東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Essays on weak identification and co...

Cheng, Xu.

FindBook

Google Book

Amazon

博客來

Essays on weak identification and cointegrating rank selection.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Essays on weak identification and cointegrating rank selection./
作者:	Cheng, Xu.
面頁冊數:	294 p.
附註:	Source: Dissertation Abstracts International, Volume: 71-07, Section: A, page: 2557.
Contained By:	Dissertation Abstracts International71-07A.
標題:	Economics, General. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3415014
ISBN:	9781124089232

Essays on weak identification and cointegrating rank selection.
Cheng, Xu.

Essays on weak identification and cointegrating rank selection. - 294 p.

Source: Dissertation Abstracts International, Volume: 71-07, Section: A, page: 2557.

Thesis (Ph.D.)--Yale University, 2010.

The first two chapters of my dissertation analyze estimation and inference with weak identification. The first chapter studies the least squares (LS) estimator of a nonlinear regression model. This chapter develops a local limit theory that provides a uniform approximation to the finite-sample distribution irrespective of the strength of identification, shows that standard confidence intervals (CIs) and subsampling CIs are prone to size distortion, and develops a new confidence interval (CI) that has good finite-sample coverage probability. This chapter also develops a sequential procedure to deal with multiple nonlinear regressors with different identification strength. It is shown that weak identification on any nonlinear regressor will lead to poor finite-sample approximation by standard asymptotic theory on all parameters in the model.

ISBN: 9781124089232Subjects--Topical Terms:

1017424
Economics, General.

Essays on weak identification and cointegrating rank selection.
LDR:03449nam 2200301 4500 001 1395090
005 20110506125605.5
008 130515s2010 ||||||||||||||||| ||eng d
020 $a 9781124089232
035 $a (UMI)AAI3415014
035 $a AAI3415014
040 $a UMI $c UMI
100 1 $a Cheng, Xu. $3 1253092
245 1 0 $a Essays on weak identification and cointegrating rank selection.
300 $a 294 p.
500 $a Source: Dissertation Abstracts International, Volume: 71-07, Section: A, page: 2557.
500 $a Advisers: Donald W. K. Andrews; Peter C. B. Phillips.
502 $a Thesis (Ph.D.)--Yale University, 2010.
520 $a The first two chapters of my dissertation analyze estimation and inference with weak identification. The first chapter studies the least squares (LS) estimator of a nonlinear regression model. This chapter develops a local limit theory that provides a uniform approximation to the finite-sample distribution irrespective of the strength of identification, shows that standard confidence intervals (CIs) and subsampling CIs are prone to size distortion, and develops a new confidence interval (CI) that has good finite-sample coverage probability. This chapter also develops a sequential procedure to deal with multiple nonlinear regressors with different identification strength. It is shown that weak identification on any nonlinear regressor will lead to poor finite-sample approximation by standard asymptotic theory on all parameters in the model.
520 $a The second chapter (joint with Donald W. K. Andrews) studies estimation and inference in a class of models in which the parameters are unidentified or weakly identified in some parts of the parameter space. It also introduces a method to make the tests and CS's robust to such identification problems. The results apply to a class of extremum estimators and corresponding tests and CS's, including maximum likelihood (ML), least squares (LS), quantile, generalized method of moments (GMM), generalized empirical likelihood (GEL), and minimum distance (MD) estimators. The consistency/lack-of-consistency and asymptotic distributions of the estimators are established under a full range of drifting sequences of true distributions. The asymptotic size (in a uniform sense) of standard tests and CS's is established.
520 $a The third chapter studies long-run exchange rate dynamics by applying a semi-parametric cointegrating rank selection method introduced in Cheng and Phillips (2009a, 2009b). Cheng and Phillips (2009a, 2009b) show that a general semi-parametric error correction model (ECM) with one lag, information criteria based on the reduced rank regression (RRR) can consistently select the cointegrating rank provided that the penalty term goes to infinity at a rate slower than the sample size. This method is robust to persistent volatility shifts of an unknown form, which makes it particularly suitable for the long-run exchange rate dynamics. This empirical study assesses the information criteria-based approach and evaluates long-run exchange rate dynamics among seven major currencies under the flexible exchange rate regimes.
590 $a School code: 0265.
650 4 $a Economics, General. $3 1017424
690 $a 0501
710 2 $a Yale University. $3 515640
773 0 $t Dissertation Abstracts International $g 71-07A.
790 1 0 $a Andrews, Donald W. K., $e advisor
790 1 0 $a Phillips, Peter C. B., $e advisor
790 $a 0265
791 $a Ph.D.
792 $a 2010
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3415014