TOE Correlationeel Hoorcollege aantekeningen 2021/2022

Correlational Research
Toepassing van onderzoeksmethoden en statistiek


MEETING 1: Surveys
Different types of data:
- Customer satisfaction
- Political polls
- Governmental statistics

The growth of digital data, groeiende hoeveelheden van deze data.

Correlational data
Data are generated in different ways
- Incidentally
 AKA organic
 Ready made, de data is er al
 Dus niet voor onderzoek
- Purposively
 AKA designed (bv, in een survey)
 Custom made; designed data
 Voor onderzoek




Focus on: survey [meeting 1]

Correlational Data (designed)
We design a study & collect data to:
- Describe the reality
- Study (causal) relationships
- Generalize to the target population, dus iets
zeggen over de populatie (genernaliseren
naar)
- Figuur laat infers zien
Inferential goals:
- Description (beschrijvend)
- Causation (oorzakelijk)
- Prediction (voorspellend)

How to ask? Survey Modes

, - Face-to-face (CAPI) (Computer assisted person interview)
- Mail
- Telephone (CATI) (Computer assisted telephone interview)
- Internet
- Mixed-mode

Differences between the modes
- Degree of interviewer involvement
 In person, via de telefoon, of helemaal geen persoon
- Degree of interaction with the respondent
- Degree of privacy
- Channels of communication
 Visual
 Auditive
- Technology use

Survey modes in comparison
Attribute Face-to-face Mail Telephone Internet
Cost high low moderate low
Response Rate high low high moderate
Researcher high low moderate moderate
control over
interview
Interviewer high low moderate low
effects

Survey Modes in NL
- Population register & over 90% internet use
 Telephone Surveys (Random Digit Dialing) not widely used
- Mode mixes
 Postal mail with invitations to internet surveys
 Telephone component if numbers are known
- Market Researchers use both probability and nonprobability online panels
- Mixed-device surveys
 Computer/smartphone

Types of mixed-mode design
- One mode of some respondetns, 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 main part of the interview, another for some subset of answers (e.g. sensitive items)
 E.g. Telephone & Audio Computer Self-Administered (ACASI)

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 & causality
 We can disentangle age, period, and cohort effects
- Potential errors:
 Attrition (uitval) (drop-out or consecutive wave-nonresponse)
 Panel conditioning (AKA learning effects)