Survey data in economics

1
Survey data in economics
2
Warm-up

• Why would we want to use survey data?

3
The use of survey data in economics(based on
Boulier/Goldfarb, 1998)

• The use of survey data may be attractive, because
• we get a lot of data on a broad range of issues
  comparatively cheap
• we can make statements about an entire population
  (if we have a representative sample)
• it may allow us to test our theories
• some variables of interest to us may not be
  directly observable (particularly important in
  behavioral economics)
• it may give us new ideas about research
  hypothesis (e.g. above average effect)

4
The use of survey data in economics(based on
Boulier/Goldfarb, 1998)

• For a long time the use of survey data was not
  very popular among economists
• Lester-Machlup debate in the 1940s
• Survey to find out whether employer equate
  marginal cost and marginal revenue
• Billiard player analogy (Friedman, 1953)
• A good pool player makes excellent use of the
  laws of physics without understanding them, and
  certainly without being able to articulate them.
  
• (quoted from Boulier/Goldfarb, 1998)

5
The use of survey data in economics(based on
Boulier/Goldfarb, 1998)

• Blinder (1991, p. 90)

6
Warm-up

• The criticism on the previous slide applies to
  certain types of survey data more than to others.
  
• Can you think of examples for survey data that is
  frequently used e.g. in labor economics?
• What kind of survey data would you be skeptical
  about?

7
The use of survey data in economics

• Criticism People have no incentive to respond
  truthfully or to think about their answer.
• What can be done?
• Compare self-reported data to actual data (e.g.
  earnings)
• Experimentally validate survey measure
• Elicit incentivized measure e.g. on risk
  preferences
• Compare with survey measure
• Potential topic for Diplomarbeit (e.g. trust,
  reciprocity)

8
Warm-up

• Methodological aside The use of incentives in
  experiments is one dimension in which
  psychological and economic experiments differ.
  There is another difference that has led to a
  considerable debate. Do you know which one?

9
The use of survey data in economics - examples

• Examples for use of survey data from lecture
• Individual risk attitudes
• Intergenerational transmission of risk and trust
  attitudes
• Are risk-aversion and impatience related to
  cognitive ability?
• The economics and psychology of personality
• XXX put (methodological summary of every paper??)

10
The use of survey data in economics - examples

• Series of research papers with a data set from
  the GSOEP
• SOEP in 2003,2004 includes several items related
  to risk preferences, trust and impatience
• Paper 1
• Experimentally validate risk question(s) from
  questionnaire (data from pretest)
• Describe risk preferences in representative
  sample
• Check which factors seem to influence risk
  preferences
• Check predictive power for actual behavior

11
Risk measure

• GSOEP 2004 wave
• General risk question
• How do you see yourself Are you generally a
  person who is fully prepared to take risks or do
  you try to avoid taking risks? Please tick a box
  on the scale, where the value 0 means unwilling
  to take risks and the value 10 means fully
  prepared to take risks.
• 11-point response scale
• Context specific risk attitudes
• Health, car driving, financial matters, sports
  and leisure, career

12
Trust measure

• GSOEP 2003 wave
• Survey measure with three sub-questions
• In general, one can trust people (trust)
• In these days you cant rely on anybody else
  (unreliance)
• When dealing with strangers it is better to be
  careful before you trust them (caution)
• Four answer categories
• Agree fully, agree somewhat, disagree somewhat,
  disagree fully
• Also experimentally validated
• Principle component (all three sub-questions)
  predicts choices in trust experiments (Fehr et
  al. 2003, Falk and Zehnder 2006)

13
The use of survey data in economics - examples

• Paper 2
• Check wether risk and trust attitudes are
  transmitted from one generation to the next
• Check whether transmission is specific
• Check whether transmission is reinforced by
  assortative mating
• Paper 3
• Use pretest data (also includes IQ test (WAIS))
• Check wether cognitive ability is related to risk
  preferences and impatience

14
Warm-up

• Why do we care about an intergenerational
  transmission of trust and risk attitudes or the
  relation between cognitive ability and risk
  preferences?
• On the previous slides the word check appeared
  six times. What do economists actually mean when
  they say we check blablabla?

15
Determinants of Risk Attitudes (Probit)
Paper 1 Check which factors seem to influence
risk preferences
16
The use of survey data in economics - examples

• Paper 1
• Check predictive power for actual behavior
• E.g. regression of dummy for stock investment on
  willingness to take risk in financial matters
• Paper 2
• Check wether risk and trust attitudes are
  transmitted from one generation to the next
• Regression of own trust on trust of parents
• Paper 3
• Check wether cognitive ability is related to risk
  preferences and impatience
• Regression of risk preferences

17
Measuring (and using) non-cognitive skills the
Big Five

• Introduction
• People possess a large amount of skills some
  innate, some acquired
• Definition skill
• a trait or capacity that has direct or indirect
  effects on socioeconomic success
• Neoclassical economists focus on cognitive skills
  as the principle source of human differences
  cognitive ability as the main reason for
  variability in outcomes

18
Measuring (and using) non-cognitive skills the
Big Five

• Traits, other than cognition are important for
  success in life e. g. motivation, social skills
• Growth of the service sector suggests that
  people skills have become more important
• Much less agreement among psychologists on
  measures of personality than on measures of IQ
  and achievement
• Psychologists define personality traits in
  particular according to
• Big Five taxonomy

19
The Big Five - history

• Allport and Odbert (1936)
• lexical hypothesismost important individual
  differences are encoded into language
• compiled a list of 4504 personality-describing
  adjectives from English dictionaries
• Cattel (1943)
• reduced these 4504 terms to 171
• 100 persons rated by two friends on these items
• factor analysis leads to 35 factors
• 200 persons rate themselves on these factors
• factor analysis leads to 16 factors (16PF), five
  second-order factors

20
The Big Five - history

• Fiske (1949) constructed simplified descriptions
  from Catells variables
• Tupes and Christal (1961) used these and found
  five relatively strong and recurrent factors
  (through factor analysis)
• Norman (1963) replicated and labelled these
  factors
• OCEAN Opennes to Experience, Conscientiousness,
  Extraversion, Agreeableness and Neuroticism

21
The Big Five - history

• Big Five Factors Goldberg (1981)
• Since then factor structures resembling the Big
  Five were identified in numerous sets of
  variables
• Neo-PI-R most used Big-Five questionnaire
• Importance of Big Five derives from their ability
  to bring a common language to personality
  psychology

22
Components of the Big Five Hogan and Hogan (2007)
23
(No Transcript)