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

Contaminated, corrupted, and missing...

Molinari, Francesca.

FindBook

Google Book

Amazon

博客來

Contaminated, corrupted, and missing data.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Contaminated, corrupted, and missing data./
作者:	Molinari, Francesca.
面頁冊數:	226 p.
附註:	Source: Dissertation Abstracts International, Volume: 64-04, Section: A, page: 1344.
Contained By:	Dissertation Abstracts International64-04A.
標題:	Economics, General. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3087948

Contaminated, corrupted, and missing data.
Molinari, Francesca.

Contaminated, corrupted, and missing data. - 226 p.

Source: Dissertation Abstracts International, Volume: 64-04, Section: A, page: 1344.

Thesis (Ph.D.)--Northwestern University, 2003.

Incomplete and error-ridden data are commonplace problems in empirical work in economics and in the social sciences. This dissertation is concerned with studying the inferential problems caused by specific types of such data imperfections.Subjects--Topical Terms:

1017424
Economics, General.

Contaminated, corrupted, and missing data.
LDR:03254nmm 2200289 4500 001 1858622
005 20041020093006.5
008 130614s2003 eng d
035 $a (UnM)AAI3087948
035 $a AAI3087948
040 $a UnM $c UnM
100 1 $a Molinari, Francesca. $3 1946305
245 1 0 $a Contaminated, corrupted, and missing data.
300 $a 226 p.
500 $a Source: Dissertation Abstracts International, Volume: 64-04, Section: A, page: 1344.
500 $a Adviser: Charles F. Manski.
502 $a Thesis (Ph.D.)--Northwestern University, 2003.
520 $a Incomplete and error-ridden data are commonplace problems in empirical work in economics and in the social sciences. This dissertation is concerned with studying the inferential problems caused by specific types of such data imperfections.
520 $a Chapter 1 and Chapter 2 investigate, respectively, the identification problems caused by missing treatment data and by data errors in discrete variables. These problems can occur, for example, when survey respondents refuse to answer a question, or when they give inaccurate reports. Each chapter contributes to the existing literature on drawing inference in presence of incomplete and error-ridden data (see Manski (2003)) starting from a base-case situation in which the researcher has no prior information on the process preventing complete observation of sample realizations, or on that generating data errors. In this case the inference that can be drawn on the distribution of the variable of interest is partial, in the sense that the parameter of interest can generally be identified to belong to a certain set, which is not a singleton. For each of the specific data problems considered I derive these sets, the identification regions, and I show that they are “sharp,” in the sense that they exhaust all the available information, given the sampling process and the maintained assumptions. I then depart from the base-case by introducing increasingly strong assumptions on the process generating the missing or erroneous data, emphasizing the inevitable trade-off between their credibility and their capability of sharpening the inference. Chapter 3, which is coauthored with Timothy C. Conley, addresses a specific problem of error-ridden data. We present a Monte Carlo study concerning inference with spatially dependent data. The fundamental feature of any spatial econometric model is the choice of locations for the observed agents, the space or metric. We investigate the impact of location/distance measurement problems upon the accuracy of parametric and nonparametric estimators of asymptotic variances. We consider measurement errors in distances, and locations that are known only up to broad areas like zip codes, SMSAs, or counties. Our results show that at modest levels of imperfection in distance information, the performance of the parametric estimator becomes worse than that of the nonparametric estimator.
590 $a School code: 0163.
650 4 $a Economics, General. $3 1017424
650 4 $a Economics, Theory. $3 1017575
650 4 $a Sociology, Industrial and Labor Relations. $3 1017858
690 $a 0501
690 $a 0511
690 $a 0629
710 2 0 $a Northwestern University. $3 1018161
773 0 $t Dissertation Abstracts International $g 64-04A.
790 1 0 $a Manski, Charles F., $e advisor
790 $a 0163
791 $a Ph.D.
792 $a 2003
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3087948