Estimating Panel Models With Internal and External Habit Formation
提出一种新的偏差校正估计量，用于处理同时包含固定效应和空间效应的动态面板模型。应用该估计量分析美国各州消费数据，发现州消费增长受邻近州滞后消费增长影响，支持外部习惯形成模型。
A new bias-corrected estimator is developed for dynamic panel model with both fixed and spatial effects. The estimator is asymptotically unbiased, normally distributed, and it has good finite sample properties (low finite sample bias and root mean squared error). Applying the estimator to annual consumption data for the continental U.S. states shows that state consumption growth is not significantly affected by its own (lagged) consumption growth. However, it is affected by lagged consumption growth of nearby states. These results support external habit formation model, which have been used to explain the behavior of U.S. stock returns.