The sample SAS and Stata code provided here is intended for use with certain datasets in the National Neighborhood Data Archive (NaNDA). NaNDA (https://www.openicpsr.org/openicpsr/nanda) contains some datasets that measure neighborhood context at the ZIP Code Tabulation Area (ZCTA) level. They are intended for use with survey or other individual-level data containing ZIP codes. Because ZIP codes do not exactly match ZIP code tabulation areas, a crosswalk is required to use ZIP-code-level geocoded datasets with ZCTA-level datasets from NaNDA. A ZIP-code-to-ZCTA crosswalk was previously available on the UDS Mapper website, which is no longer active. An archived copy of the ZIP-code-to-ZCTA crosswalk file has been included here. Sample SAS and Stata code are provided for merging the UDS mapper crosswalk with NaNDA datasets.

The PCCF+ is a SAS control program with associated datasets derived from the PCCF. It is a Postal Code population weight file with Geographic Attribute files, Health Region boundary files, and other supplementary data.

This collection of computer programs and test data files was compiled by the Census Bureau for use with GEOGRAPHIC BASE FILE/DUAL INDEPENDENT MAP ENCODING (GBF/DIME), 1980 (ICPSR 8378). This collection consists of files grouped into five categories: Special Program Information Tape (SPIT) Datasets, UNIMATCH System Datasets, ADMATCH System Datasets, EASYMAP System Datasets, and EASYCORD System Datasets. Some of the capabilities of the programs in this collection include: mapping files for which complicated data manipulation is required, generating individualized lists of candidates for carpools, linking of records on the basis of street address, creating shaded area maps for statistical display, and producing a map coordinate system.

This hands-on workshop has two parts. The first part covers working with SAS and the Postal Code Conversion File Plus. You'll start with Postal Codes, and leave with Census geography that can be linked to Census demographics. The second part introduces OpenRefine, an open source software platform for cleaning up messy data files. Initially developed by Google, OpenRefine will open your eyes to the beauty of clean data! No previous experience required.

File List ACS.zip -- .zip file containing SAS macro and example code, and example Aletris bracteata data sets. acs.sas chekika_ACS_estimation.sas chekika_1.csv chekika_2.csv philippi.3.1.zip

Description "acs.sas" is a SAS macro for computing Horvitz-Thompson and Hansen-Horwitz estimates of population size for adaptive cluster sampling with random initial sampling. This version uses ugly base SAS code and does not require SQL or SAS products other than Base SAS, and should work with versions 8.2 onward (tested with versions 9.0 and 9.1). "chekika_ACS_estimation.sas" is example SAS code calling the acs macro to analyze the Chekika Aletris bracteata example data sets. "chekika_1.csv" is an example data set in ASCII comma-delimited format from adaptive cluster sampling of A. bracteata at Chekika, Everglades National Park, with 1-m2 quadrats. "chekika_2.csv" is an example data set in ASCII comma-delimited format from adaptive cluster sampling of A. bracteata at Chekika, Everglades National Park, with 4-m2 quadrats. "philippi.3.1.zip" metadata file generated by morpho, including both xml and css.

File List All files at once

ConnDiefenbach_SAS.zip

Individual SAS files

ConnDiefenbach_ModelSelection.SAS
 ConnDiefenbach_AgeError_1year.SAS

Description The file ConnDiefenbach_ModelSelection.SAS includes requisite code to compute log likelihoods for different aging error models evaluated at their MLEs (maximum likelihood estimates). These are useful for calculating model selection criterion. The file ConnDiefenbach_AgeError_1year.SAS includes code for estimating the standing age distribution of female black bear harvests in

Pennsylvania. Because of the potential for algorithm
instability when these distributions are estimated simultaneously across all
years, this code permits estimation of age distributions 1 year at a time (which
year must be specified by the user).