Related Experiment Video
Updated: Jun 24, 2026

Inverse Probability of Treatment Weighting (Propensity Score) using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
Validity of random-digit-dialing in recruiting controls in a case-control study
Peizhong Peter Wang1, Elizabeth Dicks, Xianying Gong
1Division of Community Health and Humanities, Faculty of Medicine, Memorial University of Newfoundland, St. John's, NL, Canada. pwang@mun.ca
In a colorectal cancer study, controls recruited via Random-digit-dialing (RDD) had higher socioeconomic status and were less likely to smoke than the general population. This may skew risk factor findings.
Area of Science:
- Epidemiology
- Public Health
- Cancer Research
Background:
- Case-control studies are crucial for identifying disease risk factors.
- Ensuring control group representativeness is vital for study validity.
- Geographically isolated populations present unique challenges in recruitment.
Purpose of the Study:
- To assess the representativeness of control participants in a North American colorectal cancer case-control study.
- To determine if controls recruited via Random-digit-dialing (RDD) reflect the target population.
- To identify potential biases introduced by the control selection method.
Main Methods:
- Comparison of demographic and lifestyle characteristics of RDD-recruited controls against population estimates.
- Statistical analysis to identify significant differences between controls and the target population.
- Focus on education, income, and smoking status as key indicators.
Main Results:
- Controls exhibited higher educational attainment compared to the general population.
- Participating controls reported higher income levels.
- A lower proportion of controls were current smokers.
Conclusions:
- RDD recruitment in this isolated population resulted in controls with higher socioeconomic status.
- The observed differences may lead to an overestimation of certain colorectal cancer risk factors.
- Future studies should consider alternative recruitment strategies to enhance representativeness.
Related Concept Videos
Randomized Experiments
Simple randomization
Simple...
Group Design
Censoring Survival Data
Controls in Experiments
Data Validation
Key parameters for method validation include:
Wald-Wolfowitz Runs Test II
For binary data, runs are identified using symbols such as + and −, or equivalently, 1s and 0s. In...