TOE correlationeel– hoorcollege 1: Surveys
Quantitive Data
★ Data are generated in different ways
○ Incidentally, aka organic → aspirational, transactional for example instagram, not
created for research but can be used as such.
○ Purposively, aka designed → experiment, survey, administrative (shares some
characteristics for organic)
Correlational Data (designed)
→ We design a study & collect data to
★ describe the social reality
★ study (causal) relationships
★ generalize to the target population
Inferential goals
★ Description: describing what the situation is and what, for example, the peoples opinion is.
★ Causation: cause and effect.
★ Prediction: describing what is going on or making a prediction about a situation. (Not that
popular in surveys).
Survey Modes
★ Face to face (Computer Assisted Personal Interviewing)
★ Mail
★ Telephone (Computer Assisted Telephone Interviewing)
★ Internet
★ Mixed-mode
Difference between the survey modes
★ Degree of interviewer involvement: on web there’s no interviewer, on telephone there is an
interviewer but it’s not the same as face-to-face
★ Degree of interaction with the respondent: online interaction is more than mail
★ Degree of privacy: registered via mail or not for example
★ Channels of communication: visual, auditive
Pagina 1 van 14
, ★ Technology use
In comparison:
Types of mixed- mode design
★ One mode for some respondents, another mode for others
○ e.g. online survey with mail component for those without internet
★ One mode for recruitment, another for survey administration
○ e.g. mail invitation for an online survey
★ One mode for data collection, another for reminders, follow- up.
○ e.g. telephone reminders for an online survey
★ One mode for the main part of the interview, another for some subset of answers (e.g.
sensitive items).
○ e.g. telephone and Audio Computer Self-Administered (ACASI), so people can fill in
the sensitive items without an interviewer being there
★ One mode for one wave of the panel survey, another for others.
Cross-sectional and panel surveys
★ Panel surveys interview respondents over time (content usually the same, but may differ)
★ Advantages:
★ We can assess within-person change and causality, you can see what caused what
★ We can disentangle age, period, and cohort effects
★ Potential errors:
★ Attrition, uitval (drop-out or consecutive wave-nonrespondents)
★ Panel conditioning, can learn to give answers (aka learning effects)
■ negative: people might recognize the filtering in questioning and decide to
change their answer
■ positive: pay attention to certain details so they report better data (like how
much they earn)
Pagina 2 van 14