Re: [R] Type II and III sum of square in Anova (R, car package)
I cannot resist a very brief entry into this old and seemingly immortal issue, but I will be very brief, I promise! Amasco Miralisus suggests: As I understood form R FAQ, there is disagreement among Statisticians which SS to use (http://cran.r-project.org/doc/FAQ/R-FAQ.html#Why-does-the-output-from-a nova_0028_0029-depend-on-the-order-of-factors-in-the-model_003f). To let this go is to concede way too much. The 'disagreement' is really over whether this is a sensible question to ask in the first place. One side of the debate suggests that the real question is what hypotheses does it make sense to test and within what outer hypotheses. Settle that question and no issue on types of sums of squares arises. This is often a hard question to get your head around, and the attraction of offering a variety of 'types of sums of squares' holds out the false hope that perhaps you don't need to do so. The bad news is that for good science and good decision making, you do. Bill Venables. __ 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 and provide commented, minimal, self-contained, reproducible code.
Re: [R] Type II and III sum of square in Anova (R, car package)
Amasco, In general it is dangerous to attempt to interpret a main effect that is included in an interaction, regardless of wether or not the interaction is significant. If you want to make a valid inference about a main effect it is safest to do so after dropping any interaction that contains the main effect. Since you would not want to drop a significant interaction, you should not try to interpret a main effect in the presence of a significant interaction that contains the main effect. If the interaction is not significant drop the interaction, re-run the model and then look at the main effect. John John Sorkin M.D., Ph.D. Chief, Biostatistics and Informatics Baltimore VA Medical Center GRECC, University of Maryland School of Medicine Claude D. Pepper OAIC, University of Maryland Clinical Nutrition Research Unit, and Baltimore VA Center Stroke of Excellence University of Maryland School of Medicine Division of Gerontology Baltimore VA Medical Center 10 North Greene Street GRECC (BT/18/GR) Baltimore, MD 21201-1524 (Phone) 410-605-7119 (Fax) 410-605-7913 (Please call phone number above prior to faxing) [EMAIL PROTECTED] Amasco Miralisus [EMAIL PROTECTED] 8/28/2006 3:20 PM Hello, First of all, I would like to thank everybody who answered my question. Every post has added something to my knowledge of the topic. I now know why Type III SS are so questionable. As I understood form R FAQ, there is disagreement among Statisticians which SS to use (http://cran.r-project.org/doc/FAQ/R-FAQ.html#Why-does-the-output-from-anova_0028_0029-depend-on-the-order-of-factors-in-the-model_003f). However, most commercial statistical packages use Type III as the default (with orthogonal contrasts), just as STATISTICA, from which I am currently trying to migrate to R. This was probably was done for the convenience of end-users who are not very experienced in theoretical statistics. I am aware that the same result could be produced using the standard anova() function with Type I sequential SS, supplemented by drop1() function, but this approach will look quite complicated for persons without any substantial background in statistics, like no-math students. I would prefer easier way, possibly more universal, though also probably more for dummies :) If am not mistaken, car package by John Fox with his nice Anova() function is the reasonable alternative for any, who wish to simply perform quick statistical analysis, without afraid to mess something with model fitting. Of course orthogonal contrasts have to be specified (for example contr.sum) in case of Type III SS. Therefore, I would like to reformulate my questions, to make it easier for you to answer: 1. The first question related to answer by Professor Brian Ripley: Did I understood correctly from the advised paper (Bill Venables' 'exegeses' paper) that there is not much sense to test main effects if the interaction is significant? 2. If I understood the post by John Fox correctly, I could safely use Anova(.,type=III) function from car for ANOVA analyses in R, both for balanced and unbalanced designs? Of course providing the model was fitted with orthogonal contrasts. Something like below: mod - aov(response ~ factor1 * factor2, data=mydata, contrasts=list(factor1=contr.sum, factor2=contr.sum)) Anova(mod, type=III) It was also said in most of your posts that the decision of which of Type of SS to use has to be done on the basis of the hypothesis we want to test. Therefore, let's assume that I would like to test the significance of both factors, and if some of them significant, I plan to use post-hoc tests to explore difference(s) between levels of this significant factor(s). Thank you in advance, Amasco On 8/27/06, John Fox [EMAIL PROTECTED] wrote: Dear Amasco, A complete explanation of the issues that you raise is awkward in an email, so I'll address your questions briefly. Section 8.2 of my text, Applied Regression Analysis, Linear Models, and Related Methods (Sage, 1997) has a detailed discussion. (1) In balanced designs, so-called Type I, II, and III sums of squares are identical. If the STATA manual says that Type II tests are only appropriate in balanced designs, then that doesn't make a whole lot of sense (unless one believes that Type-II tests are nonsense, which is not the case). (2) One should concentrate not directly on different types of sums of squares, but on the hypotheses to be tested. Sums of squares and F-tests should follow from the hypotheses. Type-II and Type-III tests (if the latter are properly formulated) test hypotheses that are reasonably construed as tests of main effects and interactions in unbalanced designs. In unbalanced designs, Type-I sums of squares usually test hypotheses of interest only by accident. (3) Type-II sums of squares are constructed obeying the principle of marginality, so the kinds of contrasts employed to represent factors are irrelevant to the sums of squares produced.
Re: [R] Type II and III sum of square in Anova (R, car package)
Hello, First of all, I would like to thank everybody who answered my question. Every post has added something to my knowledge of the topic. I now know why Type III SS are so questionable. As I understood form R FAQ, there is disagreement among Statisticians which SS to use (http://cran.r-project.org/doc/FAQ/R-FAQ.html#Why-does-the-output-from-anova_0028_0029-depend-on-the-order-of-factors-in-the-model_003f). However, most commercial statistical packages use Type III as the default (with orthogonal contrasts), just as STATISTICA, from which I am currently trying to migrate to R. This was probably was done for the convenience of end-users who are not very experienced in theoretical statistics. I am aware that the same result could be produced using the standard anova() function with Type I sequential SS, supplemented by drop1() function, but this approach will look quite complicated for persons without any substantial background in statistics, like no-math students. I would prefer easier way, possibly more universal, though also probably more for dummies :) If am not mistaken, car package by John Fox with his nice Anova() function is the reasonable alternative for any, who wish to simply perform quick statistical analysis, without afraid to mess something with model fitting. Of course orthogonal contrasts have to be specified (for example contr.sum) in case of Type III SS. Therefore, I would like to reformulate my questions, to make it easier for you to answer: 1. The first question related to answer by Professor Brian Ripley: Did I understood correctly from the advised paper (Bill Venables' 'exegeses' paper) that there is not much sense to test main effects if the interaction is significant? 2. If I understood the post by John Fox correctly, I could safely use Anova(…,type=III) function from car for ANOVA analyses in R, both for balanced and unbalanced designs? Of course providing the model was fitted with orthogonal contrasts. Something like below: mod - aov(response ~ factor1 * factor2, data=mydata, contrasts=list(factor1=contr.sum, factor2=contr.sum)) Anova(mod, type=III) It was also said in most of your posts that the decision of which of Type of SS to use has to be done on the basis of the hypothesis we want to test. Therefore, let's assume that I would like to test the significance of both factors, and if some of them significant, I plan to use post-hoc tests to explore difference(s) between levels of this significant factor(s). Thank you in advance, Amasco On 8/27/06, John Fox [EMAIL PROTECTED] wrote: Dear Amasco, A complete explanation of the issues that you raise is awkward in an email, so I'll address your questions briefly. Section 8.2 of my text, Applied Regression Analysis, Linear Models, and Related Methods (Sage, 1997) has a detailed discussion. (1) In balanced designs, so-called Type I, II, and III sums of squares are identical. If the STATA manual says that Type II tests are only appropriate in balanced designs, then that doesn't make a whole lot of sense (unless one believes that Type-II tests are nonsense, which is not the case). (2) One should concentrate not directly on different types of sums of squares, but on the hypotheses to be tested. Sums of squares and F-tests should follow from the hypotheses. Type-II and Type-III tests (if the latter are properly formulated) test hypotheses that are reasonably construed as tests of main effects and interactions in unbalanced designs. In unbalanced designs, Type-I sums of squares usually test hypotheses of interest only by accident. (3) Type-II sums of squares are constructed obeying the principle of marginality, so the kinds of contrasts employed to represent factors are irrelevant to the sums of squares produced. You get the same answer for any full set of contrasts for each factor. In general, the hypotheses tested assume that terms to which a particular term is marginal are zero. So, for example, in a three-way ANOVA with factors A, B, and C, the Type-II test for the AB interaction assumes that the ABC interaction is absent, and the test for the A main effect assumes that the ABC, AB, and AC interaction are absent (but not necessarily the BC interaction, since the A main effect is not marginal to this term). A general justification is that we're usually not interested, e.g., in a main effect that's marginal to a nonzero interaction. (4) Type-III tests do not assume that terms higher-order to the term in question are zero. For example, in a two-way design with factors A and B, the type-III test for the A main effect tests whether the population marginal means at the levels of A (i.e., averaged across the levels of B) are the same. One can test this hypothesis whether or not A and B interact, since the marginal means can be formed whether or not the profiles of means for A within levels of B are parallel. Whether the hypothesis is of interest in the presence of interaction
Re: [R] Type II and III sum of square in Anova (R, car package)
Dear Amasco, Again, I'll answer briefly (since the written source that I previously mentioned has an extensive discussion): -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Amasco Miralisus Sent: Monday, August 28, 2006 2:21 PM To: r-help@stat.math.ethz.ch Cc: John Fox; Prof Brian Ripley; Mark Lyman Subject: Re: [R] Type II and III sum of square in Anova (R, car package) Hello, First of all, I would like to thank everybody who answered my question. Every post has added something to my knowledge of the topic. I now know why Type III SS are so questionable. As I understood form R FAQ, there is disagreement among Statisticians which SS to use (http://cran.r-project.org/doc/FAQ/R-FAQ.html#Why-does-the-out put-from-anova_0028_0029-depend-on-the-order-of-factors-in-the -model_003f). However, most commercial statistical packages use Type III as the default (with orthogonal contrasts), just as STATISTICA, from which I am currently trying to migrate to R. This was probably was done for the convenience of end-users who are not very experienced in theoretical statistics. Note that the contrasts are only orthogonal in the row basis of the model matrix, not, with unbalanced data, in the model matrix itself. I am aware that the same result could be produced using the standard anova() function with Type I sequential SS, supplemented by drop1() function, but this approach will look quite complicated for persons without any substantial background in statistics, like no-math students. I would prefer easier way, possibly more universal, though also probably more for dummies :) If am not mistaken, car package by John Fox with his nice Anova() function is the reasonable alternative for any, who wish to simply perform quick statistical analysis, without afraid to mess something with model fitting. Of course orthogonal contrasts have to be specified (for example contr.sum) in case of Type III SS. Therefore, I would like to reformulate my questions, to make it easier for you to answer: 1. The first question related to answer by Professor Brian Ripley: Did I understood correctly from the advised paper (Bill Venables' 'exegeses' paper) that there is not much sense to test main effects if the interaction is significant? Many are of this opinion. I would put it a bit differently: Properly formulated, tests of main effects in the presence of interactions make sense (i.e., have a straightforward interpretation in terms of population marginal means) but probably are not of interest. 2. If I understood the post by John Fox correctly, I could safely use Anova(.,type=III) function from car for ANOVA analyses in R, both for balanced and unbalanced designs? Of course providing the model was fitted with orthogonal contrasts. Something like below: mod - aov(response ~ factor1 * factor2, data=mydata, contrasts=list(factor1=contr.sum, factor2=contr.sum)) Anova(mod, type=III) Yes (or you could reset the contrasts option), but why do you appear to prefer the type-III tests to the type-II tests? It was also said in most of your posts that the decision of which of Type of SS to use has to be done on the basis of the hypothesis we want to test. Therefore, let's assume that I would like to test the significance of both factors, and if some of them significant, I plan to use post-hoc tests to explore difference(s) between levels of this significant factor(s). Your statement is too vague to imply what kind of tests you should use. I think that people are almost always interested in main effects when interactions to which they are marginal are negligible. In this situation, both type-II and type-III tests are appropriate, and type-II tests would usually be more powerful. Regards, John Thank you in advance, Amasco On 8/27/06, John Fox [EMAIL PROTECTED] wrote: Dear Amasco, A complete explanation of the issues that you raise is awkward in an email, so I'll address your questions briefly. Section 8.2 of my text, Applied Regression Analysis, Linear Models, and Related Methods (Sage, 1997) has a detailed discussion. (1) In balanced designs, so-called Type I, II, and III sums of squares are identical. If the STATA manual says that Type II tests are only appropriate in balanced designs, then that doesn't make a whole lot of sense (unless one believes that Type-II tests are nonsense, which is not the case). (2) One should concentrate not directly on different types of sums of squares, but on the hypotheses to be tested. Sums of squares and F-tests should follow from the hypotheses. Type-II and Type-III tests (if the latter are properly formulated) test hypotheses that are reasonably construed as tests of main effects and interactions in unbalanced designs. In unbalanced designs, Type-I sums of squares usually test
Re: [R] Type II and III sum of square in Anova (R, car package)
I think this starts from the position of a batch-oriented package. In R you can refit models with update(), add1() and drop1(), and experienced S/R users almost never use ANOVA tables for unbalanced designs. Rather than fit a pre-specified set of sub-models, why not fit those sub-models that appear to make some sense for your problem and data? SInce your post lacks a signature and your credentials we have no idea of your background, which makes it very difficult even to know what reading to suggest to you. But Bill Venables' 'exegeses' paper (http://www.stats.ox.ac.uk/pub/MASS3/Exegeses.pdf) may be a good start. It does explain your comment '3.'. On Sun, 27 Aug 2006, Amasco Miralisus wrote: Hello everybody, I have some questions on ANOVA in general and on ANOVA in R particularly. I am not Statistician, therefore I would be very appreciated if you answer it in a simple way. 1. First of all, more general question. Standard anova() function for lm() or aov() models in R implements Type I sum of squares (sequential), which is not well suited for unbalanced ANOVA. Therefore it is better to use Anova() function from car package, which was programmed by John Fox to use Type II and Type III sum of squares. Did I get the point? 2. Now more specific question. Type II sum of squares is not well suited for unbalanced ANOVA designs too (as stated in STATISTICA help), therefore the general rule of thumb is to use Anova() function using Type II SS only for balanced ANOVA and Anova() function using Type III SS for unbalanced ANOVA? Is this correct interpretation? 3. I have found a post from John Fox in which he wrote that Type III SS could be misleading in case someone use some contrasts. What is this about? Could you please advice, when it is appropriate to use Type II and when Type III SS? I do not use contrasts for comparisons, just general ANOVA with subsequent Tukey post-hoc comparisons. Thank you in advance, Amasco [[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 and provide commented, minimal, self-contained, reproducible code. -- 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 and provide commented, minimal, self-contained, reproducible code.
Re: [R] Type II and III sum of square in Anova (R, car package)
Dear Amasco, A complete explanation of the issues that you raise is awkward in an email, so I'll address your questions briefly. Section 8.2 of my text, Applied Regression Analysis, Linear Models, and Related Methods (Sage, 1997) has a detailed discussion. (1) In balanced designs, so-called Type I, II, and III sums of squares are identical. If the STATA manual says that Type II tests are only appropriate in balanced designs, then that doesn't make a whole lot of sense (unless one believes that Type-II tests are nonsense, which is not the case). (2) One should concentrate not directly on different types of sums of squares, but on the hypotheses to be tested. Sums of squares and F-tests should follow from the hypotheses. Type-II and Type-III tests (if the latter are properly formulated) test hypotheses that are reasonably construed as tests of main effects and interactions in unbalanced designs. In unbalanced designs, Type-I sums of squares usually test hypotheses of interest only by accident. (3) Type-II sums of squares are constructed obeying the principle of marginality, so the kinds of contrasts employed to represent factors are irrelevant to the sums of squares produced. You get the same answer for any full set of contrasts for each factor. In general, the hypotheses tested assume that terms to which a particular term is marginal are zero. So, for example, in a three-way ANOVA with factors A, B, and C, the Type-II test for the AB interaction assumes that the ABC interaction is absent, and the test for the A main effect assumes that the ABC, AB, and AC interaction are absent (but not necessarily the BC interaction, since the A main effect is not marginal to this term). A general justification is that we're usually not interested, e.g., in a main effect that's marginal to a nonzero interaction. (4) Type-III tests do not assume that terms higher-order to the term in question are zero. For example, in a two-way design with factors A and B, the type-III test for the A main effect tests whether the population marginal means at the levels of A (i.e., averaged across the levels of B) are the same. One can test this hypothesis whether or not A and B interact, since the marginal means can be formed whether or not the profiles of means for A within levels of B are parallel. Whether the hypothesis is of interest in the presence of interaction is another matter, however. To compute Type-III tests using incremental F-tests, one needs contrasts that are orthogonal in the row-basis of the model matrix. In R, this means, e.g., using contr.sum, contr.helmert, or contr.poly (all of which will give you the same SS), but not contr.treatment. Failing to be careful here will result in testing hypotheses that are not reasonably construed, e.g., as hypotheses concerning main effects. (5) The same considerations apply to linear models that include quantitative predictors -- e.g., ANCOVA. Most software will not automatically produce sensible Type-III tests, however. I hope this helps, John John Fox Department of Sociology McMaster University Hamilton, Ontario Canada L8S 4M4 905-525-9140x23604 http://socserv.mcmaster.ca/jfox -Original Message- From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED] On Behalf Of Amasco Miralisus Sent: Saturday, August 26, 2006 5:07 PM To: r-help@stat.math.ethz.ch Subject: [R] Type II and III sum of square in Anova (R, car package) Hello everybody, I have some questions on ANOVA in general and on ANOVA in R particularly. I am not Statistician, therefore I would be very appreciated if you answer it in a simple way. 1. First of all, more general question. Standard anova() function for lm() or aov() models in R implements Type I sum of squares (sequential), which is not well suited for unbalanced ANOVA. Therefore it is better to use Anova() function from car package, which was programmed by John Fox to use Type II and Type III sum of squares. Did I get the point? 2. Now more specific question. Type II sum of squares is not well suited for unbalanced ANOVA designs too (as stated in STATISTICA help), therefore the general rule of thumb is to use Anova() function using Type II SS only for balanced ANOVA and Anova() function using Type III SS for unbalanced ANOVA? Is this correct interpretation? 3. I have found a post from John Fox in which he wrote that Type III SS could be misleading in case someone use some contrasts. What is this about? Could you please advice, when it is appropriate to use Type II and when Type III SS? I do not use contrasts for comparisons, just general ANOVA with subsequent Tukey post-hoc comparisons. Thank you in advance, Amasco [[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
Re: [R] Type II and III sum of square in Anova (R, car package)
1. First of all, more general question. Standard anova() function for lm() or aov() models in R implements Type I sum of squares (sequential), which is not well suited for unbalanced ANOVA. Therefore it is better to use Anova() function from car package, which was programmed by John Fox to use Type II and Type III sum of squares. Did I get the point? 2. Now more specific question. Type II sum of squares is not well suited for unbalanced ANOVA designs too (as stated in STATISTICA help), therefore the general rule of thumb is to use Anova() function using Type II SS only for balanced ANOVA and Anova() function using Type III SS for unbalanced ANOVA? Is this correct interpretation? 3. I have found a post from John Fox in which he wrote that Type III SS could be misleading in case someone use some contrasts. What is this about? Could you please advice, when it is appropriate to use Type II and when Type III SS? I do not use contrasts for comparisons, just general ANOVA with subsequent Tukey post-hoc comparisons. There are many threads on this list that discuss this issue. Not being a great statistician myself, I would suggest you read through some of these as a start. As I understand, the best philosophy with regards to types of sums of squares is to use the type that tests the hypothesis you want. They were developed as a convenience to test many of the hypotheses a person might want automatically, and put it into a nice, neat little table. However, with an interactive system like R it is usually even easier to test a full model vs. a reduced model. That is if I want to test the significance of an interaction, I would use anova(lm.fit2, lm.fit1) where lm.fit2 contains the interaction and lm.fit2 does not. The anova function will return the appropriate F-test. The danger with worrying about what type of sums of squares to use is that often we do not think about what hypotheses we are testing and if those hypotheses make sense in our situation. Mark Lyman __ 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 and provide commented, minimal, self-contained, reproducible code.
