Errata

Last updated: 30/Dec/2023

Estimating a Continuous Treatment Model with Spillovers: A Control Function Approach

• In the paragraph just below Theorem 2, “the upper bound for \(\tau_n^*\) is \(O(\tau_n \kappa_n)\)” should be “the upper bound for \(\tau_n^*\) is \(O(\tau_n \sqrt{\kappa_n})\)”.

Sieve IV Estimation of Cross-Sectional Interaction Models with Nonparametric Endogenous Effect

• In the proof of Theorem 3.4(i), there is an error in the evaluation of \(\| D_{n22,d} \|\). Consequently, we need to slightly strengthen Assumption 3.5 to \(J^3/(\underline{\nu}_{JK}n) = O(1)\).

Semiparametric Spatial Autoregressive Models With Endogenous Regressors: With an Application to Crime Data

• In the proof of Lemma A.1(ii), \(\| R_{n2} \| \le \| R_{n21} \| + \| R_{n22} \|\) should be \(\| R_{n2} \| \le \| R_{n21} \| + 2\| R_{n22} \|\).

• In the proof of (4.6) in Section A.3, we need an additional condition to ensure that \(\sqrt{n}\left[\mathbb{S}_t \hat{\mathbf{J}}_n(s_i^*) \mathbb{S}_t'\right]^{-1/2}\left(\hat{\delta}_n(s_i^*) - \bar{\delta}_n\right)\) and \(\sqrt{n}\left[\mathbb{S}_t \hat{\mathbf{J}}_n(s_j^*) \mathbb{S}_t'\right]^{-1/2}\left(\hat{\delta}_n(s_j^*) - \bar{\delta}_n\right)\) are asymptotically uncorrelated.

Quantile Regression Estimation of Partially Linear Additive Models

• In the proof of Lemma A.3, \(E\| S_{1n} \| = 0\) should be \(ES_{1n} = 0\).

Partial Identification in Binary Response Models with Nonignorable Nonresponses

• In the final formula given in Section 5, \(\frac{x_{qi}}{\hat f_n}(v_i \mid x_i)\) should be \(\frac{x_{qi}}{\hat f_n(v_i \mid x_i)}\).