Description
Measures exposure and outcome in a representative sample at one point in time to estimate prevalence and associations of UX harm.
The treatise lists cross-sectional surveys among the epidemiological toolkit that can be adapted for UX. A cross-sectional study samples a defined population at one time, measuring exposures, outcomes and covariates simultaneously. It estimates prevalence (for example the share of adults who were charged after failing to cancel a subscription in the past year) and associations (prevalence ratios by age or literacy). Its limitation is temporality: exposure and outcome are measured together, so causal direction is uncertain. Rigour depends on probability sampling or weighting, validated questions with defined recall periods and non-response adjustment. It is the cheapest population-level instrument and the basis of active surveillance waves.
Attributes
- Discipline
- Epidemiology & Population Health
- Loss type
- Unmigrated
- Stage
- Post-launch, Discovery
- Data
- Quantitative
- Effort
- Weeks
Steps
- Define the target population and sampling frame.
- Design questions with clear recall periods and validated measures.
- Draw a probability or weighted sample of adequate size for subgroup estimates.
- Field the survey and track response rates.
- Weight results and estimate prevalence and prevalence ratios with CIs.
- Report limitations regarding temporality and recall.
Sources
- Lost Methods in UX — A Complete Treatise (Gopinath)
- Levin KA (2006) Study design III: cross-sectional studies. Evidence-Based Dentistry 7
- Groves RM et al. (2009) Survey Methodology
- Gratton, C. & Jones, I., Research Methods for Sports Studies (2010)
Also known as
- Prevalence survey
- Cross-sectional study
Categories
- Epidemiology & Population Health