Week One  - Introduction to Social Science Research  -

Chat Room Discussions:  Sunday at 8 and Tuesday at 9:15.
Quizzes and Exercises:
  1. Quiz One will close at 10 a.m. on Monday, September 15.  It will cover Chapter One in Babbie and material covered in Ayers and in class on September 6.  It will be multiple choice format.  You may take it three times and the software will tell you which items you got wrong (but not the right answer).   The quiz will close at 10:00 a.m. on Monday, September 15, and if you do not take it by then you will get a zero.  This test includes calculating some percents and expected frequencies, so have a calculator available when you take it.  Calculating percents and expected frequencies is explained at the bottom of this page.  There are 20 items and you will have one hour (stopping the quiz in SAKAI does not extend the hour).  Once you have taken the quiz you can open it in SAKAI and review your answers.
  2. AyersExerciseOneandTwo will close at 2 p.m. on Wednesday, September 17, 2008.  In Sakai, this is under Quizzes, but it is actually a digital answer sheet for the Workbook Exercise.  It includes items from Exercises One and Two in Ayers.  They are mostly fill in the blank items, so you have to be sure to get the items in the correct form as instructed.  You may take this as many times as you like before it closes at 2 p.m. on Wednesday, September 17 and the software will tell you which items you get wrong.  Ayers Exercise 1 (pages 17 to 28) and Exercise 2a(pages 43 to 50) and Exercise 2b (pages 51 to 58) are available online, for use in class, as well as in case some students need a little more time to get the book.

Required Reading: 
  1. Earl Babbie, The Basics of Social Research (third or fourth edition):  Chapter One.
  2. David Ayers, Experiencing Social Research, Pages 1-15 and 29-31 (except the last two paragraphs) and 33 (after the first two paragraphs)-42.  [We are skipping the material on "paradigms" both here and in Babbie, because the paradigms in criminal justice are different.]  It is a good idea to open the software as you read these introductions and follow along with the illustrations.  We will go over some of this in class on September 6.
Other materials:
  1. There is a powerpoint covering Chapter One in Babbie in Sakai/Resources/Week One.  You can open either the regular version or a narrated version which includes an audio explanation of the slides.  The narrated version is a much larger file.  This covers the same material as in Chapter One of the book, but you may find this format helpful.  You can also view this presentation on the internet without using powerpoint by clicking on Internet Presentation.  This does not include the narration.
  2. There is a file of sample test questions in Sakai/Resources/Week One. 
  3. The Companion Site to the Babbie book has flash cards, a glossary and sample tests.
  4. A video of the class on Sept 6 is available (however, it started half an hour late). 
  5. A podcast is also available. 
Students who have taken this course before say that the statistical material is the hardest to do online.  We will work through statistical problems in class on September 6, October 4 and November 1.  Today we will begin with percentages.  Percentages are used with categorical data, such as data from survey questions.  Here are some categorical data.  There are two variables:  gender and liking for spinach.  Each variable has only two values or attributes.   This is for simplicity, in a real study we might want more categories for Liking for Spinach such as:  hate it,  like it a little, like it ok,  like it pretty well,  love it.  Or we might ask respondents to rate it on a scale from 1 to 10.

              Variable                    Attributes or values
              Gender                      male, female
              Liking for Spiniach     like, don't like

45 men like spinach
85 women like spinach
65 men do not like spinach
80 women do not like spinach

Our first step is to put these data in a crosstabulation or contingency table.  Usually we put the Independent Variable in the Column and the Dependent Variable in the Row.  Gender is the independent variable because it might determine one's liking for spinach, but liking for spinach cannot change one's gender.  Thus gender is a possible cause, liking for spinach a possible effect.  Since we don't want to assume a causal relationship, we call them independent and dependent variables.

                        Men     women

Like                   45        85            130

Don't                  65       80             145

                         110      165            275

With this table, we can answer questions.  Some are percent questions, some are frequencies questions.  We will do these in class and I will be adding the answers to this WEB page.

How many respondents like spinach?  the base of the % is the word after how many, in this "respondents".  The numerator is the number in the next clause, those who like spinach.   130/275  =.4727  This is the proportion, or the probability that any one respondent will like spinach.  Percent meeans per 100.  We multiply by 100.  Then we allow one number after the decimal, rounding off, and add the % sign to show we know it is a %.    47.3%.     47.3% of the respondents like spinach.  145/275

How many men like spinach?   45 

What percent of the men like spinach?  The base of the calculation is the number of men.  The numerator is the number of men who like spinach.    45/110   40.9% of the men like spinach.  This is the "column percent" for the cell


What percent of those who like spinach are women?  The base is the number who like spinach.  The numerator is the number of women who like spinach.   85/130  =/6538 = 65.4%  This is the "row percent" for the cell

What percent of the respondents are men who don't like spinach?   The denominator is 275.  The numerator is men who like spinach, 65.  65/275   =  23.6%   This is the "total percent" for the cell

What percent of the respondents are men?  110/275  =  40.0%

What percent of the respondents are women?  165/275 = 60.0%

                       Men    Women

Like               40.9%    51.5%

Don't             59.1%    48.5%

Total           100%      100%
N =            (110)        (165)
Finally, we can make a finished percentage table with the independent variable as the base of the percents.
                        
We also covered "expected" frequencies in class.  These are what we would "expect" under the "null hypothesis" that there is no relationship between the variables.  The concept of the "null hypothesis" is explained on page 34 of the Ayers book.  To computer an expected frequency, you need the row, column and total percents.  For each cell, multiple the row total for the cell in which it appears by the column total for the column in which it appears, then divide by the grand total.

For example, for the table below the expected frequency for the Men Who Like Spinach cell would be (110 * 130) /275 which equals 52


Observed                     Men     women        Expected          Men          Women         Column Percent  Men    Women

Like                   25        85            110                                38.8            71.2                                    27.8%  51.5%

Don't                  65       80             145                                51.2            93.8                                    72.2%  48.5%

                          90      165            255                                90               165                                     100%   100%