mcfarland, 21sep2000 UCLA Soc. 210a, Assignment 2: Data and their Computerization 1. Create a \hamilton directory on your Zip disk. Go to the www.thomson.com/duxbury.html web site, or to the web site for this course, and download to your Zip disk the file, "hamilton.exe". Make sure to put it in the \hamilton directory, not the root directory. This is a self-extracting file. Run it, to produce the various datasets used as examples in the Hamilton book, such as the lofoten.dta dataset used on page 3. These datasets are intended to let students actually work through the examples while reading material about them in the Hamilton book. 2. The handout Western States Data is a printed version of a very small dataset, with only 13 cases and fewer than a dozen variables. Start the stata program, type in these data, and save as a stata-format file wstates.dta on your Zip disk. (See Hamilton pp 13-17 regarding creation of new stata-format datasets.) 3. Write out the bibliographic citation of the General Social Survey data, as it should appear in an ASR article. 4. Go to the online GSS codebook at the icpsr site. Look up the variable EDUC. a) Which of the numerical values represent various forms of non-response rather than amounts of education? b) With pen and paper only, write out the stata command(s) that would replace those values with the "." which stata uses as missing data code. c) Do the remaining values form a ratio scale? interval scale? ordinal scale? nominal scale? mere list? Discuss any ambiguities, such as most values forming an interval scale but one value that does not lie on that same dimension. Propose how best to resolve those ambiguities. 5. Go again to the online GSS codebook, and repeat that for each of the following variables: affrmact age attend bilinged chldidel deathpen degree divbest down1 income (What's wrong with this variable? Alternatives?) judge letin maeduc marital mawrkwrm memfrat neargod news owngun partners prestg80 sex sibs tvhours xmarsex