Abstrak RSS

A Spatio-Temporal Autoregressive SEM Model for Reducing Omitted Variable Bias

A Spatio-Temporal Autoregressive SEM Model for Reducing Omitted Variable Bias
Yusep Suparman
Universitas Padjadjaran
Bahasa Inggris
Universitas Padjadjaran

Structural Equation Modeling (SEM) has been recognized as a powerful analytical tool. Nevertheless, SEM assumes that observations are independent. This assumption prevents us to apply SEM in spatial modeling in which observations depend on each other according to their position in a space. Here we propose to formulate a SEM for accommodating spatial dependency among observations. Particularly, we focus on spatio-temporal autoregressive model for reducing omitted variable bias in a spatial autoregressive model.

Download: .Full Papers