Comparing Sampling Methods for Health Surveys
Author Information
Author(s): Yang Baohui, Margo Eyeson-Annan
Primary Institution: Centre for Epidemiology and Research, Population Health Division, New South Wales Department of Health
Hypothesis
Does sampling using random digit dialing really cost more than sampling from telephone directories?
Conclusion
A LA-RDD sample better represents the population and costs less than an EWP sample.
Supporting Evidence
- LA-RDD sampling has a better representation of the population than EWP sampling.
- LA-RDD can save up to 14.2% in cost compared to EWP sampling.
- The response rate for the EWP sample was 71.4% and 69.0% for the overall LA-RDD sample.
- Weighted LA-RDD sample demographics were closer to the New South Wales population than the EWP sample.
- LA-RDD sampling leads to potentially reduced bias in health estimates.
Takeaway
Using a special phone dialing method can help researchers get better information about people's health while saving money.
Methodology
The study compared demographic profiles, health estimates, and costs between EWP and LA-RDD samples from the New South Wales Population Health Survey in 2003.
Potential Biases
The EWP sample may over-represent socioeconomically advantaged respondents.
Limitations
The study may not account for all potential biases in health estimates.
Participant Demographics
Participants included adults aged 16 years and over, with a mix of demographics reflective of the New South Wales population.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website