Omission and commission errors in network cognition and network estimation using ROC curve

- Omission/commission errors are investigated for cognitive social structures (CSS).
- A method for estimating networks from a random sample of CSS slices is proposed.
- The method utilizes the receiver operating characteristic curve.
- A numerical study shows that the proposed estimation method performs well.
- The method may be implemented with the R package cssTools.

Network studies on cognitive social structures collect relational data on respondents' direct ties and their perception of ties among all other individuals in the network. When reporting their perception networks, respondents commit two types of errors, namely, omission (false negatives) and commission (false positives) errors. We first assess the relationship between these two error types, and their contributions on overall respondent accuracy. Next we propose a method for estimating networks based on perceptions of a random sample of respondents from a bounded social network, which utilizes the receiver operator characteristic curve for balancing the tradeoffs between omission and commission errors.