[R] Website, book, paper, etc. that shows example plots of distributions?
By any chance is any one aware of a website, book, paper, etc. or combinations of those sources that show plots of different distributions? After reading a pretty good whitepaper I became aware of the benefit of I the benefit of doing Q-Q plots and histograms to help assess a distribution. The whitepaper is called: "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , © 2002-2008 The Trustees of Indiana University Univariate Analysis and Normality Test: 1, Hun Myoung Park Unfortunately the white paper does not provide an extensive amount of example distributions plotted using Q-Q plots and histograms, so I am curious if there is a "portfolio"-type website or other whitepaper shows examples of various types of distributions. It would be helpful to see a bunch of Q-Q plots and their associated histograms to get an idea of how the distribution looks in comparison against the Gaussian. I think seeing the plot really helps. Thank you for any insights. [[alternative HTML version deleted]] __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
You may find the qreference function in the DAAG package helpful. It makes several QQ plots to give a sense of what kind of fluctuations can be expected. You can also construct a series of any plots you are interested in (using different distributions), and modifying the code in this function may help with this. On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert wrote: > By any chance is any one aware of a website, book, paper, etc. or > combinations of those sources that show plots of different distributions? > > After reading a pretty good whitepaper I became aware of the benefit of I the > benefit of doing Q-Q plots and histograms to help assess a distribution. > The whitepaper is called: > "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , (c) > 2002-2008 The Trustees of Indiana University Univariate Analysis and > Normality Test: 1, Hun Myoung Park > > Unfortunately the white paper does not provide an extensive amount of example > distributions plotted using Q-Q plots and histograms, so I am curious if > there is a "portfolio"-type website or other whitepaper shows examples of > various types of distributions. > > It would be helpful to see a bunch of Q-Q plots and their associated > histograms to get an idea of how the distribution looks in comparison against > the Gaussian. > > I think seeing the plot really helps. > > Thank you for any insights. > > > >[[alternative HTML version deleted]] > > > __ > R-help@r-project.org 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. > > __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
Thank you for the guidance. I gave the qreference, but I guess I don't get it. What are the other plots that are generated? It is my understanding that qreference only produces normal QQ plots, so should the take away be if my data distribution, the first plot, isn't similar to any of the other Q-Q plots, then it is not normal? I was hoping to be able to compare my distribution in Q-Q Plot against images of other distributions in Q-Q Plot distributions. That is I would like to determine if my distribution determine if my distribution more closely resembles an exponential, Weibull, Normal, Log-Normal, etc. using the Q-Q Plot. Not sure if there is an existing package or function to do this or if trail by error is the best approach. From the below, it sounds like I would have to construct a series of Q-Q plots and manually compare them against my distribution. Thank you again for any further insights. --- On Thu, 2/12/09, Juliet Hannah wrote: From: Juliet Hannah Subject: Re: [R] Website, book, paper, etc. that shows example plots of distributions? To: jasonkrup...@yahoo.com Cc: R-help@r-project.org Date: Thursday, February 12, 2009, 1:00 PM You may find the qreference function in the DAAG package helpful. It makes several QQ plots to give a sense of what kind of fluctuations can be expected. You can also construct a series of any plots you are interested in (using different distributions), and modifying the code in this function may help with this. On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert wrote: > By any chance is any one aware of a website, book, paper, etc. or combinations of those sources that show plots of different distributions? > > After reading a pretty good whitepaper I became aware of the benefit of I the benefit of doing Q-Q plots and histograms to help assess a distribution. The whitepaper is called: > "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , (c) 2002-2008 The Trustees of Indiana University Univariate Analysis and Normality Test: 1, Hun Myoung Park > > Unfortunately the white paper does not provide an extensive amount of example distributions plotted using Q-Q plots and histograms, so I am curious if there is a "portfolio"-type website or other whitepaper shows examples of various types of distributions. > > It would be helpful to see a bunch of Q-Q plots and their associated histograms to get an idea of how the distribution looks in comparison against the Gaussian. > > I think seeing the plot really helps. > > Thank you for any insights. > > > >[[alternative HTML version deleted]] > > > __ > R-help@r-project.org 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. > > [[alternative HTML version deleted]] __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
You can readily create a dynamic display for using qqplot and similar functions in conjunction with either the playwith or TeachingDemos packages. For example, to investigate the effect of the shape parameter in the skew normal distribution on its qqplot relative to the normal distribution: library(playwith) library(sn) playwith(qqnorm(rsn(100, shape = shape)), parameters = list(shape = seq(-3, 3, .1))) Now move the slider located at the bottom of the window that appears and watch the plot change in response to changing the shape value. You can find more distributions here: http://cran.r-project.org/web/views/Distributions.html On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert wrote: > By any chance is any one aware of a website, book, paper, etc. or > combinations of those sources that show plots of different distributions? > > After reading a pretty good whitepaper I became aware of the benefit of I the > benefit of doing Q-Q plots and histograms to help assess a distribution. > The whitepaper is called: > "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , (c) > 2002-2008 The Trustees of Indiana University Univariate Analysis and > Normality Test: 1, Hun Myoung Park > > Unfortunately the white paper does not provide an extensive amount of example > distributions plotted using Q-Q plots and histograms, so I am curious if > there is a "portfolio"-type website or other whitepaper shows examples of > various types of distributions. > > It would be helpful to see a bunch of Q-Q plots and their associated > histograms to get an idea of how the distribution looks in comparison against > the Gaussian. > > I think seeing the plot really helps. > > Thank you for any insights. > > > >[[alternative HTML version deleted]] > > > __ > R-help@r-project.org 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. > > __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
Thank you very much. Thank you again regarding the suggestion below. I will give that a shot and I guess I've got my work counted out for me. I counted 45 different distributions. Is the best way to get a QQPlot of each, to run through producing a data set for each distribution and then using the qqplot function to get a QQplot of the distribution and then compare it with my data distribution? As you can tell I am not a trained statistician, so any guidance or suggested further reading is greatly appreciated. I guess I am pretty sure my data is not a normal distribution due to doing some of the empirical "Goodness of Fit" tests and comparing the QQplot of my data against the QQPlot of a normal distribution with the same number of points. I guess the next step is to figure out which distribution my data most closely matches. Also, I guess I could also fool around and take the log, sqrt, etc. of my data and see if it will then more closely resemble a normal distribution. Thank you again for assisting this novice data analyst who is trying to gain a better understanding of the techniques using this powerful software package. --- On Fri, 2/13/09, Gabor Grothendieck wrote: From: Gabor Grothendieck Subject: Re: [R] Website, book, paper, etc. that shows example plots of distributions? To: jasonkrup...@yahoo.com Cc: R-help@r-project.org Date: Friday, February 13, 2009, 5:43 AM You can readily create a dynamic display for using qqplot and similar functions in conjunction with either the playwith or TeachingDemos packages. For example, to investigate the effect of the shape parameter in the skew normal distribution on its qqplot relative to the normal distribution: library(playwith) library(sn) playwith(qqnorm(rsn(100, shape = shape)), parameters = list(shape = seq(-3, 3, .1))) Now move the slider located at the bottom of the window that appears and watch the plot change in response to changing the shape value. You can find more distributions here: http://cran.r-project.org/web/views/Distributions.html On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert wrote: > By any chance is any one aware of a website, book, paper, etc. or combinations of those sources that show plots of different distributions? > > After reading a pretty good whitepaper I became aware of the benefit of I the benefit of doing Q-Q plots and histograms to help assess a distribution. The whitepaper is called: > "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , (c) 2002-2008 The Trustees of Indiana University Univariate Analysis and Normality Test: 1, Hun Myoung Park > > Unfortunately the white paper does not provide an extensive amount of example distributions plotted using Q-Q plots and histograms, so I am curious if there is a "portfolio"-type website or other whitepaper shows examples of various types of distributions. > > It would be helpful to see a bunch of Q-Q plots and their associated histograms to get an idea of how the distribution looks in comparison against the Gaussian. > > I think seeing the plot really helps. > > Thank you for any insights. > > > >[[alternative HTML version deleted]] > > > __ > R-help@r-project.org 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. > > [[alternative HTML version deleted]] __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
You might also want to look at the idealized situation: library(playwith) library(sn) playwith(qqnorm(qsn(1:99/100, shape = shape)), parameters = list(shape = seq(-3, 3, .1))) On Fri, Feb 13, 2009 at 6:43 AM, Gabor Grothendieck wrote: > You can readily create a dynamic display for using qqplot and similar > functions > in conjunction with either the playwith or TeachingDemos packages. > > For example, to investigate the effect of the shape parameter in the skew > normal distribution on its qqplot relative to the normal distribution: > > library(playwith) > library(sn) > playwith(qqnorm(rsn(100, shape = shape)), > parameters = list(shape = seq(-3, 3, .1))) > > Now move the slider located at the bottom of the window that > appears and watch the plot change in response to changing > the shape value. > > You can find more distributions here: > http://cran.r-project.org/web/views/Distributions.html > > On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert wrote: >> By any chance is any one aware of a website, book, paper, etc. or >> combinations of those sources that show plots of different distributions? >> >> After reading a pretty good whitepaper I became aware of the benefit of I >> the benefit of doing Q-Q plots and histograms to help assess a distribution. >> The whitepaper is called: >> "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , (c) >> 2002-2008 The Trustees of Indiana University Univariate Analysis and >> Normality Test: 1, Hun Myoung Park >> >> Unfortunately the white paper does not provide an extensive amount of >> example distributions plotted using Q-Q plots and histograms, so I am >> curious if there is a "portfolio"-type website or other whitepaper shows >> examples of various types of distributions. >> >> It would be helpful to see a bunch of Q-Q plots and their associated >> histograms to get an idea of how the distribution looks in comparison >> against the Gaussian. >> >> I think seeing the plot really helps. >> >> Thank you for any insights. >> >> >> >>[[alternative HTML version deleted]] >> >> >> __ >> R-help@r-project.org 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. >> >> > __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
This is probably the right time to issue a warning about the error of making transformations on the dependent variable before doing your analysis. The classic error that newcomers to statistics commit is to decide that they want to "make their data normal". The assumptions of most regression methods is that the *errors* need to have the desired relationship between means and variance, and not that the dependent variable be "normal". Many times the apparent non-normality will be "explained" or "captured" by the regression model. Other methods of modeling non-linear dependence are also available. I found Harrell's book "Regression Modeling Strategies" to be an excellent source for alternatives. My copy of V&R's MASS is only the second edition but chapters 5 & 6 in that edition on linear models also had examples of using QQ plots on residuals. Checking that text's website I see that chapters 6 at least is probably similar. They include the scripts from their chapters along with the MASS package (installed as part of the VR bundle). My copy is entitled "ch06.r" and resides in the scripts subdirectory: /Library/Frameworks/R.framework/Versions/2.8/Resources/library/MASS/ scripts/ch06.R -- David Winsemius On Feb 13, 2009, at 8:11 AM, Jason Rupert wrote: Thank you very much. Thank you again regarding the suggestion below. I will give that a shot and I guess I've got my work counted out for me. I counted 45 different distributions. Is the best way to get a QQPlot of each, to run through producing a data set for each distribution and then using the qqplot function to get a QQplot of the distribution and then compare it with my data distribution? As you can tell I am not a trained statistician, so any guidance or suggested further reading is greatly appreciated. I guess I am pretty sure my data is not a normal distribution due to doing some of the empirical "Goodness of Fit" tests and comparing the QQplot of my data against the QQPlot of a normal distribution with the same number of points. I guess the next step is to figure out which distribution my data most closely matches. Also, I guess I could also fool around and take the log, sqrt, etc. of my data and see if it will then more closely resemble a normal distribution. Thank you again for assisting this novice data analyst who is trying to gain a better understanding of the techniques using this powerful software package. --- On Fri, 2/13/09, Gabor Grothendieck wrote: From: Gabor Grothendieck Subject: Re: [R] Website, book, paper, etc. that shows example plots of distributions? To: jasonkrup...@yahoo.com Cc: R-help@r-project.org Date: Friday, February 13, 2009, 5:43 AM You can readily create a dynamic display for using qqplot and similar functions in conjunction with either the playwith or TeachingDemos packages. For example, to investigate the effect of the shape parameter in the skew normal distribution on its qqplot relative to the normal distribution: library(playwith) library(sn) playwith(qqnorm(rsn(100, shape = shape)), parameters = list(shape = seq(-3, 3, .1))) Now move the slider located at the bottom of the window that appears and watch the plot change in response to changing the shape value. You can find more distributions here: http://cran.r-project.org/web/views/Distributions.html On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert wrote: By any chance is any one aware of a website, book, paper, etc. or combinations of those sources that show plots of different distributions? After reading a pretty good whitepaper I became aware of the benefit of I the benefit of doing Q-Q plots and histograms to help assess a distribution. The whitepaper is called: "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , (c) 2002-2008 The Trustees of Indiana University Univariate Analysis and Normality Test: 1, Hun Myoung Park Unfortunately the white paper does not provide an extensive amount of example distributions plotted using Q-Q plots and histograms, so I am curious if there is a "portfolio"-type website or other whitepaper shows examples of various types of distributions. It would be helpful to see a bunch of Q-Q plots and their associated histograms to get an idea of how the distribution looks in comparison against the Gaussian. I think seeing the plot really helps. Thank you for any insights. [[alternative HTML version deleted]] __ R-help@r-project.org 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. [[alternative HTML version deleted]] __
Re: [R] Website, book, paper, etc. that shows example plots of distributions?
Why do you care what distribution your data comes from? That is a serious question, the more we know about what your actual question/goal is, the more we can help. It is a common mistake for people who know enough statistics to be dangerous to focus on the distribution of the data rather than the question of interest. Many of the traditional statistical tests/models based on the assumption of normality are still useful when the data does not follow a normal distribution as long as the sample size is large enough. If the above does not hold, there are often alternative tests/methods that don't rely on a specific known distribution. A simple transformation may get you close enough. David mentioned that some cases it is the distribution of the errors, not the original data that matters. Some people mistakenly think that the explanatory variables need to be normal in a regression as well, but that is not needed. For finding transformations that get you closer to normal, look at the boxcox function in the MASS package and possibly the vis.boxcox and vis.boxcoxu functions in the TeachingDemos package (and the paper referenced there). If you really want to know the distribution of the data, you should start with the science, not the data and examples. Random chance can make data from one distribution look like it comes from a different but similar one. Start with the nature of the problem (without looking at the data), will the values be discrete or continuous?, is there a lower/upper limit on the values possible? Is it likely to be skewed (have extreme values in one direction)? What distributions are commonly used in this area? Etc. Answering those questions can narrow down the candidates. Hope this helps, -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare greg.s...@imail.org 801.408.8111 > -Original Message- > From: r-help-boun...@r-project.org [mailto:r-help-boun...@r- > project.org] On Behalf Of Jason Rupert > Sent: Friday, February 13, 2009 6:12 AM > To: Gabor Grothendieck > Cc: R-help@r-project.org > Subject: Re: [R] Website, book, paper, etc. that shows example plots of > distributions? > > Thank you very much. Thank you again regarding the suggestion below. > I will give that a shot and I guess I've got my work counted out for > me. I counted 45 different distributions. > > Is the best way to get a QQPlot of each, to run through producing a > data set for each distribution and then using the qqplot function to > get a QQplot of the distribution and then compare it with my data > distribution? > > As you can tell I am not a trained statistician, so any guidance or > suggested further reading is greatly appreciated. > > I guess I am pretty sure my data is not a normal distribution due to > doing some of the empirical "Goodness of Fit" tests and comparing the > QQplot of my data against the QQPlot of a normal distribution with the > same number of points. I guess the next step is to figure out which > distribution my data most closely matches. > > Also, I guess I could also fool around and take the log, sqrt, etc. of > my data and see if it will then more closely resemble a normal > distribution. > > Thank you again for assisting this novice data analyst who is trying to > gain a better understanding of the techniques using this powerful > software package. > > > > > --- On Fri, 2/13/09, Gabor Grothendieck > wrote: > From: Gabor Grothendieck > Subject: Re: [R] Website, book, paper, etc. that shows example plots of > distributions? > To: jasonkrup...@yahoo.com > Cc: R-help@r-project.org > Date: Friday, February 13, 2009, 5:43 AM > > You can readily create a dynamic display for using qqplot and similar > functions > in conjunction with either the playwith or TeachingDemos packages. > > For example, to investigate the effect of the shape parameter in the > skew > normal distribution on its qqplot relative to the normal distribution: > >library(playwith) >library(sn) >playwith(qqnorm(rsn(100, shape = shape)), >parameters = list(shape = seq(-3, 3, .1))) > > Now move the slider located at the bottom of the window that > appears and watch the plot change in response to changing > the shape value. > > You can find more distributions here: > http://cran.r-project.org/web/views/Distributions.html > > On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert > wrote: > > By any chance is any one aware of a website, book, paper, etc. or > combinations of those sources that show plots of different > distributions? > > > > After reading a pretty good whitepaper I became aware of the benefit > of I > the benefit of doing Q-Q plots and histograms to help assess a
Re: [R] Website, book, paper, etc. that shows example plots of distributions?
Jason, Just to answer your direct question, there is Mathowrld.wolfram.com, where there are 87 continuous distributions listed. I have also used the book Statistical Distributions, 2nd ed, Merran Evans, et al. which has most of the usual distributions with pictures and relationships. Of course all of the advice about really thinking about what you are trying to accomplish is right on target. HTH, -- David -Original Message- From: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] On Behalf Of Jason Rupert Sent: Friday, February 13, 2009 7:12 AM To: Gabor Grothendieck Cc: R-help@r-project.org Subject: Re: [R] Website, book, paper,etc. that shows example plots of distributions? Thank you very much. Thank you again regarding the suggestion below. I will give that a shot and I guess I've got my work counted out for me. I counted 45 different distributions. Is the best way to get a QQPlot of each, to run through producing a data set for each distribution and then using the qqplot function to get a QQplot of the distribution and then compare it with my data distribution? As you can tell I am not a trained statistician, so any guidance or suggested further reading is greatly appreciated. I guess I am pretty sure my data is not a normal distribution due to doing some of the empirical "Goodness of Fit" tests and comparing the QQplot of my data against the QQPlot of a normal distribution with the same number of points. I guess the next step is to figure out which distribution my data most closely matches. Also, I guess I could also fool around and take the log, sqrt, etc. of my data and see if it will then more closely resemble a normal distribution. Thank you again for assisting this novice data analyst who is trying to gain a better understanding of the techniques using this powerful software package. --- On Fri, 2/13/09, Gabor Grothendieck wrote: From: Gabor Grothendieck Subject: Re: [R] Website, book, paper, etc. that shows example plots of distributions? To: jasonkrup...@yahoo.com Cc: R-help@r-project.org Date: Friday, February 13, 2009, 5:43 AM You can readily create a dynamic display for using qqplot and similar functions in conjunction with either the playwith or TeachingDemos packages. For example, to investigate the effect of the shape parameter in the skew normal distribution on its qqplot relative to the normal distribution: library(playwith) library(sn) playwith(qqnorm(rsn(100, shape = shape)), parameters = list(shape = seq(-3, 3, .1))) Now move the slider located at the bottom of the window that appears and watch the plot change in response to changing the shape value. You can find more distributions here: http://cran.r-project.org/web/views/Distributions.html On Thu, Feb 12, 2009 at 1:04 PM, Jason Rupert wrote: > By any chance is any one aware of a website, book, paper, etc. or combinations of those sources that show plots of different distributions? > > After reading a pretty good whitepaper I became aware of the benefit of I the benefit of doing Q-Q plots and histograms to help assess a distribution. The whitepaper is called: > "Univariate Analysis and Normality Test Using SAS, Stata, and SPSS*" , (c) 2002-2008 The Trustees of Indiana University Univariate Analysis and Normality Test: 1, Hun Myoung Park > > Unfortunately the white paper does not provide an extensive amount of example distributions plotted using Q-Q plots and histograms, so I am curious if there is a "portfolio"-type website or other whitepaper shows examples of various types of distributions. > > It would be helpful to see a bunch of Q-Q plots and their associated histograms to get an idea of how the distribution looks in comparison against the Gaussian. > > I think seeing the plot really helps. > > Thank you for any insights. > > > >[[alternative HTML version deleted]] > > > __ > R-help@r-project.org 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. > > [[alternative HTML version deleted]] __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
Many thanks to Greg L. Snow and David Winsemius for their responses. First off I can safely say I don't know enough statistics to be dangerous, but hopefully I will get to that point:) Regarding the goal - ultimately I would like to use linear regression (constrained for using linear regression at this point) for my data. I thought the requirements for using linear regression was the following (I pulled this list from www.utexas.edu/courses/schwab/sw318_spring_2004/SolvingProblems/Class27_RegressionNCorrHypoTest.ppt): The assumptions required for utilizing a regression equation are the same as the assumptions for the test of significance of a correlation coefficient. Both variables are interval level. Both variables are normally distributed. The relationship between the two variables is linear. The variance of the values of the dependent variable is uniform for all values of the independent variable (equality of variance). Thus, I was going to attempt to (1) identify which distribution my data most closely represents, (2) translate my data so that it is normal, and (3) then use linear regression on the data. However, if "The assumptions of most regression methods is that the *errors* need to have the desired relationship between means and variance, and not that the dependent variable be "normal". Many times the apparent non-normality will be "explained" or "captured" by the regression model." Does this mean I can just "do" linear regression without translating my data and it will be okay? Note that I was using "lm" from R to access the errors, however, I had not an opportunity to do much analysis of those results to determine if they are Gaussian or not. I guess I am going to try to track down the following documents: (1) Statistical Distributions (Paperback) by Merran Evans (Author), Nicholas Hastings (Author), Brian Peacock (Author) # ISBN-10: 0471371246 # ISBN-13: 978-0471371243 (2) Regression Modeling Strategies (Hardcover) by Frank E. Jr. Harrell (Author) # ISBN-10: 0387952322 # ISBN-13: 978-0387952321 Maybe electronic versions of those documents are available. My wife is already giving me a hard time the volume of books around. Thank you again for all your feedback and insights. --- On Fri, 2/13/09, David Winsemius wrote: From: David Winsemius Subject: Re: [R] Website, book, paper, etc. that shows example plots of distributions? To: jasonkrup...@yahoo.com Cc: "Gabor Grothendieck" , R-help@r-project.org Date: Friday, February 13, 2009, 9:10 AM This is probably the right time to issue a warning about the error of making transformations on the dependent variable before doing your analysis. The classic error that newcomers to statistics commit is to decide that they want to "make their data normal". The assumptions of most regression methods is that the *errors* need to have the desired relationship between means and variance, and not that the dependent variable be "normal". Many times the apparent non-normality will be "explained" or "captured" by the regression model. Other methods of modeling non-linear dependence are also available. I found Harrell's book "Regression Modeling Strategies" to be an excellent source for alternatives. My copy of V&R's MASS is only the second edition but chapters 5 & 6 in that edition on linear models also had examples of using QQ plots on residuals. Checking that text's website I see that chapters 6 at least is probably similar. They include the scripts from their chapters along with the MASS package (installed as part of the VR bundle). My copy is entitled "ch06.r" and resides in the scripts subdirectory: /Library/Frameworks/R.framework/Versions/2.8/Resources/library/MASS/scripts/ch06.R --David Winsemius On Feb 13, 2009, at 8:11 AM, Jason Rupert wrote: > Thank you very much. Thank you again regarding the suggestion below. I will give that a shot and I guess I've got my work counted out for me. I counted 45 different distributions. > > Is the best way to get a QQPlot of each, to run through producing a data set for each distribution and then using the qqplot function to get a QQplot of the distribution and then compare it with my data distribution? > > As you can tell I am not a trained statistician, so any guidance or suggested further reading is greatly appreciated. > > I guess I am pretty sure my data is not a normal distribution due to doing some of the empirical "Goodness of Fit" tests and comparing the QQplot of my data against the QQPlot of a normal distribution with the same number of points. I guess the next step is to figure out which distribution my data most closely matches. > > Also, I guess I could also fool around and take the log, sqrt, etc. of my data and see if it will then more
Re: [R] Website, book, paper, etc. that shows example plots of distributions?
The regression book by John Fox: http://socserv.mcmaster.ca/jfox/Books/Companion/index.html has a section on regression diagnostics and everything is done in R which might make it particularly suitable. On Sat, Feb 14, 2009 at 6:48 PM, Jason Rupert wrote: > Many thanks to Greg L. Snow and David Winsemius for their responses. > > First off I can safely say I don't know enough statistics to be dangerous, > but hopefully I will get to that point:) > > Regarding the goal - ultimately I would like to use linear regression > (constrained for using linear regression at this point) for my data. I > thought the requirements for using linear regression was the following (I > pulled this list from > www.utexas.edu/courses/schwab/sw318_spring_2004/SolvingProblems/Class27_RegressionNCorrHypoTest.ppt): > > The assumptions required for utilizing a regression equation are the same as > the assumptions for the test of significance of a correlation coefficient. > Both variables are interval level. > Both variables are normally distributed. > The relationship between the two variables is linear. > The variance of the values of the dependent variable is uniform for all > values of the independent variable (equality of variance). > > Thus, I was going to attempt to (1) identify which distribution my data most > closely represents, (2) translate my data so that it is normal, and (3) then > use linear regression on the data. > > However, if > "The assumptions of most regression methods is that the *errors* need to > have the desired relationship between means and variance, and not that the > dependent variable be "normal". Many times the apparent non-normality will > be "explained" or "captured" by the regression model." > > Does this mean I can just "do" linear regression without translating my data > and it will be okay? > > Note that I was using "lm" from R to access the errors, however, I had not > an opportunity to do much analysis of those results to determine if they are > Gaussian or not. > > I guess I am going to try to track down the following documents: > (1) Statistical Distributions (Paperback) > by Merran Evans (Author), Nicholas Hastings (Author), Brian Peacock (Author) > # ISBN-10: 0471371246 > # ISBN-13: 978-0471371243 > > (2) Regression Modeling Strategies (Hardcover) > by Frank E. Jr. Harrell (Author) > # ISBN-10: 0387952322 > # ISBN-13: 978-0387952321 > > Maybe electronic versions of those documents are available. My wife is > already giving me a hard time the volume of books around. > > Thank you again for all your feedback and insights. > > > --- On Fri, 2/13/09, David Winsemius wrote: > > From: David Winsemius > Subject: Re: [R] Website, book, paper, etc. that shows example plots of > distributions? > To: jasonkrup...@yahoo.com > Cc: "Gabor Grothendieck" , R-help@r-project.org > Date: Friday, February 13, 2009, 9:10 AM > > This is probably the right time to issue a warning about the error of making > transformations on the dependent variable before doing your analysis. The > classic error that newcomers to statistics commit is to decide that they > want to > "make their data normal". The assumptions of most regression methods > is that the *errors* need to have the desired relationship between means and > variance, and not that the dependent variable be "normal". Many times > the apparent non-normality will be "explained" or "captured" > by the regression model. Other methods of modeling non-linear dependence are > also available. > > I found Harrell's book "Regression Modeling Strategies" to be an > excellent source for alternatives. My copy of V&R's MASS is only the > second edition but chapters 5 & 6 in that edition on > linear models also had > examples of using QQ plots on residuals. Checking that text's website I see > that chapters 6 at least is probably similar. They include the scripts from > their chapters along with the MASS package (installed as part of the VR > bundle). > My copy is entitled "ch06.r" and resides in the scripts subdirectory: > /Library/Frameworks/R.framework/Versions/2.8/Resources/library/MASS/scripts/ch06.R > > --David Winsemius > > > On Feb 13, 2009, at 8:11 AM, Jason Rupert wrote: > >> Thank you very much. Thank you again regarding the suggestion below. I > will give that a shot and I guess I've got my work counted out for me. I > counted 45 different distributions. >> >> Is the best way to get a QQPlot of each, to run through producing a data > set for each distribution and then using the qqplot function to get a
Re: [R] Website, book, paper, etc. that shows example plots of distributions?
On Feb 14, 2009, at 6:48 PM, Jason Rupert wrote: > Many thanks to Greg L. Snow and David Winsemius for their responses. > > First off I can safely say I don't know enough statistics to be > dangerous, but hopefully I will get to that point:) > > Regarding the goal - ultimately I would like to use linear > regression (constrained for using linear regression at this point) > for my data. I thought the requirements for using linear regression > was the following (I pulled this list from > www.utexas.edu/courses/schwab/sw318_spring_2004/SolvingProblems/Class27_RegressionNCorrHypoTest.ppt) > > : > > The assumptions required for utilizing a regression equation are the > same as the assumptions for the test of significance of a > correlation coefficient. > Both variables are interval level. > Both variables are normally distributed. > The relationship between the two variables is linear. > The variance of the values of the dependent variable is uniform for > all values of the independent variable (equality of variance). > > Thus, I was going to attempt to (1) identify which distribution my > data most closely represents, (2) translate my data so that it is > normal, and (3) then use linear regression on the data. > > However, if > "The assumptions of most regression methods is that the *errors* > need to have the desired relationship between means and variance, > and not that the dependent variable be "normal". Many times the > apparent non-normality will be "explained" or "captured" by the > regression model." > > Does this mean I can just "do" linear regression without translating > my data and it will be okay? Not exactly. It does mean that you can "just do" linear regression but then check to see if "it was OK". The model will have the residuals in the regression object and these can be displayed with a scatterplot (versus the individual predictor variables) or as a QQ plot. > > > Note that I was using "lm" from R to access the errors, however, I > had not an opportunity to do much analysis of those results to > determine if they are Gaussian or not. > > I guess I am going to try to track down the following documents: > (1) Statistical Distributions (Paperback) > by Merran Evans (Author), Nicholas Hastings (Author), Brian Peacock > (Author) > # ISBN-10: 0471371246 > # ISBN-13: 978-0471371243 > > (2) Regression Modeling Strategies (Hardcover) > by Frank E. Jr. Harrell (Author) > # ISBN-10: 0387952322 > # ISBN-13: 978-0387952321 > > Maybe electronic versions of those documents are available. My wife > is already giving me a hard time the volume of books around. Frank Harrell's website has a lot of material that he makes available online; http://biostat.mc.vanderbilt.edu/twiki/bin/view/Main/RmS snipped remainder -- David Winsemius [[alternative HTML version deleted]] __ R-help@r-project.org 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] Website, book, paper, etc. that shows example plots of distributions?
I had a Murphy's law calendar a while back with many different laws in it. One of those laws was along the lines of: An easily understood, simple falsehood is often more useful than a complicated, often misunderstood truth (though the original was probably much better phrased than my memory). Many rules in textbooks and classes follow this principle, especially when outside pressures force teachers to cover 4-6 hours of material in a 3 hour course. The set of assumptions you list below are of this type. They are a good simple place to start, and good enough for an introductory class, but a full discussion of the truth would take more time than is reasonable for an intro class. Yes, the theory on which linear models is based was originally derived using the assumptions of normality, but linear models are amazingly robust, meaning that if the normality assumptions don't hold, the results (p-values, confidence intervals) will still usually be "close enough". How "close" and if it is "enough" depends on sample size, how nonnormal the residuals are, and the specific question(s). For regression, start by "doing" the regression, but then look at the diagnostic plots of the residuals (see ?plot.lm). If you sample size is large and the residuals do not show strong skewness/outliers, then you are probably safe using the output of lm as is (Central Limit Thoerem, but still check other assumptions and make sure that what you are seeing/saying makes sense). If there is more skewness/outliers than you are comfortable with, then there are robust methods that will be more helpful here. Also note that if you know enough to find and use the lm function in R, then you know enough statistics to be dangerous (unless you are not allowed to make any decisions or communicate with anyone else (comma patients maybe)). The goal now is to learn to use that power to do good, posting/reading here and Frank's book are a good start in that direction. Hope this helps, -- Gregory (Greg) L. Snow Ph.D. Statistical Data Center Intermountain Healthcare greg.s...@imail.org 801.408.8111 > -Original Message- > From: r-help-boun...@r-project.org [mailto:r-help-boun...@r- > project.org] On Behalf Of Jason Rupert > Sent: Saturday, February 14, 2009 4:48 PM > To: David Winsemius > Cc: R-help@r-project.org > Subject: Re: [R] Website, book, paper, etc. that shows example plots of > distributions? > > Many thanks to Greg L. Snow and David Winsemius for their responses. > > First off I can safely say I don't know enough statistics to be > dangerous, but hopefully I will get to that point:) > > Regarding the goal - ultimately I would like to use linear regression > (constrained for using linear regression at this point) for my data. I > thought the requirements for using linear regression was the following > (I pulled this list from > www.utexas.edu/courses/schwab/sw318_spring_2004/SolvingProblems/Class27 > _RegressionNCorrHypoTest.ppt): > > The assumptions required for utilizing a regression equation are the > same as the assumptions for the test of significance of a correlation > coefficient. > Both variables are interval level. > Both variables are normally distributed. > The relationship between the two variables is linear. > The variance of the values of the dependent variable is uniform for all > values of the independent variable (equality of variance). > > Thus, I was going to attempt to (1) identify which distribution my data > most closely represents, (2) translate my data so that it is normal, > and (3) then use linear regression on the data. > > However, if > "The assumptions of most regression methods is that the *errors* need > to have the desired relationship between means and variance, and not > that the dependent variable be "normal". Many times the apparent non- > normality will be "explained" or "captured" by the regression model." > > Does this mean I can just "do" linear regression without translating my > data and it will be okay? > > Note that I was using "lm" from R to access the errors, however, I had > not an opportunity to do much analysis of those results to determine if > they are Gaussian or not. > > I guess I am going to try to track down the following documents: > (1) Statistical Distributions (Paperback) > by Merran Evans (Author), Nicholas Hastings (Author), Brian Peacock > (Author) > # ISBN-10: 0471371246 > # ISBN-13: 978-0471371243 > > (2) Regression Modeling Strategies (Hardcover) > by Frank E. Jr. Harrell (Author) > # ISBN-10: 0387952322 > # ISBN-13: 978-0387952321 > > Maybe electronic versions of those documents are available. My wife is > already giving