I am new to SAS, and I would like how easy/difficult it would be to try to do an iterative multiple imputation in SAS. In R, this is relatively easy.
The algorithm is as follows:
impute missing data using known distribution
fit model to complete data in 1
use model fit in 2 to impute missing data
repeat model fitting and imputation steps 50 times (e.g. 50 data sets total)
take every 10th dataset and pool the results
Based on my limited experience in SAS, I'm guessing I would have to write a MACRO. I am specifically interested in using proc nlmixed to fit my model. I am not using R because SAS's nlmixed is more flexible and gives more robust results.
proc mi NIMPUTE=n
proc sort; by _Imputation_
proc NLMIXED; by _Imputation_
proc mianalyze;
Related
I am analyzing a temporal trend(yr) of certain chemicals(a b & c).
I use proc sgplot and series statement to draw a plot and found there was a decreasing trend.
Becuase the data is right-skewed, I used the median concentration of each year to draw the plot.
Now I would like to conduct a statistical test on the trend. My data came from the NHANES and need to use the proc survey** to perform analysis. I know I can do an ANOVA test based on proc surveyreg and use ANOVA option in the MODELstatement.
proc suveyreg data=a;
stratum stra;
cluster clus;
weight wt;
model a=yr/anova;
run;
But since the original data is right-skewed, I think maybe it is better to use Kruskal-Wallis test on the original data. But I don't know how to write a code in SAS and I didn't find information in proc survey**-related document.
My plan B is to use the log-transformed data and ANOVA test. But I am not sure if that is an appropriate approach. Can somebody tell me how to get the normality test of the residual in ANOVA while using proc surveyreg? I would also like to know if I can test a b & c in one procedure or I should write multiple procedures with changes in MODEL statement.
Looking forward to your engagement.Thank you!
I am using SAS for producing ROC curves. But the "PROC LOGISTIC" does not give me the confidence-interval for sensitivity and specificity.
Does any one know if there is an option in order to produce the lower and upper band for sensitivity and specificity ?
If it is not the case, does anyone know another method ?
Thk an lot,
when I use basic stats, I use proc freq for associations.
proc freq data=tempds noprint;
tables variable1*std_variable2 / chisq measures;
output out=outds pchi n OR FISHER;
run;
The output dataset "outds" now contains RROR(OR), L_RROR(Lower CI), U_RROR(Upper CI). Is this what you are looking for?
If proc logistic doesn't directly support this, you could try bootstrapping - produce many ROC plots for random samples of your data (e.g. using proc surveyselect) and then calculate the p5 and p95 points for each x and y value in the plot using proc summary. This should give a good approximation provided that you use a large enough number of samples.
I am estimating a model for firm bankruptcy that involves 11 factors. I have data from 1900 to 2000 and my goal is to estimate my model using proc logistic for the period 1900-1950 and then test its performance on the 1951 through 2000 data. Proc logistic runs fine but the problem I have is that the estimated coefficients have the same name as my factors that I was using in my model. Suppose the dataset that contains all my observations is called myData and the dataset that contains the estimated coefficients which I obtain using an outtest statement (in proc logistic) is called factorEstimates. Now both of these data sets have the variables factor1, factor2, ..., factorN. Now I want to form the dataset outOfSampleResults that does something like the following:
data outOfSampleResults;
set myData factorEstimates;
newVar=factor1*factor1;
run;
Where the first mention of factor1 refers to that contained in myData and the second refers to that contained in factorEstimates. How can I inform sas which dataset it should read for this variable that is common to both of the datasets in the set statement? Alternatively, how could I quickly rename factor1, factor2, ..., factorN as factor1Estimate, factor2Estimate, ..., factorNEstimate in the factorEstimates dataset so as to circumvent this common variable name issue altogether?
Two quick ways to get estimates for a model already developed:
1. Proc logistic score statement
http://support.sas.com/documentation/cdl/en/statug/63033/HTML/default/viewer.htm#statug_logistic_sect066.htm
Include the data in your original proc logistic but use a new variable and ensure that the dependent variable is missing for the observations you want to predict.
data stacked;
set all;
if year >1950 then predicted=.;
else predicted=y;
run;
proc logistic data=stacked;
model predicted = factor1 - factor12;
output out=out_predicted predicted=p;
run;
I'm attempting to conduct a simple one-way random-effects ANOVA in SAS. I want to know if the population variance is significantly different than zero or not.
On UCLA's idre site, they state to use PROC MIXED as follows:
proc mixed data = in.hsb12 covtest noclprint;
class school;
model mathach = / solution;
random intercept / subject = school;
run;
This makes sense to me given my previous experience with using PROC MIXED.
However, in the text Biostatistical Design and Analysis Using R by Murray Logan, he says for a one-way ANOVA, fixed and random effects are not distinguished and conducts (in R) a "standard" one-way ANOVA even though he's testing the variance, not the means. I've found that in SAS, his R procedure is equivalent to using any of the following:
PROC ANOVA
PROC GLM (same as ANOVA, but with GLM in place of ANOVA)
PROC GLM with RANDOM statement
The p-values from the above three models are the same, but differ from the PROC MIXED model used by UCLA. For my data, it's a difference of p=0.2508 and p=0.3138. Although conclusions don't change in this instance, I'm not really comfortable with this difference.
Can anyone give advice on which one is more appropriate and also why there is this difference?
For your model, the difference between PROC ANOVA and PROC MIXED is only due to numerical noise(REML estimator of PROC MIXED). However, the p-values mentioned in your question correspond to the different tests. In order to get the F value using the output of COVTEST in PROC MIXED, you need to recalculate MS_groups taking into account the unequal sample sizes (either manually as explained on p.231 of http://bio.classes.ucsc.edu/bio286/MIcksBookPDFs/QK08.PDF, or just using PROC MIXED with the same fixed model spec as in PROC ANOVA). This paper (http://isites.harvard.edu/fs/docs/icb.topic1140782.files/S98.pdf) provides some examples of used of PROC MIXED in addition to SAS manual.
Background: I have a categorical variable, X, with four levels that I fit as separate dummy variables. Thus, there are three total dummy variables representing x=1, x=2, x=3 (x=0 is baseline).
Problem/issue: I want to be able to calculate the value of a linear combination (i.e. using SAS as a calculator) of these dummy variables. For example, 2*B1 + 2*B2 + B3.
In Stata, this can be done using the lincom command, which uses the stored beta estimates to calculate linear combinations of the parameters.
In SAS in a procedure such as PROC GLM, I think I should use the ESTIMATE statement, but I'm not sure how I would specify the "weights" for each variable in this case.
You are looking for PROC SCORE. This takes output regression or factor estimates and scores a new data set. See here for an example. http://support.sas.com/documentation/cdl/en/statug/66859/HTML/default/viewer.htm#statug_score_examples02.htm
FYI, PROC MODEL does allow this in the model statement, which may be less work than PROC SCORE. I know PROC MODEL can be used readily in place of PROC REG, but I'm not sure how advanced of modeling PROC MODEL does, so it may not be an option for more complex models. I was hoping for something with less coding, but given the nature of SAS, I think this and PROC SCORE are the best I'm going to get.
What if you add your linear combination as a variable in your input dataset?
data myDatasetWithLinCom;
set mydata;
LinComb=2*(x=1)+ 2*(x=2)+(x=3); /*equvilent to 2*B1 + 2*B2 + B3*/
run;
then you can specify LinComb as one of the explanatory variables and you can lookup the coefficient directly from the output.