Quantitative Research Flashcards
Surveys
Adv- Large samples – generalisability, estimates differences, easy to administer and record answers, can assess abstract concepts and relationships
Disadv- Questions to measure accurately attitudes and behaviours are hard to develop, data from open ended questions may not be enough to record all concepts, response rate over surveying
Person administered surveys
In home – expensive, timely, anonymity, data fabrication
Mall intercepts– people in a hurry, may not be representative, anonymity, data fabrication, expensive
Telephone survey (CATI)
Faster and cheaper, quality assurance, expands geographic flexibility, call backs, allows validation, more anonymous
Lengthy question is hard to administer, can’t present visuals, access only to people with landline
Self administered
Direct-mail, mail panel – people agree to participate, drop off/pick up
For when you want to survey the whole population. But, expensive, low response rate, non-response bias, missing data, take longer to complete and return, how to ensure right person completed
Online survey (email)
Link sent directly to participant, cheaper, faster data collection (80% of data in first 2 days), forced response = no missing data, allows visuals and videos, other interactive scales.
Disadvantages: representativeness, need to have active emails, duplicates, need to keep an eye on speeders or click throughs
Online panels
People volunteer to give away their data for reward - bias. Quality issues- people may report different age/gender. May not be representative of aus population.
But: give access to specific target groups, multiple panel providers available.
In the moment research
Have to complete immediately when you receive a notification. Requires access to mobile numbers and respondents openness to method. Lack of convenience.
Factors impacting method choice
Budget (online cheaper)
Speed (online and cati)
Quality requirements (cati)
Generalisability (random lists(cati) better)
Visual stimulating (online/self administered)
Research topic sensitivity (online)
Random sampling error
Difference between findings in sample and actual population.
Insufficient sample size.
Systematic error (bias)
Interviewer error: recording error, cheating, misinterpretation.
Data processing error: coding open ended questions, data entry, data editing (recoding)
Administrative error: sample selection- selecting/avoiding specific people, survey admin method
Problem definition: misunderstood brief, wrong hypotheses. Make sure to talk to client, researcher, lit review.
Measurement/design error: ambiguity, layout, wrong influences, filters not applied
Respondent error
Non response- not home, wrong contact details, refusal.
Response error- deliberate falsification, unconscious misrepresentation
