search for: sudaan

Test =) soddsjbmshdwqwu -- Test, yep.

I am trying to age standardize using the svystandardize package in R. I have successfully managed to hit my SUDAAN based targets for estimates by sex, but not the total. The total is only a little different, but I'd like some help knowing why it isn't exact. I've included the SUDAAN code that generates the targets and my R script (and output) that I have so far. I can't supply the data since tha...

Hi, is there a way to analyze subpopulations (e.g. women over 50, those who answered "yes" to a particular question) in a survey using Survey package? Other packages (e.g. Stata, SUDAAN) do this with a subpopulation option to identify the subpopulation for which the analysis shoud be done. I did not see this option in the Survey package. Is there another way to do this? ********************************************************* Prediction is very difficult, especially about the...

...rned a lot from this list. I would like to thank the developers and contributors who devote so much of their time to this project. Does anyone know if any methods have been developed for handling data from complex sample surveys that include sample weights, clusters, strata, and so on? I know that SUDAAN, Stata have some abilities. Does anything exist in R/S? Paul E. Green [[alternative HTML version deleted]]

Can someone direct me to an R function that properly computes standard errors of data obtained from a complex survery design, i.e. perform alnalyses similiar to those that can be performed with SUDAAN, particularly for a non-parametric one-way ANOVA, e.g. signed rank test? Thanks, 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...

...om the NAMCS describes this for Stata as follows (note the variable names in the data are in caps): The pweight (PATWT), strata (CSTRATM), and PSU (CPSUM) are set with the svyset command as follows: svyset pweight PATWT svyset strata CSTRATM svyset psu CPSUM They provide similar instructions for SUDAAN: as SUDAAN 1-stage WR Option The program below provides a with replacement ultimate cluster (1-stage) estimate of standard errors for a cross-tabulation. PROC CROSSTAB DATA=COMB1 DESIGN=WR FILETYPE=SAS; NEST CSTRATM CPSUM/MISSUNIT; In R, the svydesign command is used to set the sampling scheme, bu...

...Dr. Lumley's homepage of the survey package -- http://faculty.washington.edu/tlumley/survey/ucla-examples.pdf -- doesn't contain confidence interval output. http://faculty.washington.edu/tlumley/survey/YRBS-report-extension.pdf -- confirms that the confidence interval differences between SUDAAN and R in Table 3 exist, but doesn't provide much detail about why. I tried running the analysis example below in SUDAAN as well, which calculated confidence intervals not matching either R or Stata -- I'm confused why all three would be different. I understand (as the report above quotes)...

...y of the following: the stdize and stdweight parameters from a Stata complex survey analysis command (like this) svyset [w= WEIGHTVAR], psu(PSUVAR) strata(STRATAVAR) vce(linearized) svy: mean VARNAME, stdize(agecat) stdweight(agewt) the stdvar and stdwgt parameters from a SUDAAN proc descript call the ESTIMATE statement in a PROC SURVEYREG (used to generate adjusted means) in SAS version 9.2 I am attempting to match figure 1 from nchs data brief #92 exactly using R. The data are here: http://www.cdc.gov/nchs/data/databriefs/db92_fig1.png and the full brief is here...

...state obt_mrj_p obt_mrj_se ob_mrj_cat 45 Utah 42 1.49 <NA> # I expected this to be (42,48.7] instead of <NA>. ### The Reproducible Example (data and code) is shown below: #read estimates of risk factors for substances use (ages 12-17) by State obtained from SUDAAN output p1_st_data <-read.table (text=" Alabama, 49.60, 1.37 Alaska, 55.00, 1.41 Arizona, 52.50, 1.56 Arkansas, 50.50, 1.22 California, 51.10, 0.65 Colorado, 55.10, 1.26 Connecticut, 56.30, 1.28 Delaware, 53.60,...

...Does anyone know what the problem here might be? Has anyone else used the survey package on public-use survey datasets like BRFSS or NHIS? Was there anything special you had to do to those datasets before specifying the survey design? I know that's a pretty vague question. If any of you are SUDAAN users, I basically mean does it have to be structured differently that what you pass into a SUDAAN procedure. Thanks in advance for any suggestions! I am using R 1.6.2 on Windows 2000. -Trevor

Version 2.9 of survey is on CRAN. In addition to various minor improvements and bug fixes there are two major changes - full multistage finite-population sampling is supported (as in SUDAAN) - the same analysis commands can be used for all design types (eg svymean instead of svrepmean for replicate weight designs) -thomas Thomas Lumley Assoc. Professor, Biostatistics tlumley at u.washington.edu University of Washington, Seattle _______________________________________________...

Version 2.9 of survey is on CRAN. In addition to various minor improvements and bug fixes there are two major changes - full multistage finite-population sampling is supported (as in SUDAAN) - the same analysis commands can be used for all design types (eg svymean instead of svrepmean for replicate weight designs) -thomas Thomas Lumley Assoc. Professor, Biostatistics tlumley at u.washington.edu University of Washington, Seattle _______________________________________________...

Hi, Where can I find information ( freely available on the Internet , and also books or other sources ) on how having sampling weights changes the calculation of the standard error (of means and proportions)? How good is R for this type of procedure? And SAS? thanks Robert [[alternative HTML version deleted]]

Hello, Is there a way to get complex sample variances in the survey package on summary statistics other than means? If not, can they be added to a future version? It would be be great to have them on totals, quantiles, ratios, and tables (eg row percent, columns percent, etc). Thanks. Fred --------------------------------- [[alternative HTML version deleted]]