(1)Common Features in Vector Nonlinear Time Series Models
30
0
0
Full text
(2) To Love.
(3) Örebro Studies in Statistics 6. DAO LI. Common Features in Vector Nonlinear Time Series Models.
(4) © Dao Li, 2013 Title: Common Features in Vector Nonlinear Time Series Models. Publisher: Örebro University 2013 www.publications.oru.se Print: Örebro University, Repro August/2013 ISSN 1651-8608 ISBN 978-91-7668-952-3.
(5) Abstract Dao Li (2013): Common Features in Vector Nonlinear Time Series Models. Örebro Studies in Statistics 6. This thesis consists of four manuscripts in the area of nonlinear time series econometrics on topics of testing, modeling and forecasting nonlinear common features. The aim of this thesis is to develop new econometric contributions for hypothesis testing and forecasting in these area. Both stationary and nonstationary time series are concerned. A definition of common features is proposed in an appropriate way to each class. Based on the definition, a vector nonlinear time series model with common features is set up for testing for common features. The proposed models are available for forecasting as well after being well specified. The first paper addresses a testing procedure on nonstationary time series. A class of nonlinear cointegration, smooth-transition (ST) cointegration, is examined. The ST cointegration nests the previously developed linear and threshold cointegration. An F-type test for examining the ST cointegration is derived when stationary transition variables are imposed rather than nonstationary variables. Later ones drive the test standard, while the former ones make the test nonstandard. This has important implications for empirical work. It is crucial to distinguish between the cases with stationary and nonstationary transition variables so that the correct test can be used. The second and the fourth papers develop testing approaches for stationary time series. In particular, the vector ST autoregressive (VSTAR) model is extended to allow for common nonlinear features (CNFs). These two papers propose a modeling procedure and derive tests for the presence of CNFs. Including model specification using the testing contributions above, the third paper considers forecasting with vector nonlinear time series models and extends the procedures available for univariate nonlinear models. The VSTAR model with CNFs and the ST cointegration model in the previous papers are exemplified in detail, and thereafter illustrated within two corresponding macroeconomic data sets. Keywords: Nonliearity, Time Series, Econometrics, Smooth transition, Common features, Cointegration, Forecasting, Residual-based, PPP. Dao Li, Department of Statistics, Örebro University School of Business Örebro University, SE-701 82 Örebro, Sweden, daoli2013@gmail.com.
(6)
(7) 0
(8)
(9) 0 .. 0 ". 0 #. 2+-,*10 #
(10). / # 0 . 0 ". 0 #. 2+-,*10 #
(11)
(12) $ 0 . 0 ". 0 #. 2+-,*10
(13) 0 . 0 ". 2+-,*10 / #
(14)
(15) 0 .. dao li Nonlinearity and Common Features. 7.
(16) 8. dao li Nonlinearity and Common Features.
(17) C ontents. . . .
(18) . . 3 #
(19)
(20)
(21) 3 3 !
(22) . . . . . . . . . . . . . . . . . . ,* ,* ,* ,( ,&. . . +,. . +). #
(23)
(24)
(25)
(26) / # . . . . . . +& *, '* ,-' ,**. dao li Nonlinearity and Common Features. 9.
(27) 10. dao li Nonlinearity and Common Features.
(28)
(29) F ,
(30)
(31) 0
(32)
(33)
(34)
(35)
(36) F 0
(37) H H &
(38)
(39)
(40)
(41)
(42) F %
(43)
(44)
(45)
(46) 0
(47) G
(48) %
(49)
(50)
(51)
(52)
(53)
(54)
(55)
(56) F 0
(57) F 0
(58)
(59)
(60)
(61)
(62)
(63) H & .
(64)
(65) H
(66)
(67)
(68) F 0
(69)
(70)
(71)
(72) F H
(73)
(74) G
(75)
(76)
(77) F 0
(78) H 0 G
(79) H
(80)
(81) F 0
(82) H
(83) H
(84)
(85)
(86)
(87)
(88)
(89) K F 8 H 0
(90) 4
(91)
(92) F ,
(93)
(94)
(95)
(96)
(97) F
(98)
(99)
(100)
(101)
(102) H
(103)
(104)
(105)
(106) F
(107)
(108) G 4
(109) 0
(110) F 0
(111)
(112)
(113)
(114)
(115)
(116) H G
(117)
(118)
(119)
(120)
(121) F +
(122)
(123)
(124)
(125) F &
(126)
(127)
(128)
(129)
(130)
(131) H . 6 H
(132)
(133) )5 7
(134)
(135) G
(136)
(137)
(138) F
(139)
(140)
(141)
(142)
(143) H
(144)
(145)
(146) F 0
(147)
(148) 7 F
(149)
(150) H
(151) F %
(152)
(153)
(154)
(155)
(156)
(157) 6
(158)
(159) 77(
(160) F &
(161)
(162)
(163) H F
(164)
(165)
(166)
(167) & H G
(168)
(169)
(170)
(171) . dao li Nonlinearity and Common Features. 11.
(172)
(173)
(174) F %
(175)
(176) H
(177) H
(178) G H
(179) H
(180) F H
(181) H
(182)
(183)
(184)
(185)
(186) . F %
(187) F %
(188)
(189)
(190) F.
(191) F ,
(192) / -
(193) F ,
(194)
(195) %
(196) -
(197)
(198)
(199)
(200)
(201) &
(202)
(203) F 0
(204)
(205)
(206) G
(207) F 0
(208) F ,
(209) -
(210) '
(211)
(212) H
(213)
(214)
(215)
(216)
(217)
(218) F %
(219) 8
(220) 3
(221)
(222) G
(223) F %
(224) / 1
(225)
(226)
(227) F %
(228) 6 1H
(229) H
(230)
(231) G
(232)
(233) F %
(234) * +
(235)
(236)
(237)
(238) F %
(239) ' & , 8
(240)
(241)
(242)
(243)
(244)
(245)
(246)
(247)
(248)
(249)
(250)
(251) F %
(252) 5 "
(253)
(254)
(255) 7 $
(256) F %
(257) .
(258) &
(259)
(260)
(261)
(262)
(263)
(264)
(265) F ,
(266) 6 6 H ! &
(267)
(268)
(269) F %
(270)
(271)
(272)
(273)
(274) F 8
(275) G
(276) H H !F1F ,
(277)
(278) F " G 1
(279) H #
(280)
(281) F %
(282) ,H ! H
(283)
(284)
(285)
(286) H
(287)
(288)
(289)
(290)
(291)
(292)
(293) H
(294) H H
(295)
(296) F ,
(297) 8H - H "H H 3H -
(298) H & H H
(299) H )5
(300)
(301) H
(302)
(303)
(304) F. 7 H CEDB 5 . 12. dao li Nonlinearity and Common Features.
(305)
(306) # %
(307)
(308)
(309)
(310)
(311) F ,
(312)
(313)
(314)
(315)
(316)
(317)
(318)
(319)
(320)
(321) F 0 H
(322)
(323) J
(324) H FFH %
(325) : D<<AIF &
(326)
(327)
(328)
(329)
(330) H
(331)
(332)
(333)
(334)
(335) F ,
(336)
(337)
(338)
(339)
(340) F ,
(341)
(342)
(343)
(344)
(345)
(346) G
(347) F & 4 . JD<<BIF &
(348) G
(349)
(350) F "
(351)
(352) G H
(353)
(354)
(355)
(356) F 6
(357)
(358)
(359)
(360) G
(361) G
(362)
(363) F 6
(364)
(365) G
(366)
(367)
(368)
(369)
(370)
(371)
(372)
(373) 4 2 JD<=>I F 0
(374)
(375)
(376)
(377)
(378)
(379)
(380)
(381)
(382) G
(383)
(384) G F 4
(385)
(386)
(387) 7 & JD<=>I 6 G *
(388) JD<==I
(389) H .
(390) JD<=<I
(391)
(392)
(393) 2+) H 6 JD<<AI
(394) G
(395) F "
(396) H G
(397)
(398)
(399)
(400) G
(401) F %
(402)
(403)
(404)
(405) G
(406) J&%I F % G
(407) F 2 %
(408) JD<<BI 2 JD<<@I 4 2 JD<=>I
(409) F 7 3 JD<<>I
(410) G
(411) G
(412) F ) )
(413) JD<<<H CEEDI 6 F JCEEDI
(414)
(415)
(416)
(417)
(418) F 1
(419) & JCEEC.
(420)
(421) 8 &%8'
(422)
(423)
(424)
(425) G
(426)
(427)
(428)
(429)
(430)
(431)
(432)
(433)
(434) .
(435)
(436)
(437) . dao li Nonlinearity and Common Features. DB. 13.
(438) %
(439) JD<<AI
(440)
(441)
(442)
(443) &%8'
(444) F %
(445)
(446) &%8'
(447)
(448)
(449) F 4
(450) JD<=>I 2 & G
(451) JD<<?I
(452) G
(453) G G
(454) F /
(455) JD<<@I
(456) G
(457)
(458) G F , H 5 3
(459)
(460) JD<<<I &%8'
(461)
(462) F - %
(463) JD<<AI 1 & JCEE?I
(464) G &%8'
(465)
(466)
(467) F 1 F JCEE<I
(468)
(469)
(470)
(471)
(472) #&%8' F. &
(473)
(474)
(475)
(476)
(477) F %
(478)
(479)
(480)
(481) H #&%8' H . . . . . . . . . H H H H
(482) H
(483)
(484) H
(485)
(486)
(487)
(488) . JDI. . . . .
(489). . . . JCI. .
(490) F 1 H
(491) F %
(492)
(493)
(494)
(495)
(496)
(497)
(498)
(499) G
(500)
(501)
(502) F %
(503) G
(504) J&%I H
(505)
(506) H
(507)
(508)
(509) H
(510)
(511)
(512) G
(513) F & 3 D
(514) F. "
(515)
(516) J6+3
(517) IH
(518)
(519)
(520) . . . . . . JBI. . .
(521)
(522) 6+3
(523)
(524) . . 14. . .
(525)
(526)
(527) . dao li Nonlinearity and Common Features. DA. . F.
(528) ,%
(529)
(530)
(531) .
(532) . . %
(533)
(534)
(535) 6+3
(536) . . . . . . JAI. . . . . . . . . . . . JBI
(537)
(538)
(539)
(540) JDI H H H F 3 C
(541)
(542)
(543) 6+3F +
(544)
(545)
(546)
(547)
(548) G
(549)
(550) H
(551)
(552)
(553)
(554)
(555)
(556) F & 4 2 JD<=>IF %
(557) &% F %
(558)
(559) &% G.
(560) G
(561) H . . . . J@I. .
(562)
(563)
(564) . dao li Nonlinearity and Common Features. D@. 15.
(565) +%
(566)
(567)
(568)
(569)
(570)
(571)
(572)
(573)
(574)
(575)
(576) . . . . . . J?I. . . H H H
(577) H
(578)
(579) H F & )
(580) JD<<DI
(581) F 3 B
(582)
(583) &% F. #
(584) # . %
(585)
(586)
(587)
(588)
(589)
(590) F 3
(591) H
(592)
(593)
(594)
(595)
(596) F & H
(597)
(598)
(599)
(600)
(601)
(602)
(603)
(604)
(605) F % H
(606)
(607)
(608) F 0
(609) H
(610)
(611)
(612)
(613) H
(614)
(615)
(616) F 1 H
(617)
(618) H
(619)
(620)
(621)
(622)
(623)
(624)
(625). . 16.
(626)
(627)
(628) . dao li Nonlinearity and Common Features. D?.
(629) *%
(630)
(631)
(632)
(633)
(634)
(635)
(636)
(637)
(638)
(639)
(640)
(641)
(642)
(643)
(644) .
(645) F " -. F JD<==I
(646)
(647) - 1 JCEDBI F 0
(648) H
(649)
(650)
(651)
(652)
(653) G
(654)
(655) G F 3 H 4 . JD<<BI
(656)
(657)
(658)
(659) 4 2 JD<=>IF %
(660) G
(661) F 4
(662)
(663)
(664)
(665) 8
(666) # JD<<=I
(667)
(668) G
(669)
(670)
(671) F %
(672)
(673)
(674)
(675)
(676) G
(677)
(678)
(679)
(680)
(681)
(682)
(683)
(684)
(685) F %
(686)
(687)
(688)
(689)
(690)
(691) F 1 H
(692)
(693)
(694)
(695) .
(696)
(697)
(698) . dao li Nonlinearity and Common Features. D>. 17.
(699)
(700) F 6
(701) H
(702)
(703) 6+3
(704)
(705)
(706)
(707)
(708) H
(709)
(710)
(711)
(712) F $
(713)
(714)
(715)
(716) H
(717)
(718)
(719)
(720) F 8
(721)
(722)
(723) 6+3
(724) 9 0
(725)
(726)
(727) 6+3
(728)
(729) JAI
(730) F 7
(731)
(732)
(733)
(734)
(735) 6+3
(736) F *
(737) H
(738) F %
(739)
(740)
(741)
(742)
(743) &%8' 4 %
(744) 2 JD<<? JD<==IF 1 H
(745)
(746)
(747)
(748)
(749)
(750)
(751)
(752)
(753) F %
(754) .
(755)
(756) F 3 H
(757) JAI
(758)
(759) H G
(760)
(761)
(762) F "
(763) G
(764)
(765)
(766)
(767) H
(768)
(769)
(770)
(771) H
(772)
(773)
(774) G
(775) H
(776)
(777)
(778)
(779)
(780)
(781) J
(782) I
(783) F % H
(784)
(785)
(786)
(787)
(788)
(789) G
(790)
(791)
(792) )
(793) *
(794) JD<<EIF '
(795) G
(796)
(797) G
(798)
(799)
(800)
(801)
(802)
(803)
(804)
(805)
(806) F 1 H
(807)
(808)
(809)
(810)
(811)
(812)
(813)
(814)
(815)
(816) F ' '
(817) JD<=CIH ) & JD<=?I ) JD<=?IF 8
(818)
(819)
(820)
(821)
(822) H H % G
(823) 4 2 JD<=>I
(824)
(825) F 7
(826)
(827) F ,
(828)
(829)
(830) G F &%
(831)
(832)
(833) &%
(834) 6 & JCEEAIF % G H H
(835)
(836)
(837) J@I J?I
(838)
(839)
(840) H
(841) %
(842)
(843) J@I J?I F 6 & JCEEAI
(844) - , J-,I
(845)
(846) &%
(847)
(848)
(849)
(850)
(851)
(852) & 6 JCEEAIF 1 H & 6 JCEEAI
(853)
(854)
(855)
(856)
(857)
(858)
(859) . . 18.
(860)
(861)
(862) . dao li Nonlinearity and Common Features. D=.
(863)
(864)
(865)
(866) F "
(867)
(868)
(869)
(870) G
(871)
(872)
(873)
(874)
(875)
(876)
(877) F %
(878)
(879)
(880) & 6 JCEEAIF 6
(881)
(882)
(883)
(884) H
(885)
(886) & 6 JCEEAI
(887)
(888)
(889)
(890) H
(891)
(892)
(893)
(894)
(895)
(896)
(897) F %
(898)
(899) F 7
(900)
(901)
(902)
(903)
(904)
(905)
(906)
(907)
(908)
(909)
(910)
(911)
(912) F
(913)
(914)
(915) F *
(916)
(917)
(918)
(919) G F & %
(920) JD<<AIF % #&%8' &%
(921)
(922)
(923)
(924) J+-&IF 1G H #&%8' 6+3
(925)
(926) G
(927)
(928) H +-&
(929) F %
(930) '''
(931)
(932) F & '
(933) # JD<<=IF '
(934)
(935)
(936)
(937)
(938) F "
(939)
(940)
(941) #&%8' J 6+3
(942) IH
(943)
(944)
(945)
(946) G &%
(947)
(948)
(949)
(950)
(951)
(952)
(953) F. )
(954)
(955)
(956)
(957)
(958)
(959) G
(960)
(961)
(962) F %
(963) JCEE?H 6 =I
(964)
(965)
(966)
(967) F &
(968)
(969)
(970)
(971)
(972)
(973) . . . J>I.
(974)
(975)
(976)
(977)
(978)
(979) F - G
(980)
(981) H
(982) F " H G
(983)
(984)
(985)
(986)
(987)
(988) F 1 H . H
(989) F &
(990)
(991)
(992)
(993)
(994)
(995) F " H.
(996)
(997)
(998) . dao li Nonlinearity and Common Features. D<. 19.
(999) H G
(1000)
(1001)
(1002)
(1003)
(1004)
(1005) . . . .
(1006)
(1007) . .
(1008)
(1009) F 8
(1010)
(1011)
(1012) H
(1013)
(1014)
(1015)
(1016) F 6
(1017) H
(1018)
(1019)
(1020)
(1021) F 0 H , 6
(1022)
(1023)
(1024) G F 8
(1025)
(1026) H G
(1027)
(1028)
(1029). H
(1030)
(1031) . .
(1032)
(1033) . .
(1034)
(1035) F )
(1036)
(1037) G
(1038)
(1039) F 1 H
(1040)
(1041)
(1042)
(1043)
(1044) G
(1045)
(1046)
(1047)
(1048) F 3 H
(1049)
(1050)
(1051) G
(1052)
Related documents
One important objective of nonlinear time series analysis is to identify a time series as having a nonlinear origin in the first place.. It might be that the data is better
The main objective of this thesis has been to study how well various individual machine learning models perform by comparing them when predicting stock indexes as of three
macroeconomic data) for both single and multivariate relationships are presented (2) a sound modeling cycle is provided, and contains the steps specification, estimation, and
Figure 4.6: One-step forecast made using the RNN-RBM model (red) with multiple cells, a single counter and 7 days of history as input.. The real data is shown in blue and
In the Vector Space Model (VSM) or Bag-of-Words model (BoW) the main idea is to represent a text document, or a collection of documents, as a set (bag) of words.. The assumption of
The long-term goal is that the algorithms proposed in this work be used in time- series data forecasting applications (both in industry and academia) that meet the
This thesis consists of four manuscripts in the area of nonlinear time series econometrics on topics of testing, modeling and forecasting non- linear common features.. The aim of
The most common used in this context is the autoregressive moving average model (ARMA) and the autoregressive integrated moving average model (ARIMA) For
