sasnewbie12 Tracker
https://communities.sas.com/kntur85557/tracker
sasnewbie12 TrackerFri, 19 Apr 2024 02:47:34 GMT2024-04-19T02:47:34ZRe: ANOVA one observation
https://communities.sas.com/t5/SAS-Procedures/ANOVA-one-observation/m-p/448324#M69571
<P>Its not a data issue. This is a two factor design, and there are one observations within each factor combination. </P><P> </P><P>How can I get ANOVA to display the SS and MS for each effect? It only give me the full model and error effects. I tried using the test statement as follows:</P><P> </P><P>Test h=[effect of interest] e=??? ;</P><P> </P><P>I am not sure what to put in the error statement, I just want it with the default error of MSE(mean squared error). </P><P> </P><P>Thanks</P>Fri, 23 Mar 2018 20:45:38 GMThttps://communities.sas.com/t5/SAS-Procedures/ANOVA-one-observation/m-p/448324#M69571sasnewbie122018-03-23T20:45:38ZRe: ANOVA one observation
https://communities.sas.com/t5/SAS-Procedures/ANOVA-one-observation/m-p/448284#M69569
<P>How can I get sas to display the SS and MS for each factor in the ANOVA table? There is only the model and error information. </P><P> </P><P>Thanks</P>Fri, 23 Mar 2018 18:48:12 GMThttps://communities.sas.com/t5/SAS-Procedures/ANOVA-one-observation/m-p/448284#M69569sasnewbie122018-03-23T18:48:12ZANOVA one observation
https://communities.sas.com/t5/SAS-Procedures/ANOVA-one-observation/m-p/448282#M69568
<P> I am conducting a two-factorial anova analysis with only one observation per cell. </P><P>How can I run the proc glm statement? I will add an interaction term for the two factors: factor a* factor b; </P><P> </P><P>Proc glm data=mydata;</P><P>class factor1 factor2;</P><P>model y= factor1 factor2 factor1*factor2; run;</P><P> </P><P>I am currently getting having an issue and the error SS and MS is coming up as 0.00; </P><P>I need to also break down the error SS into residual and interaction parts. </P><P> </P><P>Thanks</P>Fri, 23 Mar 2018 18:37:28 GMThttps://communities.sas.com/t5/SAS-Procedures/ANOVA-one-observation/m-p/448282#M69568sasnewbie122018-03-23T18:37:28ZRe: sum of squares error and treatment
https://communities.sas.com/t5/Statistical-Procedures/sum-of-squares-error-and-treatment/m-p/439311#M23158
<P>I do not have the data; this is an unusual scenario. </P>Thu, 22 Feb 2018 15:05:13 GMThttps://communities.sas.com/t5/Statistical-Procedures/sum-of-squares-error-and-treatment/m-p/439311#M23158sasnewbie122018-02-22T15:05:13Zsum of squares error and treatment
https://communities.sas.com/t5/Statistical-Procedures/sum-of-squares-error-and-treatment/m-p/439276#M23156
<P>I have information on 7 treatments, x, and am assessing their effects. If I have the means and standard deviations of the outcome measurement, y, along with the numbers of observations for each treatment, n, how can I calculate the sum of squares for the error and for the treatment effects? </P><P> </P><P> </P>Thu, 22 Feb 2018 14:17:55 GMThttps://communities.sas.com/t5/Statistical-Procedures/sum-of-squares-error-and-treatment/m-p/439276#M23156sasnewbie122018-02-22T14:17:55ZStandardized residuals
https://communities.sas.com/t5/Statistical-Procedures/Standardized-residuals/m-p/439132#M23150
<P>I am comparing the effects of four treatments, x1,x2,x3,x4 on an outcome, y. I am using proc GLM to run this analysis. I need to calculate the standardized residuals for the model, how can I do that?</P><P> </P><P>Thank You</P>Thu, 22 Feb 2018 00:43:29 GMThttps://communities.sas.com/t5/Statistical-Procedures/Standardized-residuals/m-p/439132#M23150sasnewbie122018-02-22T00:43:29ZRe: Logistic Regression Collinearity
https://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423721#M104237
<P>Another question, if I find a categorical variable has non-significant association on multivariate analysis under "analysis of likelihood estimates", but the "Type 3 analysis of effects" shows that it is significant, what does that mean and how can it be interpreted?</P><P> </P><P> </P>Wed, 27 Dec 2017 13:41:14 GMThttps://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423721#M104237sasnewbie122017-12-27T13:41:14ZRe: Logistic Regression Collinearity
https://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423719#M104235
<P>A followup question, say that an independant variables has significant association on the "univariate" analysis, and non-significant on "multivariate" analysis, will I be able to make any use of the adjusted odds-ratio for that variable, if the p-value is non-significant ?</P><P> </P><P>I have seen studies where they list the adjusted odd-ratio without a p-value, so I am wondering if it holds any importance when it is non-significant?</P><P> </P><P>Thank You</P><P> </P><P> </P>Wed, 27 Dec 2017 13:33:38 GMThttps://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423719#M104235sasnewbie122017-12-27T13:33:38ZRe: Logistic Regression Collinearity
https://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423533#M104168
<P>I have a large number of observations, 200,000 weighted, so there should be no issue with the 20 variables from that stand point. </P><P> </P><P>I am also just trying to find associations between the independent variables and the dependent variable, and am not interested in building a powerful model. However, when I add or remove some of the variables, it causes a few of the other variables to change significance drastically, sometimes becoming significant only after adding another variable to the model. I don't want to come up with an association that may differ from what someone else may find if they look for they same associations (for example, if they have a slightly different selection of variables and show difference in significance from what I have shown, that would make my study seem inaccurate).</P><P> </P><P>Thank you</P>Tue, 26 Dec 2017 01:13:20 GMThttps://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423533#M104168sasnewbie122017-12-26T01:13:20ZLogistic Regression Collinearity
https://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423491#M104160
<P>I am trying to run a model with logistic regression containing about 20 independent variables, both categorical and continuous.</P><P>However, I am finding that the significance varies depending on which variables I include and exclude, and I believe that there is association and collinearity among the variables. </P><P> </P><P>As I am a new SAS user, is there any simple way to check for association among the variables in logistic regression? </P><P> </P><P>Thank You</P>Sun, 24 Dec 2017 22:05:35 GMThttps://communities.sas.com/t5/SAS-Programming/Logistic-Regression-Collinearity/m-p/423491#M104160sasnewbie122017-12-24T22:05:35ZChi-Square significance: what does it mean?
https://communities.sas.com/t5/Statistical-Procedures/Chi-Square-significance-what-does-it-mean/m-p/423469#M22285
<P>I am looking for binary outcome "speeding ticket" (1/0)</P><P> </P><P>I have a categorical variable "bright color" which is categorized into 1, 2, 3 and 0.</P><P> </P><P>I will run a chi-sq with speeding ticket*bright color </P><P> </P><P>On the other hand I make three categorical variables using the same information from bright colors 1, 2, and 3. Each bright color is made into a separate variable:</P><P>bright color 1 (1/0)</P><P>bright color 2 <SPAN>(1/0)</SPAN></P><P>bright color 3 <SPAN>(1/0)</SPAN></P><P><SPAN> </SPAN></P><P><SPAN>Then I will run a chi=sq with each variable such as:</SPAN></P><P><SPAN>bright color 1*speeding ticket</SPAN></P><P><SPAN>bright color 2*speeding ticket</SPAN></P><P><SPAN>bright color 3*speeding ticket</SPAN></P><P> </P><P><SPAN>Will there be a correlation between running a chi-sq testing bright color as a single variable vs. speeding ticket with categories 1, 2, 3 and on the other hand running 3 chi-sq testing bright colors as individual variables vs. speeding ticker(bright color1, bright color 2, bright color 3)??</SPAN></P><P> </P><P><SPAN>If I find a significant association when running each color as a separate variable, should I expect to find a significant association when running all the colors as one variable with multiple categories?</SPAN></P><P> </P><P><SPAN>Thank You</SPAN></P><P> </P><P> </P>Sat, 23 Dec 2017 23:15:31 GMThttps://communities.sas.com/t5/Statistical-Procedures/Chi-Square-significance-what-does-it-mean/m-p/423469#M22285sasnewbie122017-12-23T23:15:31ZLogistic Regression Categorization
https://communities.sas.com/t5/Statistical-Procedures/Logistic-Regression-Categorization/m-p/423326#M22279
<P> </P><P>Why is that when I categorize a variable in logistic regression by making it binary at the 75th percentile cutoff, it makes Variable 2 which was previously significant into non-significant. Then, when I change the categorization to binary while using an outlier number much greater than the 75th percentile as the cut off , Variable 2 then becomes significant again?</P><P> </P><P>For example</P><P> </P><P>1) model event1= variable 1(continuous), variable 2(categorical)</P><P> - variable 1 is significant, variable 2 is significant</P><P> </P><P>2) model event1= variable 1 (categorical at 75th percentile), variable 2(categorical)</P><P> - variable 1 is significant, variable 2 becomes non-significant</P><P> </P><P>3) model event1= variable1 (categorical at outlier point, much greater than 75th percentile), variable 2(categorical)</P><P> - variable 1 is significant, variable 2 is again significant</P>Fri, 22 Dec 2017 15:08:22 GMThttps://communities.sas.com/t5/Statistical-Procedures/Logistic-Regression-Categorization/m-p/423326#M22279sasnewbie122017-12-22T15:08:22ZRe: multivariate logistic regression: variable troubleshooting
https://communities.sas.com/t5/Statistical-Procedures/multivariate-logistic-regression-variable-troubleshooting/m-p/419428#M22065
<P>I haven't seen the warning "<SPAN>WARNING: The information matrix is singular and thus the convergence is questionable" </SPAN> and I am not getting any errors in the log statement. However, there is some other possible association between variables. </P><P> </P><P>I wonder if there is any way I can see whether some variables have whatever assocation there may be because I can find the problem variables and then remove them manually. </P><P> </P><P> </P><P> </P>Fri, 08 Dec 2017 01:07:16 GMThttps://communities.sas.com/t5/Statistical-Procedures/multivariate-logistic-regression-variable-troubleshooting/m-p/419428#M22065sasnewbie122017-12-08T01:07:16ZRe: multivariate logistic regression: variable troubleshooting
https://communities.sas.com/t5/Statistical-Procedures/multivariate-logistic-regression-variable-troubleshooting/m-p/419390#M22063
<P>How do I use this for survey data?</P><P>I need to account for stratums, clusters, and weights.</P><P>I am currently using Proc Surveylogistic.</P>Thu, 07 Dec 2017 22:16:38 GMThttps://communities.sas.com/t5/Statistical-Procedures/multivariate-logistic-regression-variable-troubleshooting/m-p/419390#M22063sasnewbie122017-12-07T22:16:38Zmultivariate logistic regression: variable troubleshooting
https://communities.sas.com/t5/Statistical-Procedures/multivariate-logistic-regression-variable-troubleshooting/m-p/419337#M22061
<P>I am assessing for outcome "eventX" with survey data.</P><P> </P><P>One variables, "diseaseX" has an association of p=0.023 on univariate chi square. </P><P> </P><P>When placed in the multivariate regression model with multiple other variables, it has a lower p-value of 0.0003. SAS does not give any messages about correlation and the model has convergence. </P><P> </P><P>If this is due to some kind association where one variable reenforces another (forgot what thats called), then how can I find which variable it is? Otherwise, how can I deal with this, is it ok to leave the variable in the model, if there is an association?</P><P> </P><P>Please explain. Thanks </P>Thu, 07 Dec 2017 20:46:13 GMThttps://communities.sas.com/t5/Statistical-Procedures/multivariate-logistic-regression-variable-troubleshooting/m-p/419337#M22061sasnewbie122017-12-07T20:46:13ZRe: Missing observations in Multivariate Regression
https://communities.sas.com/t5/SAS-Programming/Missing-observations-in-Multivariate-Regression/m-p/418008#M102683
<P>Just want to make sure, will observations that are missing a value for a variable that is not included in your model as a independant or dependant variable also be excluded?</P><P> </P><P> </P>Sun, 03 Dec 2017 15:41:56 GMThttps://communities.sas.com/t5/SAS-Programming/Missing-observations-in-Multivariate-Regression/m-p/418008#M102683sasnewbie122017-12-03T15:41:56ZMissing observations in Multivariate Regression
https://communities.sas.com/t5/SAS-Programming/Missing-observations-in-Multivariate-Regression/m-p/417978#M102673
<P>Dear all,</P><P> </P><P>I am running a multivariate logistic regression model assessing for occurrence of dependant event X (0-didn't occur 1-occurred) with about 200,00 weighted observations using survey data. </P><P> </P><P>I have multiple independant variables, (both continuous and a few categorical). </P><P>Many of the independant variables are missing in about 5% of the data observations (the same 5% of observations are missing data). </P><P> </P><P>Will this make my conclusion inaccurate? I am not sure of how this will effect the overall model, and how it will effect the variables that do not have missing information. </P><P> </P><P>Please clarify if I can run the analysis, or will it cause a major issue. I would prefer to include those 5% of observations if possible, because they have information for some variables.</P><P> </P><P>Thank You</P>Sun, 03 Dec 2017 00:52:28 GMThttps://communities.sas.com/t5/SAS-Programming/Missing-observations-in-Multivariate-Regression/m-p/417978#M102673sasnewbie122017-12-03T00:52:28ZWhen are there too many observations?
https://communities.sas.com/t5/Statistical-Procedures/When-are-there-too-many-observations/m-p/414604#M21759
<P>Dear community,</P><P> </P><P>I am running a study over five years with survey data, and the weighted number of patients included is about 30 million in total. </P><P>I will assess for a relationship between two variables. When does the number of observations become so large that everything starts to show significance (as I have heard)? I am subsetting the observations by a classification variable which includes about 20 subsets, and so the numbers will be smaller ultimately, but I would still like to know how I should interpret results with larger data in the millions, or does this issue happen when we go into the billions?</P><P> </P><P>Thanks</P>Sat, 18 Nov 2017 14:07:41 GMThttps://communities.sas.com/t5/Statistical-Procedures/When-are-there-too-many-observations/m-p/414604#M21759sasnewbie122017-11-18T14:07:41ZRe: multiple models in one proc surveyreg statement or surveylogistic
https://communities.sas.com/t5/Statistical-Procedures/multiple-models-in-one-proc-surveyreg-statement-or/m-p/413203#M21650
<P>proc surveyreg data=mydata;</P><P>stratum str;</P><P>cluster clstr;</P><P>domain set;</P><P>weight wt;</P><P>model age=index;</P><P>model height = index;</P><P>model color = index;</P><P>run;</P><P> </P><P>I ran the above statement. The log states: Multiple model statements. only the first model statement will be used. </P><P> </P><P> </P>Tue, 14 Nov 2017 05:10:34 GMThttps://communities.sas.com/t5/Statistical-Procedures/multiple-models-in-one-proc-surveyreg-statement-or/m-p/413203#M21650sasnewbie122017-11-14T05:10:34Zmultiple models in one proc surveyreg statement or surveylogistic
https://communities.sas.com/t5/Statistical-Procedures/multiple-models-in-one-proc-surveyreg-statement-or/m-p/413147#M21642
<P>Hi</P><P> </P><P>When running proc survey means or proc survey freq, we can check multiple variable means/frequencies/chi squares by listing them out in the vars or tables statement. </P><P> </P><P>Proc Surveyfreq data=sample;</P><P>cluster clstr<SPAN>;</SPAN> </P><P>stratum str<SPAN>;</SPAN></P><P><SPAN>weight wt;</SPAN></P><P>tables subset*color* (shape size weight number location)/ chisq;</P><P><SPAN>run;</SPAN></P><P><SPAN> </SPAN></P><P><SPAN>Is there anything similar I can do with a proc surveryreg or proc surveylogistic to run multiple univariate regression or logistic models by way of the same proc without having to write the proc again ?</SPAN></P><P> </P><P><SPAN>Thank you </SPAN></P><P> </P><P> </P>Tue, 14 Nov 2017 01:33:59 GMThttps://communities.sas.com/t5/Statistical-Procedures/multiple-models-in-one-proc-surveyreg-statement-or/m-p/413147#M21642sasnewbie122017-11-14T01:33:59Z