Communications Week 11

    On Monday, we will discuss proposals and presentations and work on cross-tabulation and recoding variables.  Wednesday will be a lab session to work on papers.  Anyone who submits the crosstabulation assignment before class on Wednesday can be exempt from attending.


Closes 4 a.m. Tuesday, April 8.  Quiz Ten will cover both "The Left's New Machine" and "Experimental Macrosociology:  Predicting the Next Best Seller."  There will be some items from the other readings on this study, especially the points covered in the powerpoint.  Closes at a 4 p.m. on Monday, April 7.  Two tries, but the answers will not be released until after the test closes.
Due Tuesday, April 8 Writing Assignment.  A five paragraph review of the five references included in your Research Proposal (or new references if you find others that are more useful).  You should mention the data and methods used by the authors as well as their arguments.  References to the authors should be embedded in the text following APA format, e.g.,  "Jones (2005) used data from the General Social Survey to...".   Due Tuesday, April 8 (actually 5 a.m. Wednesday morning).  Ten percent penalty for each day late.
Due Thursday, April 10.  Prepare a finished multiple bivariate cross-tabulation tables using  the GSS data set.  It should have one column variable and five or six row variables, one of which should be year if your variable was asked in more than one year.  These tables should be typed in Word with a descriptive paragraph that quotes some of the data.  This material will go in your final paper.  Some instructions (from last year's methods class) are available below.  We will work on this assignment in the lab on Wednesday, April 9.  If you have completed and submitted the assignment before class, you may be excused from attending or you may work on the next assignment.  Ten percent penalty for each day late.  Submit to the Assignment Dropbox for "Multiple Bivariate Crosstabulation Assignment"

Public Speaking Skills.  These are summarized on the Guidelines for Oral Presentations form which will be used in grading your presentations next week.  We will view some videos by TJ Walker of Media Training Worldwide.  These are available on the Google Video site.   To see them, just go to Google Video and type "Media Training Worldwide" in the Search box.   Two that may be particularly useful to us are learn the art of public speaking, don't overdo your powerpoint presentations"  and "the rule of three".  
Powerpoint Logic- Gettysburg Address in Powerpoint

Instructions for the cross-tabulation assignment:

For this assignment, use the General Social Survey 1972-2006 data file.  This very large data set is described in an article from NY Times.  To access the data we can use the Survey Data and Analysis program at the University of California, Berkeley.  Just click on SDA.  to go to the SDA Frequencies/Crosstabulation program.  You can also use Microcase for this in the computer labs.  Click on "New Stuff" on the desktop and you will find a link to Microcase professional edition.  it includes the 1972-2006 data file.

Your first task is to crosstabulate your research variable with YEAR.  If your variable was not asked in at least three years, choose a related variable.  If your variable has more than three categories, you should recode it first to combine categories.

Your second task is to produce a multiple bivariate table with one column variable and at least five row variables. (NOTE:  you will get a little.  The percentages should be row percentages.  You should write a paragraph summarizing the results in which you correctly describe some of the percentages.  The finished product should look like this Sample Assignment.except that you should not use YEAR as a row variable since that will be in your first table.   You should prepare the table in a word processor, save it in doc format, and submit it to SAKAI

If you completed a proposal, you already know what your research variable is.  Your independent variables should be ones that would be expected to have some relationship to your research variable. 

If you use Microcase, you may find that your variables have been conveniently recoded.  If you use the SDA, you may have to recode them yourself first.  To do this, click on "create variables" and "recoding rules".  It shows how to recode AGE for this purpose.   You need to check each of your row variables to see if it needs recoding.   This gives you the flexibility to recode them as YOU wish rather than relying on someone else's choices.

Then you need to do a cross tabulation for EACH of your row variables.  You will need five cross-tabulations.  You may wish to print these out for your convenience or you can work on the screen.  You take the results for all the variables and type them into one big table for your assignment.

You should also include a TOTAL row at the bottom of each table.  You can get these numbers from the bottom of your cross-tabulation table.    These may vary slightly from table to table, however, because of missing data.  Another way to get them, for the whole sample, is to type the name of the column variable in your table in the ROW box on SDA with nothing in the column box.  This will get you the frequencies.  In Microcase, you can use the Univariate command.