- Home
- About Us
- Chapters
- Study Design and Organizational Structure
- Study Management
- Tenders, Bids, and Contracts
- Sample Design
- Questionnaire Design
- Instrument Technical Design
- Translation
- Adaptation
- Pretesting
- Interviewer Recruitment, Selection, and Training
- Data Collection
- Paradata and Other Auxiliary Data
- Data Harmonization
- Data Processing and Statistical Adjustment
- Data Dissemination
- Statistical Analysis
- Survey Quality
- Ethical Considerations
- Resources
- How to Cite
- Help
Appendix C (Coder Design Effect)
The coder design effect (deffc) applies much of the same logic as the interviewer design effect (see Interviewer Recruitment, Selection, and Training) [zotpressInText item="{2265844:BLZRKBZS}"].
- In the following formula for coder design effect, [latex]\rho_{c}[/latex] is the intraclass coefficient for coders, [latex]m[/latex] is the average number of cases coded per coder, and [latex]r[/latex] is the reliability of a particular (item) code: [latex]\text{deff}_{c}=1+\rho_{c}(m-1)(1-r)[/latex].
- The intraclass coefficient for coders is a measure of the ratio of coder variance to the total variance and is defined as [latex]\rho_{c}=\frac{\text{between-coder variance}}{\text{between-coder variance}+\text{within-coder variance}}[/latex].