本頁只刊出中文翻譯與中文說明；英文原文請見下方原文連結。
原文連結
論文資訊
- 類型：已發表論文
- 日期：2021-07-12
摘要
社會 influence cannot be identified from purely observational data on 社會 網絡s, because such influence is generically confounded with latent homophily, that is, with a node's 網絡 partners being informative about the node's attributes and therefore its behavior. If the 網絡 grows according to either a latent community (隨機 block) model, or a continuous latent space model, then latent homophilous attributes can be consistently estimated from the global pattern of 社會 ties. We show that, for common versions of those two 網絡 models, these estimates are so informative that controlling for estimated attributes allows for asymptotically unbiased and consistent estimation of 社會-influence effects in linear models. In particular, the bias shrinks at a rate that directly reflects how much 資訊 the 網絡 provides ab
※ 此為已發表論文，全文需透過期刊付費取得