Generalized Non-Parametric Deconvolution with an Application to Earnings Dynamics
提出一种非参数估计方法，用于在线性独立多因子模型中估计潜变量分布，假设因子载荷已知。该方法利用经验特征函数，可估计最多L(L+1)/2个因子的分布。蒙特卡洛模拟显示有限样本表现良好，但在分布高度偏斜或尖峰时稍差。最后，作者将方法应用于PSID数据，将个人对数收入分解为永久和暂时成分。
In this paper, we construct a non-parametric estimator of the distributions of latent factors in linear independent multi-factor models under the assumption that factor loadings are known. Our approach allows estimation of the distributions of up to <it>L</it>(<it>L</it>+ 1)/2 factors given <it>L</it> measurements. The estimator uses empirical characteristic functions, like many available deconvolution estimators. We show that it is consistent, and derive asymptotic convergence rates. Monte Carlo simulations show good finite-sample performance, less so if distributions are highly skewed or leptokurtic. We finally apply the generalized deconvolution procedure to decompose individual log earnings from the panel study of income dynamics (PSID) into permanent and transitory components.