Text Ch.10 Flashcards
Lollipop question:
was “double-barrelled” in that it had to parts which could be answered differently
Types of survey(4)
Interviewer administered • Face to face • Telephone Self-administered • Internet • Mail/paper
non-response bias
some part of the population is less likely to respond
Things to look for in a survey (6)
.order, interviewer affect, question makeup, authors of survey itself, claimed portability, is topic appropriate for survey research
cross sectional
In medical research and social science, a cross-sectional study (also known as a cross-sectional analysis, transverse study, prevalence study) is a type of observational study that analyzes data from a population, or a representative subset, at a specific point in time—that is, cross-sectional data.
A longitudinal study
is an observational research method in which data is gathered for the same subjects repeatedly over a period of time. Longitudinal research projects can extend over years or even decades. In a longitudinal cohort study, the same individuals are observed over the study period.
Issues and Positives(basic, 2 points)
1.Cross-sectional Survey
- Longitudinal Survey
- Randomized survey experiment
1• Cannot establish temporal order
• Challenge of confounding
2• Temporal order
• Challenge of confounding
3• Temporal order
• Reduced risk of confounding
What type are these: Nominal, Ordinal, Interval, Qualitative
- Scale
- Forced Choice
- Feeling Thermometer
- Open Ended
- Ordinal
- Nominal/Ordinal
- Interval
- Qualitative
Assessing Survey Questions(11) criteria
1q Neutral language
2q Clear (short, specific)
3q Single-barrelled
4q Balanced response options
5q Exhaustive response categories
6q Mutually exclusive response categories
7q Non-response option
8q Is your question sensitive or nonsensitive?
9q Is your question factual or non-factual?
10q Is your question openended or closed-ended?
11q Is your question easy to answer or difficult to
answer?
Official Statistics Vs. Secondary Data
Official Statistics – Electoral returns data – Administrative data – Survey-based data (including census)
Secondary data – Survey datasets designed and compiled by others (e.g., Canadian Election Study)
ecological fallacy
An ecological fallacy (or ecological inference fallacy) is a logical fallacy in the interpretation of statistical data where inferences about the nature of individuals are deduced from inference for the group to which those individuals belong.
omnibus survey
where researchers can add a few questions to a larger survey
coverage bias
the survey data collection mode or some other factor excludes a particular group(s) from the sampling frame
non-response bias
sampling error that occrs if the individuals who opt to participate in a survey are in some important way disimilar to those who dont participate
Bibby reports
an example of longitudinal study of canadian population