2010
DOI: 10.1017/s0266466610000381
|View full text |Cite
|
Sign up to set email alerts
|

On Rate Optimality for Ill-Posed Inverse Problems in Econometrics

Abstract: In this paper, we clarify the relations between the existing sets of regularity conditions for convergence rates of nonparametric indirect regression (NPIR) and nonparametric instrumental variables (NPIV) regression models. We establish minimax risk lower bounds in mean integrated squared error loss for the NPIR and the NPIV models under two basic regularity conditions that allow for both mildly ill-posed and severely ill-posed cases. We show that both a simple projection estimator for the NPIR model, and a si… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

5
128
1

Year Published

2011
2011
2023
2023

Publication Types

Select...
5
2
1

Relationship

2
6

Authors

Journals

citations
Cited by 107 publications
(134 citation statements)
references
References 27 publications
5
128
1
Order By: Relevance
“…Condition LB is standard in the optimal rate literature (see Hall and Horowitz (2005) and Chen and Reiss (2011)). The mildly ill-posed case corresponds to choosing ν(t) = t −ς , and says roughly that the conditional expectation operator T makes p-smooth functions of X into (ς + p)-smooth functions of W .…”
Section: Lower Boundsmentioning
confidence: 99%
See 2 more Smart Citations
“…Condition LB is standard in the optimal rate literature (see Hall and Horowitz (2005) and Chen and Reiss (2011)). The mildly ill-posed case corresponds to choosing ν(t) = t −ς , and says roughly that the conditional expectation operator T makes p-smooth functions of X into (ς + p)-smooth functions of W .…”
Section: Lower Boundsmentioning
confidence: 99%
“…As in Chen and Reiss (2011), Theorem 3.2 is proved by (i) noting that the risk (in sup-norm loss) for the NPIV model is at least as large as the risk (in sup-norm loss) for the NPIR model, and (ii) calculating a lower bound (in sup-norm loss) for the NPIR model. Theorem 3.2 therefore follows from a sup-norm analogue of Lemma 1 of Chen and Reiss (2011) and Theorem G.1, which establishes a lower bound on minimax risk over Hölder classes under sup-norm loss for the NPIR model.…”
Section: G2 Proofs For Section 32mentioning
confidence: 99%
See 1 more Smart Citation
“…Condition LB(i)-(ii) is standard (see Hall and Horowitz (2005) and Chen and Reiss (2011)). Condition LB(iii) is a so-called link condition (Chen and Reiss, 2011).…”
Section: Lower Bounds On Sup-norm Ratesmentioning
confidence: 99%
“…If W were observed this would be the instrumental variables nonparametric regression model of, e.g., Newey and Powell (2003), Hall and Horowitz (2005), Darolles, Fan, Florens, and Renault, (2011) and Chen and Reiss (2011). Assume, as those authors do, that g .X / is identified from the conditional moments in equation (8), and consider how we might construct sample moment analogues to this equation in the case where W is not observed.…”
Section: Latent Nonparametric Instrumental Variablesmentioning
confidence: 99%