only be responding to those inquiries that most closely align with the stated requirements. Moreover, our client employer can only review candidates with valid US work authorization at this time. Please include the position ID (CC 083) in the subject line of your correspondence to ensure review and forward your credentials (* Word/PDF/HTML or Text format please), in confidence, to: [EMAIL PROTECTED] General CV/resume submissions for inclusion in our knowledgebase of future opportunities can be made to: [EMAIL PROTECTED] For our most recent searches, please review our web site at: www.ccesearch.com. Kind regards, Don Alexander Director of Biz Dev Life Sciences Carlyle Conlan (919) 474-0771x105 [EMAIL PROTECTED] http://www.ccesearch.com __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Re: [CSL #265590] Schily ueber Deutschland
Greetings. (This is an automated response. There is no need to reply.) Your message regarding: Schily ueber Deutschland has been received and assigned a request number of 265590. In order help us track the progress of this request, we ask that you note the following: 1) Please save this email -- it contains the tracking number for this request. 2) include the string: [CSL #265590] (exactly as it appears -- with the square brackets) in the Subject: line of any further mail about this particular request. For example: Subject: [CSL #265590] Schily ueber Deutschland You may do this simply by replying to this email. 3) Please make sure to include [EMAIL PROTECTED] as a recipient for any future email about this topic (To: [EMAIL PROTECTED] or Cc: [EMAIL PROTECTED]) For your convenience, a copy of your original mail is at the end of this message. Thank You, Computer Systems Lab == From [EMAIL PROTECTED] Sun May 15 06:11:22 2005 Received: from obsidian.cs.wisc.edu (obsidian.cs.wisc.edu [128.105.6.13]) by vampire.cs.wisc.edu (8.13.1/8.13.1) with ESMTP id j4FBBMQj030446 for [EMAIL PROTECTED]; Sun, 15 May 2005 06:11:22 -0500 Received: from kotqg.org (gdd87.gdd.macalester.edu [141.140.121.87]) by obsidian.cs.wisc.edu (8.13.1/8.13.1) with SMTP id j4FBBGqU011854; Sun, 15 May 2005 06:11:17 -0500 From: [EMAIL PROTECTED] To: [EMAIL PROTECTED] Date: Sun, 15 May 2005 11:11:16 GMT Subject: [CSL #265590] Schily ueber Deutschland Importance: Normal X-Priority: 3 (Normal) X-Msmail-Priority: Normal MIME-Version: 1.0 Message-ID: [EMAIL PROTECTED] Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=us-ascii X-CSL-Mailscanner-Information: Please contact [EMAIL PROTECTED] for more information X-CSL-Mailscanner: Found to be clean Lese selbst: http://www.heise.de/newsticker/meldung/59427 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Save parameters from optim during iteration procedure
Dear R-users, I am going to try to be as clearer as possible, showing also an example. 1) I have a function (in my real case it's much more complex) 2) I use optim to minimize 3) I want to use as method L-BFGS-B for several reasons 4) I know I could use trace=6 (in control) in order to see live the procedure 5) I would like to see separately the values of my parameters during each iteration (what, on the screen, are the values of X) 6) Hence I would need to know the way of asking R to save somewhere the values of X during the optimization procedure 7) I have already tried to use write.table into the function I want to minimize (in the example with comments), but it gave me more values that I would need Might you know a solution? EXAMPLE: ## function fun - function(param){ a - param[1] b - param[2] r - sqrt(a^2+b^2) res - -10 * sin(r)/r #write.table(x=b, file=B.txt, append=TRUE, sep=,, col.names=FALSE, # row.names=FALSE) return(res) } optimization procedure ott - optim(par=c(-1,1), fn =fun, method = c(L-BFGS-B), control=c(trace=6) ) # what I would need to save [...] X = -0.292893 0.292893 [...] X = 0.0942275 -0.0942275 [...] X = -0.00110391 0.00110391 [...] X = 1.93949e-006 -1.93949e-006 [...] X = -4.98008e-013 4.98008e-013 [...] Thanks in advance, Carlo Giovanni Camarda Camarda Carlo Giovanni Max Planck Institute for Demographic Research Konrad-Zuse-Strasse 1 18057 Rostock, Germany Tel: +49 (0)381 2081 172 Fax: +49 (0)381 2081 472 [EMAIL PROTECTED] + This mail has been sent through the MPI for Demographic Rese...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Suppressing warning messages
How do I suppress the following ? Warning messages: 1: the condition has length 1 and only the first element will be used in: if (strike == forward) atmvol(forward, t, alpha, beta, rho, upsilon) else { 2: the condition has length 1 and only the first element will be used in: if (x(z) == 0) 1 else z/x(z) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Suppressing warning messages
Tolga Uzuner wrote: How do I suppress the following ? Warning messages: 1: the condition has length 1 and only the first element will be used in: if (strike == forward) atmvol(forward, t, alpha, beta, rho, upsilon) else { 2: the condition has length 1 and only the first element will be used in: if (x(z) == 0) 1 else z/x(z) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Maybe better to understand what generates the warning! To assure you are uninformed, say options(warn=-1) Kjetil -- Kjetil Halvorsen. Peace is the most effective weapon of mass construction. -- Mahdi Elmandjra -- No virus found in this outgoing message. Checked by AVG Anti-Virus. __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Suppressing warning messages
On 5/15/05, Tolga Uzuner [EMAIL PROTECTED] wrote: How do I suppress the following ? Warning messages: 1: the condition has length 1 and only the first element will be used in: if (strike == forward) atmvol(forward, t, alpha, beta, rho, upsilon) else { 2: the condition has length 1 and only the first element will be used in: if (x(z) == 0) 1 else z/x(z) Check out ?suppressWarnings __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Suppressing warning messages
Kjetil Brinchmann Halvorsen wrote: Tolga Uzuner wrote: How do I suppress the following ? Warning messages: 1: the condition has length 1 and only the first element will be used in: if (strike == forward) atmvol(forward, t, alpha, beta, rho, upsilon) else { 2: the condition has length 1 and only the first element will be used in: if (x(z) == 0) 1 else z/x(z) __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Maybe better to understand what generates the warning! Yes! In both cases you should really look why you are using *conditions of length 1*! And if this is intended, you certainly want to use ifelse() rather than if(){} else{}. Uwe Ligges To assure you are uninformed, say options(warn=-1) Kjetil __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
RE: [R] Job Opportunity: Statistical Guru CC 083
Wow, Cutting edge to bleeding heart - and all in one day! 8¬ Mike P.s. Uwe - start with an easy one, like a Unicorn. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Uwe Ligges Sent: 15 May 2005 12:00 To: Don Alexander Cc: r-help@stat.math.ethz.ch Subject: Re: [R] Job Opportunity: Statistical Guru CC 083 BTW: I am looking for a wife that is very intelligent, earns at least 300,000$ a year, is less than 25 years old, is a real beauty, happily cooks, cleans, and works in the garden, and is never moody, of course. She would have the great opportunity to solve one of the most complex challenges facing human life today: Marrying me, a guy working 12 hours a day, only talking about statistics and alike, looking tired, frequently beeing ill, a couple of years older, always moody, not even remembering his own birthday. Of course, I will not send any answers on your inquiries if I like your photo and you have sent me at least 10,000$. Uwe Ligges Don Alexander wrote: Do you consider yourself a cutting edge statistical expert with a penchant for applying your broad theoretical background to solving some of the most complex statistical challenges facing human health today? Does the idea of working for an emerging company who has a strong management team, financial backing and world class scientific advisors appeal to you? If so, read on... Our client is a drug development platform technology company whose patent pending intellectual property is poised to dramatically impact both drug discovery and development processes. The ultimate benefit to the drug development process will be to identify safer compounds for development, shorten the time for drugs to get to market and identify diagnostic markers for earlier disease detection. This technology will increase the success rate, decrease the time to market and stopdevelopment of products before critical investments are lost. Responsibilities: Independently develop novel statistical approaches to a variety of data types. Provide statistical support for all data-mining efforts, platform Quality Control, and data monitoring. Produce statistical programs as needed. Qualifications: Ph.D. or Masters in Statistics At least 8 years of experience Prior experience in R, S, SAS and/or S-plus and Design of Experiments (DOE) Prior Data Mining knowledge (PLS, neural networks, OLAP, etc.) Breadth of statistical approaches (Q Value/false discovery rate, P Value, Bayesian, Frequentist, Monte Carlo Methods, multivariate data analysis, logistic regression, chi-squared, Random Forest (RF) predictors) Prior experience in a Life Sciences research and development environment Bioinformatics knowledge preferable Ability to lead or direct the work of others Characteristics: Naturally creative, with a broad background Self starter Assertive with a positive outlook and performance oriented attitude Passion, energy, personal drive and motivation Outstanding communication skills, a strategic mindset, an ability to interface at an executive level and a polished presence are required As a professional search firm, we will only be responding to those inquiries that most closely align with the stated requirements. Moreover, our client employer can only review candidates with valid US work authorization at this time. Please include the position ID (CC 083) in the subject line of your correspondence to ensure review and forward your credentials (* Word/PDF/HTML or Text format please), in confidence, to: [EMAIL PROTECTED] General CV/resume submissions for inclusion in our knowledgebase of future opportunities can be made to: [EMAIL PROTECTED] For our most recent searches, please review our web site at: www.ccesearch.com. Kind regards, Don Alexander Director of Biz Dev Life Sciences Carlyle Conlan (919) 474-0771x105 [EMAIL PROTECTED] http://www.ccesearch.com __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Save parameters from optim during iteration procedure
Camarda, Carlo Giovanni wrote: Dear R-users, I am going to try to be as clearer as possible, showing also an example. 1) I have a function (in my real case it's much more complex) 2) I use optim to minimize 3) I want to use as method L-BFGS-B for several reasons 4) I know I could use trace=6 (in control) in order to see live the procedure 5) I would like to see separately the values of my parameters during each iteration (what, on the screen, are the values of X) 6) Hence I would need to know the way of asking R to save somewhere the values of X during the optimization procedure 7) I have already tried to use write.table into the function I want to minimize (in the example with comments), but it gave me more values that I would need Might you know a solution? EXAMPLE: ## function fun - function(param){ a - param[1] b - param[2] r - sqrt(a^2+b^2) res - -10 * sin(r)/r #write.table(x=b, file=B.txt, append=TRUE, sep=,, col.names=FALSE, # row.names=FALSE) This way you get each step where the function is *evaluated*, which might be much more than each iteration step of the optimization. return(res) } optimization procedure ott - optim(par=c(-1,1), fn =fun, method = c(L-BFGS-B), control=c(trace=6) ) For example, you can sink() temorarily into a file and extract the relevant lines (beginning with X = ) afterwards. Uwe Ligges # what I would need to save [...] X = -0.292893 0.292893 [...] X = 0.0942275 -0.0942275 [...] X = -0.00110391 0.00110391 [...] X = 1.93949e-006 -1.93949e-006 [...] X = -4.98008e-013 4.98008e-013 [...] Thanks in advance, Carlo Giovanni Camarda Camarda Carlo Giovanni Max Planck Institute for Demographic Research Konrad-Zuse-Strasse 1 18057 Rostock, Germany Tel: +49 (0)381 2081 172 Fax: +49 (0)381 2081 472 [EMAIL PROTECTED] + This mail has been sent through the MPI for Demographic Rese...{{dropped}} __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Seeking friend for life (not)
I'll take a risk following Uwe's wonderful response to that advert. I'm looking for someone, perhaps particularly a stats student, who might want to do a piece of work with me on using R to present and analyse routine data that psychotherapists might submit on a cgi-bin interface and perhaps cross-referencing that against some largish referential data to which I have access. Like Uwe, I require that the student bring beauty, brains, money, infinite tolerance ... no, seriously. If this might be of any possible link up with yourself or a student of yours, read on, otherwise reread Uwe's post or just hit the delete button! The situation is that I have co-developed a copyleft self-report measure that adult, tabloid literate clients in psychological therapies can complete readily that gives reasonable indication of their state say at referral, assessment, start of therapy, during therapy, end of therapy, follow-up etc. It's part of a system we call CORE (Clinical Outcomes in Routine Evaluation). How it is used is up to practitioners as our aim is to persuade therapists that such data can be of use to them, not just to researchers. There is a linked therapist completed assessment form and end of therapy form which provides a therapist rating of initial and final state but, much more importantly, provides information that contextualises the self-report data. A company in whom I have no financial interest have written a wonderful PC based program that takes data and analyses it (CORE-PC, see http://coreims.co.uk/ for information on that and the system of measures). However, I am interested in putting something on the www using a cgi-bin interface to R to allow therapists not yet convinced of the value of CORE-PC to overcome their alienation from routine data analysis. I am a psychotherapist and psychotherapy researcher first but my stats is competent and I've pretty much fixed on R for all my stats work now (bye SPSS et al.!) and love it. However, to use R to do this well clearly means getting my head around RZope/RSOAP or Rstatserver or something like that as just using CGIwithR, though brilliant, is slow and inefficient. I have discussed this with our local university (Nottingham) who are R supportive but have no cgi-bin expertise so I'm asking more widely now. Our/my history is of getting good papers out and we have good ones on uses of the system in submission and in press as well as as a sample list below. Unless I do most of the work I'm very unconcerned about where my name comes in co-authorship as I'm not under RAE pressures, just my own and NHS pressures to move this initiative on. Hence it may be a good link up for people. I currently have legitimate access to anonymised datasets from a few thosand in specific (multi-practitioner) services to massive (c40k) datasets from wider collections and there are many angles to look at within a general EDA/visualising approach to help therapy practitioners overcome their phobias and lack of numeracy. Do get in touch directly if you think this may be of some interest. Very best, Chris Sample publications, happy to send snail mail copies: Barkham, M., Evans, C., Margison, F., et al (1998) The rationale for developing and implementing core outcome batteries for routine use in service settings and psychotherapy outcome research. Journal of Mental Health, 7, 35-47. Barkham, M., Margison, F., Leach, C., et al (2001) Service profiling and outcomes benchmarking using the CORE-OM: toward practice-based evidence in the psychological therapies. Journal of Consulting and Clinical Psychology, 69, 184-196. Evans, C., Connell, J., Barkham, M., et al (2002) Towards a standardised brief outcome measure: psychometric properties and utility of the CORE-OM. British Journal of Psychiatry, 180, 51-60. (2003) Practice-Based Evidence: benchmarking NHS primary care counselling services at national and local levels. Clinical Psychology Psychotherapy, 10, 374-388. Evans, C., Mellor-Clark, J., Margison, F., et al (2000) CORE: Clinical Outcomes in Routine Evaluation. Journal of Mental Health, 9, 247-255. Margison, F. R., Barkham, M., Evans, C., et al (2000) Measurement and psychotherapy: Evidence-based practice and practice-based evidence. British Journal of Psychiatry, 177, 123-130. Mellor-Clark, J., Connell, J., Barkham, M., et al (2001) Counselling outcomes in primary health care: a CORE system data profile. European journal of psychotherapy, counselling and health, 4, 65-86. -- Chris Evans [EMAIL PROTECTED] Consultant Psychiatrist in Psychotherapy, Rampton Hospital; Research Programmes Director, Nottinghamshire NHS Trust, Hon. SL Institute of Psychiatry *** My views are my own and not representative of those institutions *** __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide!
RE: [R] Job Opportunity: Statistical Guru CC 083
On 15-May-05 Mike Waters wrote: Wow, Cutting edge to bleeding heart - and all in one day! 8¬ Mike P.s. Uwe - start with an easy one, like a Unicorn. Dear Uwe, Some further advice. I fear your vacancy notice has not been written to attract the best candidate. There are even important details which you have left unmentioned (for example, is your preferred method of communication by Command, or by Point and Click, or by both?) Perhaps slightly more seriously, Don Alexander's advertisement contains many of the elements of a good vacancy notice, and could perhaps serve as a model which you could refine. I am reminded of C. Northcote Parkinson's penetrating analyis of job adverts (he of Parkinson's Law). He pointed out that most job advertisements are inefficient and ineffective, in that they are written in such a way that they attract far too many applicants. As a result, much time, effort and expense is incurred in rejecting most or even all of these (since really discriminating candidates would probably not respond in the first place. He recommended instead the Chinese Method. In this, you know exactly whom you precisely want, and you frame the advert in such terms as to exclude all other possibilities, and to just (but no more) irresistibly attract that one candidate. Don Alexander's effort clearly goes some distance in this direction, though even so there will probably be unnecessary duplication of applicants. But you can work on it! With best wishes, and with tongue in cheek, Ted. -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Uwe Ligges Sent: 15 May 2005 12:00 To: Don Alexander Cc: r-help@stat.math.ethz.ch Subject: Re: [R] Job Opportunity: Statistical Guru CC 083 BTW: I am looking for a wife that is very intelligent, earns at least 300,000$ a year, is less than 25 years old, is a real beauty, happily cooks, cleans, and works in the garden, and is never moody, of course. She would have the great opportunity to solve one of the most complex challenges facing human life today: Marrying me, a guy working 12 hours a day, only talking about statistics and alike, looking tired, frequently beeing ill, a couple of years older, always moody, not even remembering his own birthday. Of course, I will not send any answers on your inquiries if I like your photo and you have sent me at least 10,000$. Uwe Ligges Don Alexander wrote: Do you consider yourself a cutting edge statistical expert with a penchant for applying your broad theoretical background to solving some of the most complex statistical challenges facing human health today? Does the idea of working for an emerging company who has a strong management team, financial backing and world class scientific advisors appeal to you? If so, read on... Our client is a drug development platform technology company whose patent pending intellectual property is poised to dramatically impact both drug discovery and development processes. The ultimate benefit to the drug development process will be to identify safer compounds for development, shorten the time for drugs to get to market and identify diagnostic markers for earlier disease detection. This technology will increase the success rate, decrease the time to market and stopdevelopment of products before critical investments are lost. Responsibilities: Independently develop novel statistical approaches to a variety of data types. Provide statistical support for all data-mining efforts, platform Quality Control, and data monitoring. Produce statistical programs as needed. Qualifications: Ph.D. or Masters in Statistics At least 8 years of experience Prior experience in R, S, SAS and/or S-plus and Design of Experiments (DOE) Prior Data Mining knowledge (PLS, neural networks, OLAP, etc.) Breadth of statistical approaches (Q Value/false discovery rate, P Value, Bayesian, Frequentist, Monte Carlo Methods, multivariate data analysis, logistic regression, chi-squared, Random Forest (RF) predictors) Prior experience in a Life Sciences research and development environment Bioinformatics knowledge preferable Ability to lead or direct the work of others Characteristics: Naturally creative, with a broad background Self starter Assertive with a positive outlook and performance oriented attitude Passion, energy, personal drive and motivation Outstanding communication skills, a strategic mindset, an ability to interface at an executive level and a polished presence are required As a professional search firm, we will only be responding to those inquiries that most closely align with the stated requirements. Moreover, our client employer can only review candidates with valid US work authorization at this time. Please include the position ID (CC 083) in the subject line of your correspondence to ensure review and forward your credentials (* Word/PDF/HTML or Text
[R] adjusted p-values with TukeyHSD?
hi list, i have to ask you again, having tried and searched for several days... i want to do a TukeyHSD after an Anova, and want to get the adjusted p-values after the Tukey Correction. i found the p.adjust function, but it can only correct for holm, hochberg, bonferroni, but not Tukey. Is it not possbile to get adjusted p-values after Tukey-correction? sorry, if this is an often-answered-question, but i didn´t find it on the list archive... thx a lot, list, Chris Christoph Strehblow, MD Department of Rheumatology, Diabetes and Endocrinology Wilhelminenspital, Vienna, Austria [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] CircStats and Anova
It's not clear to me what you are asking. Have you considered aov.circular in package circular? The following example comes from the help page for that function: x - c(rvonmises(50, 0, 1), rvonmises(100, pi/3, 10)) group - c(rep(0, 50), rep(1, 100)) aov.circular(x, group) Call: aov.circular(x = x, group = group) Circular Analysis of Variance: High Concentration F-Test df SS MS F p Between 1 5.901 5.9009 34.15 3.135e-08 Within 148 29.431 0.1989NANA Total 149 35.332 0.2371NANA aov.circular(x, group, method=LRT) Call: aov.circular(x = x, group = group, method = LRT) Circular Analysis of Variance: Likelihood Ratio Test df: 1 ChiSq: 29.31 p.value: 6.163e-08 Does this provide what you want? If no, I suggest you follow the procedure in the posting guide, http://www.R-project.org/posting-guide.html;. Some people answer their own questions following that process. If they still have questions, they increase their chances of getting useful replies in part because their subsequent posts provides more of the information someone else needs to understand your concern and reply in a way that you will understand. For me, one of the most useful things is a simple example that someone else can easily copy from an email and test in R, craft a reply and send it in a few seconds. hope this helps. spencer graves Mueller, Adrienne wrote: Hi, If I have two sets of directional data (in radians) and want to compare them with a multifactorial anova. Is it even legitimate to compare circular data with an anova? The books I've picked up from the library don't really say, but it looks unlikely. If it is allowable, is my having stored the data as circular (X = as.circular(A)) something the aov() function will take into account, assuming the anova would be somewhat different for directional information? Thanks in advance, Adrienne [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Not sure if this is aggregate or some other task.
I have data where where I've taken some measurements three times... twice in rapid succession so I could check test-retest reliability of a piece of equipment, and then a third measurement some time later. Not I'd like to do an analysis where I have two scores... the first being the mean of the first two taken the same day, and the second being the one taken later. I have a lot of other variables in the row, and I'd like to do the same thing to all of them. Soo Data.Frame: Subj Obs MeasureA MeasureB 1 1 45 685 1 2 50 690 1 3 48 693 2 1 39 595 2 2 41 585 2 3 45 343 should become: Subj Obs MeasureA MeasureB 1 1 47.5 687.5 1 2 50 690 2 1 40 590 2 2 41 585 It seems like a job for aggregate, but I want to collapse on only cases where observation # 3, and take the mean of a few vars in the aggregation. I can't seem to make it work, and didn't find examples that were on the mark. I think I'm suffering from prospective interference and my SPSS syntax knowledge to do exactly this is just getting in my way. any volunteers? I'd very grateful. Thanks! -- --- David L. Van Brunt, Ph.D. mailto:[EMAIL PROTECTED] [[alternative HTML version deleted]] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Finding Gradient from Contour map
I have a detailed map matrix in R (x,y,z co-ords), and am wishing to calculate the physical gradient at a number of points on the map wrt different axes and averaged over a number of distances (i.e. slope in N-S direction averaged over 10m, 50m, 100m respectively). Is there any function within R which will allow for this? Thanks, Laura Laura Quinn Institute of Atmospheric Science School of Earth and Environment University of Leeds Leeds LS2 9JT tel: +44 113 343 1596 fax: +44 113 343 6716 mail: [EMAIL PROTECTED] __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] How to make label in multi plot
Hi (cc'ed to Pierre Lapointe because this should answer the question about [R] Centered overall title with layout() as well) Muhammad Subianto wrote: Dear R-Help, As a reference about multi plot, http://finzi.psych.upenn.edu/R/Rhelp02a/archive/48725.html I want to know how can I make a label for each row. I mean like, - -- || || || Group A | plot1 | | plot 2 | | plot 3 | || || || -- -- - || Group B | plot 4 | || - Two ways (at least): (i) use an outer margin ... ooma - par(oma=c(0, 5, 0, 0)) layout(rbind(c(1, 2, 3), c(0, 4, 0))) plot(1:10, main=Plot 1) olas - par(las=2) mtext(Group A, side=2, adj=1, outer=TRUE, at=0.75) par(olas) plot(1:20, main=Plot 2) plot(1:30, main=Plot 3) plot(1:40, main=Plot 4) olas - par(las=2) mtext(Group B, side=2, adj=1, outer=TRUE, at=0.25) par(olas) # new page! plot(1:40, main=Plot 5) par(ooma) (ii) create an extra row/coloumn in the layout for the labels: layout(rbind(c(1, 2, 3, 4), c(5, 0, 6, 0)), widths=c(2, 5, 5, 5)) # plot 1 is label for row 1 omar - par(mar=rep(0, 4)) plot.new() text(0.5, 0.5, Group A, cex=2) par(omar) plot(1:10, main=Plot 1) plot(1:20, main=Plot 2) plot(1:30, main=Plot 3) # plot 5 is label for row 2 omar - par(mar=rep(0, 4)) plot.new() text(0.5, 0.5, Group B, cex=2) par(omar) plot(1:40, main=Plot 4) # new page! plot(1:40, main=Plot 5) Paul -- Dr Paul Murrell Department of Statistics The University of Auckland Private Bag 92019 Auckland New Zealand 64 9 3737599 x85392 [EMAIL PROTECTED] http://www.stat.auckland.ac.nz/~paul/ __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] Mann-Whitney Wilcoxon Rank Sum
Hello, I am hoping someone could shed some light into the Wilcoxon Rank Sum Test for me? In looking through Stats references, the Mann-Whitney U-test and the Wilcoxon Rank Sum Test are statistically equivalent. When using the following dataset: m - c(2.0863,2.1340,2.1008,1.9565,2.0413,NA,NA) f - c(1.8938,1.9709,1.8613,2.0836,1.9485,2.0630,1.9143) and the wilcox.test command as below: wilcox.test(m,f, paired = FALSE, alternative = c(two.sided)) I get a test statistic (W) of 30. When I perform this test by hand utilizing the methodology laid out in Ch. 6 of Ott Longnecker I get a value of 45. Any insight or good reference(s) as to the algorithm R is using or this issue in general would be most appreciated. Thanks __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] row.names need reordering
Hi, The row.names in my matrix seem to be out of order. I don't remember putting row.names in in the first place, I don't see what use they are, and they are out of order (perhaps because I sorted them at one point when the data was in data.frame format). Can I delete the rownames? or at least just reorder them in proper order? I know how to delete them -- how do I reorder them sequentially? Thanks, Anders Corr __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
[R] turning labels into a vector
Hello 1/ 'priors' is a table looking like: W123 T678 S789 23 42 11 12 35 9 etc 2/ WBS - labels(priors) gives me a result of class list and length 1 looking like: W123 T678 S789 I want to read W123 into X[1] as W, T687 into X[2] as T and S789 into X[3] as S using substr(X[1],1,1) but I'm having trouble extracting each group of 4 digits from WBS Any help would be gratefully accepted. thanks Meredith __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
Re: [R] Mann-Whitney Wilcoxon Rank Sum
On Mon, 16 May 2005, Jim BRINDLE wrote: Hello, I am hoping someone could shed some light into the Wilcoxon Rank Sum Test for me? In looking through Stats references, the Mann-Whitney U-test and the Wilcoxon Rank Sum Test are statistically equivalent. Yes, but not numerically: they differ by a constant (in the data, a function of the data size). When using the following dataset: m - c(2.0863,2.1340,2.1008,1.9565,2.0413,NA,NA) f - c(1.8938,1.9709,1.8613,2.0836,1.9485,2.0630,1.9143) and the wilcox.test command as below: wilcox.test(m,f, paired = FALSE, alternative = c(two.sided)) I get a test statistic (W) of 30. When I perform this test by hand utilizing the methodology laid out in Ch. 6 of Ott Longnecker I get a value of 45. Any insight or good reference(s) as to the algorithm R is using or this issue in general would be most appreciated. I don't know that book but the R help page does have references. Also, ?pwilcox says This distribution is obtained as follows. Let 'x' and 'y' be two random, independent samples of size 'm' and 'n'. Then the Wilcoxon rank sum statistic is the number of all pairs '(x[i], y[j])' for which 'y[j]' is not greater than 'x[i]'. This statistic takes values between '0' and 'm * n', and its mean and variance are 'm * n / 2' and 'm * n * (m + n + 1) / 12', respectively. Your samples have length 5 (after removing NAs) and 7 and no ties. The R code is readable by getAnywhere(wilcox.test.default) as essentially r - rank(c(x,y)) sum(r[seq(along = x)]) - n.x * (n.x + 1)/2 I guess your reference just uses the first term. Another way of looking at this is whether ranks start at 0 or at 1 (as in rank()): R's definition is the rank sum with 0-based ranks. -- Brian D. Ripley, [EMAIL PROTECTED] Professor of Applied Statistics, http://www.stats.ox.ac.uk/~ripley/ University of Oxford, Tel: +44 1865 272861 (self) 1 South Parks Road, +44 1865 272866 (PA) Oxford OX1 3TG, UKFax: +44 1865 272595 __ R-help@stat.math.ethz.ch mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html