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

Nonparametric inference on nonstatio...

Zhang, Ting.

FindBook

Google Book

Amazon

博客來

Nonparametric inference on nonstationary time series.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Nonparametric inference on nonstationary time series./
作者:	Zhang, Ting.
面頁冊數:	97 p.
附註:	Source: Dissertation Abstracts International, Volume: 74-01(E), Section: B.
Contained By:	Dissertation Abstracts International74-01B(E).
標題:	Statistics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3526375
ISBN:	9781267602497

Nonparametric inference on nonstationary time series.
Zhang, Ting.

Nonparametric inference on nonstationary time series. - 97 p.

Source: Dissertation Abstracts International, Volume: 74-01(E), Section: B.

Thesis (Ph.D.)--The University of Chicago, 2012.

Nonparametric methods are model-free approaches that can be useful in assessing parametric and semiparametric models. The problem of testing parametric assumptions has been widely studied in the literature, but mainly for independent data. However, the later assumption can be easily violated in time series analysis where dependence is the rule rather than the exception. In this thesis, we consider the situation with locally stationary processes, a special class of nonstationary processes. We start with the problem of testing whether the mean trend of a locally stationary process falls into a certain parametric form. A central limit theorem for the integrated squared error is derived, and a simulation-assisted hypothesis testing procedure is proposed to improve the finite-sample performance. We demonstrate by simulation that ignoring the underlying dependence can lead to erroneous conclusions. The method is applied to assess the trend pattern of lifetime-maximum wind speeds of tropical cyclones and the central England temperature series. Its extension to high dimensional time series data and time-varying coefficient models are also considered.

ISBN: 9781267602497Subjects--Topical Terms:

517247
Statistics.

Nonparametric inference on nonstationary time series.
LDR:02003nam a2200265 4500 001 1958208
005 20140327081050.5
008 150210s2012 ||||||||||||||||| ||eng d
020 $a 9781267602497
035 $a (MiAaPQ)AAI3526375
035 $a AAI3526375
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Ting. $3 1282232
245 1 0 $a Nonparametric inference on nonstationary time series.
300 $a 97 p.
500 $a Source: Dissertation Abstracts International, Volume: 74-01(E), Section: B.
500 $a Advisers: Wei Biao Wu; Lars P. Hansen.
502 $a Thesis (Ph.D.)--The University of Chicago, 2012.
520 $a Nonparametric methods are model-free approaches that can be useful in assessing parametric and semiparametric models. The problem of testing parametric assumptions has been widely studied in the literature, but mainly for independent data. However, the later assumption can be easily violated in time series analysis where dependence is the rule rather than the exception. In this thesis, we consider the situation with locally stationary processes, a special class of nonstationary processes. We start with the problem of testing whether the mean trend of a locally stationary process falls into a certain parametric form. A central limit theorem for the integrated squared error is derived, and a simulation-assisted hypothesis testing procedure is proposed to improve the finite-sample performance. We demonstrate by simulation that ignoring the underlying dependence can lead to erroneous conclusions. The method is applied to assess the trend pattern of lifetime-maximum wind speeds of tropical cyclones and the central England temperature series. Its extension to high dimensional time series data and time-varying coefficient models are also considered.
590 $a School code: 0330.
650 4 $a Statistics. $3 517247
690 $a 0463
710 2 $a The University of Chicago. $b Statistics. $3 1673632
773 0 $t Dissertation Abstracts International $g 74-01B(E).
790 $a 0330
791 $a Ph.D.
792 $a 2012
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3526375