Social Capital

Document Sample
Social Capital Powered By Docstoc
					 Social Capital [II]
Exercise for the Research Master
     Multivariate Statistics

     W. M. van der Veld
   University of Amsterdam
      Goal of the ‘groups work’
• Formulate a research question
• Develop a (testable) theory
• Develop measurement instruments
  – part I - Two types of concepts
  – Part II - Two types of constructs
• Data for the test - European Social Survey
• Analyze the data
• Presentation of research results
               Quantitative Methods in The Social Sciences   2
           Two types of concepts
• Social Trust
   – It is the core of social capital, measures the degree to
     which you trust other people.
• There are many questions that might capture the
  concept of social trust. A distinction should be made
  for concepts
   – by intuition, or
   – by postulation.



                  Quantitative Methods in The Social Sciences   3
           Two types of concepts
• Concepts by intuition are ‘simple’ concepts:
   – The concept is immediately clear from the wording of the
     survey question(s).
• Concepts by postulation are ‘complex’ concepts:
   – The concept not necessarily clear from the wording of the
     survey questions.
   – Concepts by postulation are also called constructs.
• An illustration



                 Quantitative Methods in The Social Sciences     4
           Two types of concepts
• Generally speaking, would you say that most people
  can be trusted, or that you can’t be too careful in
  dealing with people?
• Would this be ‘by intuition’ or ‘by postulation’?
   – By intuition;
   – However there is catch!




                 Quantitative Methods in The Social Sciences   5
             Two types of concepts
• Some people say that social trust is an attitude, and
  attitudinal measures should contain several components:
   – An affective component,
   – A cognitive component, and
   – A behavioral component.
• Therefore social trust could also be measured with:
   – Generally speaking, would you say that most people can be trusted, or
     that you can’t be too careful in dealing with people?
       • [affective, trust & behavioral, be careful]
   – Do you think that most people would try to take advantage of you if
     they got the chance, or would they try to be fair?
       • [cognitive, take advantage & cognitive, be fair]
   – Would you say that most of the time people try to be helpful or that
     they are mostly looking out for themselves?
       • [cognitive, be helpful & cognitive, looking out]

                      Quantitative Methods in The Social Sciences           6
          Two types of concepts
• So, we have two possible measurement instruments
  for social trust:
• Simple(?)
  – Most people can be trusted, or you can't be too careful.
• Complex (Construct)
  – Most people can be trusted, or you can't be too careful.
  – Most people try to take advantage of you, or try to be fair.
  – Most of the time people are helpful, or mostly looking out
    for themselves.


                 Quantitative Methods in The Social Sciences       7
Two types of constructs
          Two types of constructs
• I make a distinction between two types of constructs:
   – By definition, and
   – By derivation.
• Note that this is different from the distinction
  between concepts by definition and by postulation.
  Here we are discussing variables that are
  categorized: concepts by postulation (or constructs).




                 Quantitative Methods in The Social Sciences   9
          Two types of constructs
• Construct by definition. For example:
   – A family’s “living space” is the sum of
   – the surface area of all rooms in a house.
   – The surface areas are expressed in the same quantity (m2),
     therefore we can just add and the result is also in that
     quantity.
• These constructs don’t need any further statistical
  analysis, to show that they form one construct/are
  uni-dimensional.


                 Quantitative Methods in The Social Sciences   10
          Two types of constructs
• Construct by derivation. For example:
   – Political efficacy (int) is the sum of
      • How difficult or easy do you find it to make your mind up about
        political issues?
      • How often does politics seem so complicated that you can’t really
        understand what is going on?
      • Do you think that you could take an active role in a group
        involved with political issues?
   – Note that the quantities are all different,
   – so in what quantity is the sum expressed?
• Normally a statistical analysis is used to ‘show’ that
  the questions measure one construct/are uni-
  dimensional.
                   Quantitative Methods in The Social Sciences          11
          Two types of constructs
• There is also a difference between these two types of constructs
  from a modeling point of view.

                                                                    Internal
                                                                    Political
           Room   Kitchen   Bedroom                                 Efficacy
           (m2)    (m2)       (m2)




                                                         Politics   Political    Able to
                                                           too       issues     participate
                                                        complex     complex         In
                  Living                                                         politics
                  space




                  Quantitative Methods in The Social Sciences                                 12
   Data for the test
European Social Survey
      The European Social Survey
• Normally you would
   – develop measurement instruments;
   – draw a sample; and
   – start collecting the data.
• More than normally, you would
   – not have any money to engage in such a project.
• Thus we use second hand data.
• It requires some knowledge of the studies available
  make a fruitful choice for a data set.


                 Quantitative Methods in The Social Sciences   14
     The European Social Survey
• Here we use data from the European Social Survey.
• The European Social Survey (the ESS) is an
  academically-driven social survey designed to chart
  and explain the interaction between Europe's
  changing institutions and the attitudes, beliefs and
  behavior patterns of its diverse populations. Now in
  its third round, the survey covers over 20 nations
  and employs the most rigorous methodologies. It is
  funded via the European Commission's 5th and 6th
  Framework Programmes, the European Science
  Foundation and national funding bodies in each
  country.
• http://www.europeansocialsurvey.org/
               Quantitative Methods in The Social Sciences   15
         The European Social Survey
•   We will work with the round 1 data from 2002. This round contains
    measures of:
      A1-A10      Media; social trust
      B1 – B50    Politics, including: political interest, efficacy, trust, electoral and other forms of
                  participation, party allegiance, socio-political evaluations/orientations, multi-
                  level governance
      C1 – C28    Subjective well-being and social exclusion; religion; perceived discrimination;
                  national and ethnic identity
      D1 – D58    Immigration and asylum issues, including: attitudes, perceptions, policy
                  preferences and knowledge
      E1 – E43    Citizen involvement: including organizational membership, family and friendship
                  bonds, citizenship values, working environment
      F1 – F65    Socio-demographic profile, including: Household composition, sex, age, type of
                  area, Education & occupation details of respondent, partner, parents, union
                  membership, household income, marital status
      Section G   Human values scale

                          Quantitative Methods in The Social Sciences                              16
       The European Social Survey
• The source questionnaires can be found on my
  website.
• The drop-off questionnaire contains measures of
  some psychological traits.
• The following data files are available:
   –   All (renamed)   = ‘ESS-Round1-V51 [Renamed].sav’
   –   Finland         = ‘ESS-Finland.sav’
   –   Great-Britain   = ‘ESS-GB.sav’
   –   Netherlands     = ‘ESS-Netherlands.sav’
   –   Poland          = ‘ESS-Poland.sav’
                  Quantitative Methods in The Social Sciences   17
        The European Social Survey
• Because the link of the variable names and survey questions is
  unclear, I made a Link between survey questions and Variables
  (Adobe Acrobat)
• When you are searching for some variable; search the file using
  a keyword.
 Question Varname Description
   C4      sclact     Take part in social activities compared to others of same
                      age
   C5      crmvct     Respondent or household member victim of
                      burglary/assault last 5 years
   C6      aesfdrk    Feeling of safety of walking alone in local area after
                      dark
   C7      health     Subjective general health
                     Quantitative Methods in The Social Sciences               18
                    Assignment
• You should have listed the questions that measure
  the variables/constructs in your study.
• Now mark which variables are constructs.
• Explore the data with PCA.
• And for constructs by definition you can use PCA to
  compute component scores of the constructs.




               Quantitative Methods in The Social Sciences   19
                                  Notes
• Keep in mind that it is not possible to be perfect, i.e.
   – You might change your model during the course.
   – You might add or delete variables during the course.
• Next week I will present an example of how to
  analyze data with LISREL.




                    Quantitative Methods in The Social Sciences   20

				
DOCUMENT INFO
Shared By:
Categories:
Tags:
Stats:
views:2
posted:3/28/2013
language:English
pages:20