I am working on my thesis in which i have couple of independent variables that are categorical in nature and the depndent variable is dichotomus. Initially I run univariate analysis and added the variables with significant p-values (p<0.25) in my full model. I have three confusions. Firstly, I am looking for confounding variables by using formula "(crude beta-cofficient - adjusted beta-cofficient)/ crude beta-cofficient x 100" as per rule if the percentage of any variable is >10% than I have considered that as confounder. I wanted to know that from initial model i have deducted one variable with insignificant p-value to form adjusted model. Now how will i know if the variable that i deducted from initial model was confounder or not? Secondly, I wanted to know if the percentage comes in negative like (-17.84%) than will it be considered as confounder or not? I also wanted to know that confounders should be removed from model? or should be kept in model? Lastly, I wanted to know that I am running likelihood ratio test to identify if the value is falling in critical region or not. So if the value doesnot fall in critical region than what does it show? what should I do in this case? In my final reduced model all p-values are significant but still the value identified via likelihood ratio test is not falling in critical region. So what does that show? -- View this message in context: http://r.789695.n4.nabble.com/Logistic-Regression-tp3578962p3578962.html Sent from the R help mailing list archive at Nabble.com.
----------------------------------------> Date: Tue, 7 Jun 2011 01:38:32 -0700 > From: farah.farid.n09 at student.aku.edu > To: r-help at r-project.org > Subject: [R] Logistic Regression > > I am working on my thesis in which i have couple of independent variables > that are categorical in nature and the depndent variable is dichotomus. > Initially I run univariate analysis and added the variables with significant > p-values (p<0.25) in my full model. > I have three confusions. Firstly, I am looking for confounding variables byI'm not sure what your thesis is about, some system that you are strying by statistics or maybe the thesis is about statistics, but according to this disputed wikipedia entry, http://en.wikipedia.org/wiki/Confounding confounding or extraneous is determined by the reality of your system. It may help to consider factors related to that and use the statistics to avoid fooling yourself. Look at the pictures ( non-pompous way of saying look at graphs and scatter plots for some ideas to test ) and then test various ideas. You see bad cause/effect inferences all the time in many fields- from econ to biotech ( although anecdotes suggest these mistakes usually favour the sponsors LOL). Consider some mundane "known" examples about what your data would look like and see if that relates to what you have. If you were naively measuring car velocity at a single point in front of traffic light and color of light, what might you observe ( much like with an earlier example on iron in patients, there are a number of more precisely defined measurements you could take on a given "thing."). If your concern is that " I ran test A and it said B but test C said D and D seems inconsistent with B" it generally helps to look at assumptions and detailed equations for each model and explore what those mean with your data. With continuous variables anyway, non-monotonic relationships can easily destroy a correlation even with strong causality.> using formula "(crude beta-cofficient - adjusted beta-cofficient)/ crude > beta-cofficient x 100" as per rule if the percentage of any variable is >10% > than I have considered that as confounder. I wanted to know that from > initial model i have deducted one variable with insignificant p-value to > form adjusted model. Now how will i know if the variable that i deducted > from initial model was confounder or not? > Secondly, I wanted to know if the percentage comes in negative like > (-17.84%) than will it be considered as confounder or not? I also wanted to > know that confounders should be removed from model? or should be kept in > model? > Lastly, I wanted to know that I am running likelihood ratio test to identify > if the value is falling in critical region or not. So if the value doesnot > fall in critical region than what does it show? what should I do in this > case? In my final reduced model all p-values are significant but still the > value identified via likelihood ratio test is not falling in critical > region. So what does that show? > > > -- > View this message in context: http://r.789695.n4.nabble.com/Logistic-Regression-tp3578962p3578962.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help at 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.
The "10% change" idea was never a good one and has not been backed up by simulations. It is quite arbitrary and results in optimistic standard errors of remaining variables. In fact a paper presented at the Joint Statistical Meetings about 3 years ago (I'm sorry I've forgotten the names of the authors) showed that conflicting results are obtained according to whether you apply the 10% to the coefficients or to the odds ratios, and there is no theory to guide the choice. Why risk residual confounding? Form a good model apriori and adjust for all potential confounders; don't base the choice on P-values. Use propensity scores if overfitting is an issue. Frank farahnazlakhani wrote:> > I am working on my thesis in which i have couple of independent variables > that are categorical in nature and the depndent variable is dichotomus. > Initially I run univariate analysis and added the variables with > significant p-values (p<0.25) in my full model. > I have three confusions. Firstly, I am looking for confounding variables > by using formula "(crude beta-cofficient - adjusted beta-cofficient)/ > crude beta-cofficient x 100" as per rule if the percentage of any variable > is >10% than I have considered that as confounder. I wanted to know that > from initial model i have deducted one variable with insignificant p-value > to form adjusted model. Now how will i know if the variable that i > deducted from initial model was confounder or not? > Secondly, I wanted to know if the percentage comes in negative like > (-17.84%) than will it be considered as confounder or not? I also wanted > to know that confounders should be removed from model? or should be kept > in model? > Lastly, I wanted to know that I am running likelihood ratio test to > identify if the value is falling in critical region or not. So if the > value doesnot fall in critical region than what does it show? what should > I do in this case? In my final reduced model all p-values are significant > but still the value identified via likelihood ratio test is not falling in > critical region. So what does that show? >----- Frank Harrell Department of Biostatistics, Vanderbilt University -- View this message in context: http://r.789695.n4.nabble.com/Logistic-Regression-tp3578962p3579392.html Sent from the R help mailing list archive at Nabble.com.
IMHO, you evidence considerable confusion and misunderstanding of statistical methods. I would say that most of what you describe is nonsense. Of course, maybe I'm just the one who's confused, but I would strongly suggest you consult with a local statistician. This list is unlikely to be able to provide you the level of support and understanding that you need. Cheers, Bert On Tue, Jun 7, 2011 at 1:38 AM, farahnazlakhani <farah.farid.n09 at student.aku.edu> wrote:> I am working on my thesis in which i have couple of independent variables > that are categorical in nature and the depndent variable is dichotomus. > Initially I run univariate analysis and added the variables with significant > p-values (p<0.25) in my full model. > I have three confusions. Firstly, I am looking for confounding variables by > using formula "(crude beta-cofficient - adjusted beta-cofficient)/ crude > beta-cofficient x 100" as per rule if the percentage of any variable is >10% > than I have considered that as confounder. I wanted to know that from > initial model i have deducted one variable with insignificant p-value to > form adjusted model. Now how will i know if the variable that i deducted > from initial model was confounder or not? > Secondly, I wanted to know if the percentage comes in negative like > (-17.84%) than will it be considered as confounder or not? I also wanted to > know that confounders should be removed from model? or should be kept in > model? > Lastly, I wanted to know that I am running likelihood ratio test to identify > if the value is falling in critical region or not. So if the value doesnot > fall in critical region than what does it show? what should I do in this > case? In my final reduced model all p-values are significant but still the > value identified via likelihood ratio test is not falling in critical > region. So what does that show? > > > -- > View this message in context: http://r.789695.n4.nabble.com/Logistic-Regression-tp3578962p3578962.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help at 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. >-- "Men by nature long to get on to the ultimate truths, and will often be impatient with elementary studies or fight shy of them. If it were possible to reach the ultimate truths without the elementary studies usually prefixed to them, these would not be preparatory studies but superfluous diversions." -- Maimonides (1135-1204) Bert Gunter Genentech Nonclinical Biostatistics