[R] R: Re: Differences in output of lme() when introducing interactions
Do you have legal advice that suing the University (if that is the right context) would actually be a fruitful way forwards, that it would achieve anything useful within reasonable time and without causing the student severe financial risk? What may work in that context is for students to collectively complain that important aspects of their training and support are being neglected. With the rapidity of recent technological change, the issue is widespread. To an extent, able post-docs and PhDs have to lead the charge in getting training and support updated and brought into the modern world. John Maindonald email: john.maindon...@anu.edu.au<mailto:john.maindon...@anu.edu.au> On 22/07/2015, at 22:00, r-help-requ...@r-project.org<mailto:r-help-requ...@r-project.org> wrote: Da: li...@dewey.myzen.co.uk<mailto:li...@dewey.myzen.co.uk> Data: 21-lug-2015 11.58 A: "angelo.arc...@virgilio.it<mailto:angelo.arc...@virgilio.it>"mailto:angelo.arc...@virgilio.it>>, mailto:bgunter.4...@gmail.com>> Cc: mailto:r-help@r-project.org>> Ogg: Re: R: Re: [R] R: Re: Differences in output of lme() when introducing interactions Dear Angelo I suggest you do an online search for marginality which may help to explain the relationship between main effects and interactions. As I said in my original email this is a complicated subject which we are not going to retype for you. If you are doing this as a student I suggest you sue your university for failing to train you appropriately and if it is part of your employment I suggest you find a better employer. On 21/07/2015 10:04, angelo.arc...@virgilio.it<mailto:angelo.arc...@virgilio.it> wrote: Dear Bert, thank you for your feedback. Can you please provide some references online so I can improve "my ignorance"? Anyways, please notice that it is not true that I do not know statistics and regressions at all, and I am strongly convinced that my question can be of interest for some one else in the future. This is what forums serve for, isn't it? This is why people help each other, isn't it? Moreover, don't you think that I would not have asked to this R forum if I had the possibility to ask or pay a statician? Don't you think I have done already my best to study and learn before posting this message? Trust me, I have read different online tutorials on lme and lmer, and I am confident that I have got the basic concepts. Still I have not found the answer to solve my problem, so if you know the answer can you please give me some suggestions that can help me? I do not have a book where to learn and unfortunately I have to analyze the results soon. Any help? Any online reference to-the-point that can help me in solving this problem? Thank you in advance Best regards Angelo [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
[R] R: Re: Differences in output of lme() when introducing interactions
Dear Terry, I am very grateful to you for such a detailed and helpful answer. Following your recommendation then I will skip the method presented at http://www.ats.ucla.edu/stat/r/faq/type3.htm So far, based on my understanding of R I arrived to the conclusion that the correct way to see if there is a correlation between my dependent variable (spectral centroid of a sound) and weight, height, and interaction between weight and height of participants asked to create those sounds (in a repeated measure design) is: lme_centroid <- lme(Centroid ~ Weight*Height*Shoe_Size, data = My_data, random = ~1 | Subject) anova.lme(lme_centroid,type = "marginal") Can anyone please confirm me that those formulas are actually correct and give the significant or non significant p-values for the main effects and their interactions? I would prefer to use lme(), not lmer(). I am making the assumption of course that the model I am using (Centroid ~ Weight*Height*Shoe_Size) is the best fit for my data. Thanks in advance Angelo Messaggio originale Da: thern...@mayo.edu Data: 22-lug-2015 15.15 A: , Ogg: Re: Differences in output of lme() when introducing interactions "Type III" is a peculiarity of SAS, which has taken root in the world. There are 3 main questions wrt to it: 1. How to compute it (outside of SAS). There is a trick using contr.treatment coding that works if the design has no missing factor combinations, your post has a link to such a description. The SAS documentation is very obtuse, thus almost no one knows how to compute the general case. 2. What is it? It is a population average. The predicted average treatment effect in a balanced population-- one where all the factor combinations appeared the same number of times. One way to compute 'type 3' is to create such a data set, get all the predicted values, and then take the average prediction for treatment A, average for treatment B, average for C, ... and test "are these averages the same". The algorithm of #1 above leads to another explanation which is a false trail, in my opinion. 3. Should you ever use it? No. There is a very strong inverse correlation between "understand what it really is" and "recommend its use". Stephen Senn has written very intellgently on the issues. Terry Therneau On 07/22/2015 05:00 AM, r-help-requ...@r-project.org wrote: > Dear Michael, > thanks a lot. I am studying the marginality and I came across to this post: > > http://www.ats.ucla.edu/stat/r/faq/type3.htm > > Do you think that the procedure there described is the right one to solve my > problem? > > Would you have any other online resources to suggest especially dealing with > R? > > My department does not have a statician, so I have to find a solution with my > own capacities. > > Thanks in advance > > Angelo [[alternative HTML version deleted]] __ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
Re: [R] R: Re: Differences in output of lme() when introducing interactions
I believe Michael's point is that you need to STOP asking such questions and START either learning some statistics or work with someone who already knows some. You should not be doing such analyses on your own given your present state of statistical ignorance. Cheers, Bert Bert Gunter "Data is not information. Information is not knowledge. And knowledge is certainly not wisdom." -- Clifford Stoll On Mon, Jul 20, 2015 at 5:45 PM, angelo.arc...@virgilio.it wrote: > Dear Michael, > thanks for your answer. Despite it answers to my initial question, it does > not help me in finding the solution to my problem unfortunately. > > Could you please tell me which analysis of the two models should I trust then? > My goal is to know whether participants’ choices > of the dependent variable are linearly related to their own weight, height, > shoe size and > the combination of those effects. > Would the analysis of model 2 be more > correct than that of model 1? Which of the two analysis should I trust > according to my goal? > What is your recommendation? > > > Thanks in advance > > Angelo > > > > > > Messaggio originale > Da: li...@dewey.myzen.co.uk > Data: 20-lug-2015 17.56 > A: "angelo.arc...@virgilio.it", > > Ogg: Re: [R] Differences in output of lme() when introducing interactions > > In-line > > On 20/07/2015 15:10, angelo.arc...@virgilio.it wrote: >> Dear List Members, >> >> >> >> I am searching for correlations between a dependent variable and a >> factor or a combination of factors in a repeated measure design. So I >> use lme() function in R. However, I am getting very different results >> depending on whether I add on the lme formula various factors compared >> to when only one is present. If a factor is found to be significant, >> shouldn't remain significant also when more factors are introduced in >> the model? >> > > The short answer is 'No'. > > The long answer is contained in any good book on statistics which you > really need to have by your side as the long answer is too long to > include in an email. > >> >> I give an example of the outputs I get using the two models. In the first >> model I use one single factor: >> >> library(nlme) >> summary(lme(Mode ~ Weight, data = Gravel_ds, random = ~1 | Subject)) >> Linear mixed-effects model fit by REML >> Data: Gravel_ds >>AIC BIC logLik >>2119.28 2130.154 -1055.64 >> >> Random effects: >> Formula: ~1 | Subject >> (Intercept) Residual >> StdDev:1952.495 2496.424 >> >> Fixed effects: Mode ~ Weight >> Value Std.Error DF t-value p-value >> (Intercept) 10308.966 2319.0711 95 4.445299 0.000 >> Weight-99.036 32.3094 17 -3.065233 0.007 >> Correlation: >> (Intr) >> Weight -0.976 >> >> Standardized Within-Group Residuals: >> Min Q1 Med Q3 Max >> -1.74326719 -0.41379593 -0.06508451 0.39578734 2.27406649 >> >> Number of Observations: 114 >> Number of Groups: 19 >> >> >> As you can see the p-value for factor Weight is significant. >> This is the second model, in which I add various factors for searching their >> correlations: >> >> library(nlme) >> summary(lme(Mode ~ Weight*Height*Shoe_Size*BMI, data = Gravel_ds, random = >> ~1 | Subject)) >> Linear mixed-effects model fit by REML >> Data: Gravel_ds >> AIC BIClogLik >>1975.165 2021.694 -969.5825 >> >> Random effects: >> Formula: ~1 | Subject >> (Intercept) Residual >> StdDev:1.127993 2494.826 >> >> Fixed effects: Mode ~ Weight * Height * Shoe_Size * BMI >> Value Std.Error DFt-value p-value >> (Intercept) 5115955 10546313 95 0.4850941 0.6287 >> Weight -13651237 6939242 3 -1.9672518 0.1438 >> Height -18678 53202 3 -0.3510740 0.7487 >> Shoe_Size 93427213737 3 0.4371115 0.6916 >> BMI -13011088 7148969 3 -1.8199949 0.1663 >> Weight:Height 28128 14191 3 1.9820883 0.1418 >> Weight:Shoe_Size 351453186304 3 1.8864467 0.1557 >> Height:Shoe_Size -783 1073 3 -0.7298797 0.5183 >> Weight:BMI 19475 11425 3 1.7045450 0.1868 >> Height:BMI 226512118364 3 1.9136867 0.1516 >> Shoe_Size:BMI 329377190294 3 1.7308827 0.1819 >> Weight:Height:Shoe_Size -706 371 3 -1.9014817 0.1534 >> Weight:Height:BMI-10963 3 -1.7258742 0.1828 >> Weight:Shoe_Size:BMI -273 201 3 -1.3596421 0.2671 >> Height:Shoe_Size:BMI-5858 3200 3 -1.8306771 0.1646 >> Weight:Height:Shoe_Size:BMI 2 1 3 1.3891782 0.2589 >> Correlation: >> (Intr) Weight Height Sho_Sz BMIWght:H >> Wg:S_S Hg:S_S Wg:BMI Hg:BMI S_S:BM Wg:H:S_S W:H:BM W:S_S: H:S_S: >>
[R] R: Re: Differences in output of lme() when introducing interactions
Dear Michael, thanks for your answer. Despite it answers to my initial question, it does not help me in finding the solution to my problem unfortunately. Could you please tell me which analysis of the two models should I trust then? My goal is to know whether participants’ choices of the dependent variable are linearly related to their own weight, height, shoe size and the combination of those effects. Would the analysis of model 2 be more correct than that of model 1? Which of the two analysis should I trust according to my goal? What is your recommendation? Thanks in advance Angelo Messaggio originale Da: li...@dewey.myzen.co.uk Data: 20-lug-2015 17.56 A: "angelo.arc...@virgilio.it", Ogg: Re: [R] Differences in output of lme() when introducing interactions In-line On 20/07/2015 15:10, angelo.arc...@virgilio.it wrote: > Dear List Members, > > > > I am searching for correlations between a dependent variable and a > factor or a combination of factors in a repeated measure design. So I > use lme() function in R. However, I am getting very different results > depending on whether I add on the lme formula various factors compared > to when only one is present. If a factor is found to be significant, > shouldn't remain significant also when more factors are introduced in > the model? > The short answer is 'No'. The long answer is contained in any good book on statistics which you really need to have by your side as the long answer is too long to include in an email. > > I give an example of the outputs I get using the two models. In the first > model I use one single factor: > > library(nlme) > summary(lme(Mode ~ Weight, data = Gravel_ds, random = ~1 | Subject)) > Linear mixed-effects model fit by REML > Data: Gravel_ds >AIC BIC logLik >2119.28 2130.154 -1055.64 > > Random effects: > Formula: ~1 | Subject > (Intercept) Residual > StdDev:1952.495 2496.424 > > Fixed effects: Mode ~ Weight > Value Std.Error DF t-value p-value > (Intercept) 10308.966 2319.0711 95 4.445299 0.000 > Weight-99.036 32.3094 17 -3.065233 0.007 > Correlation: > (Intr) > Weight -0.976 > > Standardized Within-Group Residuals: > Min Q1 Med Q3 Max > -1.74326719 -0.41379593 -0.06508451 0.39578734 2.27406649 > > Number of Observations: 114 > Number of Groups: 19 > > > As you can see the p-value for factor Weight is significant. > This is the second model, in which I add various factors for searching their > correlations: > > library(nlme) > summary(lme(Mode ~ Weight*Height*Shoe_Size*BMI, data = Gravel_ds, random = ~1 > | Subject)) > Linear mixed-effects model fit by REML > Data: Gravel_ds > AIC BIClogLik >1975.165 2021.694 -969.5825 > > Random effects: > Formula: ~1 | Subject > (Intercept) Residual > StdDev:1.127993 2494.826 > > Fixed effects: Mode ~ Weight * Height * Shoe_Size * BMI > Value Std.Error DFt-value p-value > (Intercept) 5115955 10546313 95 0.4850941 0.6287 > Weight -13651237 6939242 3 -1.9672518 0.1438 > Height -18678 53202 3 -0.3510740 0.7487 > Shoe_Size 93427213737 3 0.4371115 0.6916 > BMI -13011088 7148969 3 -1.8199949 0.1663 > Weight:Height 28128 14191 3 1.9820883 0.1418 > Weight:Shoe_Size 351453186304 3 1.8864467 0.1557 > Height:Shoe_Size -783 1073 3 -0.7298797 0.5183 > Weight:BMI 19475 11425 3 1.7045450 0.1868 > Height:BMI 226512118364 3 1.9136867 0.1516 > Shoe_Size:BMI 329377190294 3 1.7308827 0.1819 > Weight:Height:Shoe_Size -706 371 3 -1.9014817 0.1534 > Weight:Height:BMI-10963 3 -1.7258742 0.1828 > Weight:Shoe_Size:BMI -273 201 3 -1.3596421 0.2671 > Height:Shoe_Size:BMI-5858 3200 3 -1.8306771 0.1646 > Weight:Height:Shoe_Size:BMI 2 1 3 1.3891782 0.2589 > Correlation: > (Intr) Weight Height Sho_Sz BMIWght:H Wg:S_S > Hg:S_S Wg:BMI Hg:BMI S_S:BM Wg:H:S_S W:H:BM W:S_S: H:S_S: > Weight -0.895 > Height -0.996 0.869 > Shoe_Size -0.930 0.694 0.933 > BMI -0.911 0.998 0.887 0.720 > Weight:Height0.894 -1.000 -0.867 -0.692 -0.997 > Weight:Shoe_Size 0.898 -0.997 -0.873 -0.700 -0.999 0.995 > Height:Shoe_Size 0.890 -0.612 -0.904 -0.991 -0.641 0.609 0.619 > Weight:BMI 0.911 -0.976 -0.887 -0.715 -0.972 0.980 0.965 > 0.637 > Height:BMI 0.900 -1.000 -0.875 -0.703 -0.999 0.999 0.999 > 0.622 0.973 > Shoe_Size:B