Document Sample
Sociology Powered By Docstoc
					General Social Survey
           Kiran Doranalli
               Lucy Li

Data & GIS Library Services, U of S Library
         September 11, 2008
General Social Survey (GSS) - Overview

     Primary objectives/Aims:
      Collect data on social trends in order to
       monitor changes in living environment
       and welfare of Canadians over time.
      Provide instant information on specific
       social policy issues of existing and
       emerging interests.
Target population for GSS:
Population living in private households in the 10
Survey collects data over 1 year
Sample size till 1998 - ~ 10,000 persons
Sample size from 1999 to 2006 - ~ 25,000 persons

            CANSIM via Statistics Canada
Method of data collection:

    Computer assisted telephone interviewing
    Response rate over years for GSS is approx.
    Cycles of GSS available till date:
Cycle no. Year   GSS cycle topic Focus issue
1         1985   Health               Social support
2         1986   Time use, social     Language
3         1988   Victimization        Victim services
4         1989   Education, work      No focus issue
                 and retirement
5         1990   Family and friends   No focus issue
6         1991   Health               Various health topics
7         1992   Time use             Culture, sport and unpaid work activities
Cycle no. Year GSS cycle topic Focus issue
8         1993   Victimization        Alcohol and drug abuse
9         1994   Education, work      Transition into retirement
                 and retirement
10        1995   Family               Effect of tobacco smoke
11        1996   Social support       Tobacco use
12        1998   Time use             Sports participation/ culture
13        1999   Victimization        Spouse, senior abuse/ perceptions
14        2000   Technology –         No focus issue
                 Computer and
15        2001   Family               No focus issue
16        2002   Social support and   Retirement planning and experience
17        2003   Social               No focus issue
18        2004   Victimization        No focus issue
19        2005   Time use             Social networks/ trust/ transportation
20        2006   Family               Family transition
 GSS cycle 1 (Health & Social support): 1985

Cycles in 1991 (6), 1996 (11), 2002 (16).
Target population
        – 15 years of age and older in Canada
        – 15-64 years of age (telephone interview), 65 and older (personal
        – Exclude Yukon, Northwest territories and Nunavut and full-time
          residents of institutions.

Reference period – Sept to Oct 1985
GSS cycle 1 (Health & Social support): 1985

Brief of variables measured
   Short and long term disability      Use and help of health care
   Height and weight
   Well-being
   Health problems
   Smoking
   Alcohol use
   Physical activity
   Sleep
GSS cycle 1 (Health & Social support): 1985 - Survey      Design
Employed 3 different sampling techniques

A. Persons aged 15 to 64
      a. Elimination of non-working Banks method
          (NewFoundland and Ontario) – Details in section 4.2 of Code book
      b. Waksberg method (Remaining provinces) – Details in section
            4.1 of Code book
B. Persons aged 65 and older
      a. Survey based on Canadian Labour Force Survey Frame
          and sampling procedures – Details in section 4.3 of code book.
 GSS cycle 9 (Education, work & Ret.): 1994

Cycles in 1989 (4).
Target population
        – 15 years of age and older in Canada
        – Exclude Yukon, Northwest territories and Nunavut and full-time
          residents of institutions.

Reference period – Jan to Dec 1994
GSS cycle 9 (Education, work & Ret.): 1994

Brief of variables measured
   Work and education in the service economy
   New technologies and human resources
   Emerging trends in education and work
GSS cycle 9 (Education, work & Ret.): 1994   – Survey Design

   Data collected from Jan to Dec 1994 were evenly distributed
    over 12 months to counterbalance the seasonal variation in the
    information gathered
   Sample selected using Elimination of Non-Working Banks
    technique of Random Digit Dialing (RDD).
   Supplementary sample was added to RDD from Labour Force
   For method description please refer section 4.2 in code book.
GSS cycle 18 (Victimization): 2004

Previous cycles in 1988 (3), 1993 (8), 1999 (13).
Target population
        – 15 years of age and older in Canada
        – Exclude Yukon, Northwest territories and Nunavut and full-time
          residents of institutions.

Reference period – Jan 2004 to Dec 2004
GSS cycle 18 (Victimization): 2004
Brief of variables measured
   Age, sex and marital status                Stalking of respondent
   Perceptions, history and risk              Crime incident report
   Criminal victimization screening           Other crime events
   Abuse by current spouse/partner            Main activity of respondent
   Abuse by ex-spouse/partner                 Education of respondent,
                                                spouse/partner, parents
   Spousal abuse report
                                               Activities of spouse/partner
   Ex-spousal abuse report
                                               Ex-spousal abuse report
   Housing characteristics of respondent
Method references
Waksberg, J. 'Sampling methods for Random Digit Dialling,'
Journal of the American Statistical Association, 73, (1978):40-46.

RDD; A bank of telephone numbers is a set of 100 numbers with the
same first eight digits (i.e. the same Area Code-Prefix-Bank ID).
Thus 613-951-9180 and 613-951-9192 are in the same bank, but
613-951-9280 is in a different bank.
U of S Data Archive
     Data Lib webpage
     By subject
     Select the file
     U of S data archive
     Download the file and unzip it
     Codebooks and other documentations are available in
      TXT or PDF format (some are available in print
      copy—search the library catalogue)
     Restrictions: DLI license
 What is a codebook?
  – ―A codebook describes and documents the questions asked or items
    collected in a survey. Codebooks and study documentation will provide you
    with crucial details to help you decide whether or not a particular data
    collection will be useful in your research. The codebook will describe the
    subject of the survey or data collection, the sample and how it was
    constructed, and how the data were coded, entered, and processed. The
    questionnaire or survey instrument will be included along with a description
    or layout of how the data file is organized. Some codebooks are available
    electronically, and you can read them on your computer screen, download
    them to your machine, or print them out. Others are not electronic and must
    be used in a library or archive, or, depending on copyright, photocopied if
    you want your own for personal use.‖
                     --ISSR Social Science Data Archive, UCLA
General Content of GSS Codebooks:
Description of the study or cycle – who, why and how it was
Sampling information – population studied, how was sample
 drawn and number of response rate.
Technicality about files – number of observations or variable,
 length of record, number of records per observations.
Structure of the data within file – eg., hierarchial, multiple
 cards etc…
Details about the data
Questionnaire and responses
Example (Data Dictionary):
        The fourth
     the 4th column in                                           Question Text -Exact text of a
        spreadsheet                                              question as delivered to a

                               The variable starts from
                               column 19 ends in
                               column 20 in datafile

Data dictionary is found from Pages C1 to C 200. This example is on Page C2.
Example cont.
 Here is what the same information might look like in a data file:
                             The first line is not a part of data, we put it here to
                             identify the position of the variable more easily.

                            If a variable A is noted as ―Field: 2 Position: 5-8‖,
                            then variable A’s value starts from column 5, ends in
                            column 8.
                            And this variable A is the second variable. You will find it
                            in column B in spreadsheet.
 This is how the data looks like after you put them
  into SPSS.
   3. Ask Data Library Staff
                  Office: 2nd Floor, Main Library
                  Appointments recommended
                  Email us at

                                                                Kiran Doranalli   Lucy Li
                                                                (8841)            (8841)

Darlene Fichter    Winnie Smit   Rob Alary   Elise Pietroniro
(7209)             (7261)        (5987)      (2677)
(on sabbatical)