Return and Volatility Spillovers Between Large and Small Stocks in the UK

Size: px
Start display at page:

Download "Return and Volatility Spillovers Between Large and Small Stocks in the UK"

Transcription

1 eurn and Vlailiy Spillvers Beween Large and Small Scks in he UK ichard D. F. Harris Xfi Cenre fr Finance and Invesmen Universiy f Exeer, UK Aniru Pisedasalasai Deparmen f Accuning, Finance and Infrmain Sysems Universiy f Canerbury, New Zealand Augus 005 Paper Number: 06/09 Absrac This paper invesigaes reurn and vlailiy spillver effecs beween he FTSE 100, FTSE 50 and FTSE Small Cap equiy indices using he mulivariae GACH framewrk. We find ha reurn and vlailiy ransmissin mechanisms beween large and small scks in he UK are asymmeric. In paricular, here are significan spillver effecs in bh reurns and vlailiy frm he prflis f larger scks he prflis f smaller scks. Fr vlailiy, here is als evidence f limied feedback frm he prflis f smaller scks he prflis f larger scks, alhugh sub-perid analysis suggess ha his is sme exen perid-specific. Simulain evidence shws ha nn-synchrnus rading penially explains sme, bu n all, f he spillver effecs in reurns, and ha i explains nne f he spillver effecs in vlailiy. These resuls are cnsisen wih a marke in which infrmain is firs incrpraed in he prices f large scks befre being impunded in he prices f small scks. KEYWODS: eurn and vlailiy spillvers; Mulivariae GACH; FTSE indices. Address fr Crrespndence: ichard D.F. Harris, Xfi Cenre fr Finance and Invesmen, Universiy f Exeer, Exeer EX4 4ST, UK. .D.F.Harris@exeer.ac.uk. 1

2 1. Inrducin Transmissin mechanisms beween he reurns and vlailiies f differen scks are impran fr a number f reasns. Firsly, ransmissin mechanisms ell us smehing abu marke efficiency. In an efficien marke, and in he absence f ime-varying risk premia, i shuld n be pssible frecas he reurns f ne sck using he lagged reurns f anher sck. The finding ha here are spillver effecs in reurns implies he exisence f an expliable rading sraegy and, if rading sraegy prfis exceed ransacin css, penially represens evidence agains marke efficiency. Secndly, ransmissin mechanisms may be useful fr prfli managemen, where knwledge f reurn spillver effecs may be useful fr asse allcain r sck selecin. Thirdly, infrmain abu vlailiy spillver effecs may be useful fr applicains in finance ha rely n esimaes f cndiinal vlailiy, such as pin pricing, prfli pimizain, value a risk and hedging. Many previus sudies have dcumened ha he reurns f large and small scks in he US sck marke are crss-crrelaed. 1 Mrever, a number f hese sudies shw ha hese crss-crrelains are asymmeric: he reurns f small sck prflis end be crrelaed wih he lagged reurns f large sck prflis, while he reurns f large sck prflis end be uncrrelaed wih he lagged reurns f small sck prflis. L and MacKinlay (1990a, 1990b) rule u nn-synchrnus rading as an explanain since implausible levels f nn-synchrnus rading are required generae he size f he crss-crrelains ha exis in pracice. A number f her explanains have herefre been prpsed. Mech (1993) suggess ha asymmery in he crss-crrelain beween reurns n large and small scks is due ransacin css, and shws ha he speed f price adjusmen is assciaed wih he sandard deviain f reurns and he bid-ask spread. Chan (1993) suggess ha differences in signal qualiy beween large and small scks induce asymmery in heir crsscrrelains. In paricular, if he signal qualiy f large scks is assumed be beer han ha f small scks, he cvariance f he curren reurns f small scks wih he lagged reurns f large scks is larger han he cvariance f he curren reurns f 1 See, fr example, L and MacKinlay (1990a, 1990b), Budukh, ichardsn and Whielaw (1994), Mech (1993), Badrinah, Kale and Ne (1995), McQueen, Pinegar and Thrley (1996) and Campbell, L and MacKinlay (1997, pages 74-78).

3 large scks wih he lagged reurns f small scks. Sme sudies (fr example, Grinbla, Timan, and Wermers, 1995; Keim and Madhavan, 1995) argue ha asymmeric spillver effecs in he reurns f large and small scks are relaed asymmeric rading paerns and he behavir f insiuinal invesrs. Cnrad, Gulekin and Kaul (1991) shw ha he same asymmery ha exiss in he ransmissin f shr hrizn reurns beween large and small scks in he US als exiss in he ransmissin f vlailiy. They find ha vlailiy shcks large scks are impran fr he fuure vlailiy f small scks, bu ha vlailiy shcks smaller scks have lile r n impac n he fuure vlailiy f large scks. As wih he resuls fr reurn spillvers, simulain evidence suggess ha he bserved spillver effecs in vlailiy are n caused by nn-synchrnus rading. Cnrad Gulekin and Kaul (1991) ne ha since sck price vlailiy is direcly relaed he rae f flw f infrmain he marke (see ss, 1989), he asymmery in vlailiy spillvers beween large and small scks is cnsisen wih a marke in which he prices f large scks respnd new infrmain immediaely, bu he prices f small scks respnd wih a lag. This explanain is suppred by McQueen, Pinegar and Thrley (1996), wh shw ha small scks display a delayed reacin cmpared large scks when news reaches he marke. Using lnger hrizn reurns, Hasan and Francis (1998) als find ha here are vlailiy spillvers beween small and large scks in he US, bu in cnras wih Cnrad Gulekin and Kaul (1991), hey find ha hese spillvers are apprximaely symmeric, acing bh frm large scks small scks, and frm small scks large scks. This paper invesigaes he reurn and vlailiy ransmissin mechanisms beween large and small scks in he UK sck marke using daily daa n he FTSE 100, FTSE 50 and FTSE Small Cap equiy indices. We invesigae hese ransmissin mechanisms using he cnsan crrelain mulivariae GACH mdel f Bllerslev (1990). We mdel he spillver effecs by inrducing in he mean and variance equain fr each index, he lagged shcks he reurns and vlailiies f he her w indices. T ensure ha ur resuls are rbus, we include dummy variables capure uliers, calendar effecs and he asymmeric respnse f vlailiy gd and bad news. T furher es he rbusness f ur resuls, we cnduc he analysis using bh he full sample and w sub-samples. Our resuls shw ha here are srng 3

4 reurn and vlailiy ransmissin mechanisms beween small and large scks in he UK sck marke. Furhermre, cnsisen wih he resuls f her sudies fr he US, we find ha hese reurn spillver effecs are asymmeric. In paricular, here are very significan reurn spillvers frm he prflis f large scks he prflis f small scks. Fr vlailiy, here are again psiive spillvers frm he prflis f large scks he prflis f small scks, alhugh here is als evidence f feedback frm he prflis f smaller scks he prflis f larger scks, and in ne case, his feedback effec is negaive. Hwever, fr he sub-samples, he paern f vlailiy spillvers is very similar ha fr reurn spillvers, wih nly limied psiive feedback frm small sck prflis large sck prflis. In rder analyse he effec f nn-synchrnus rading n ur resuls, we underake a Mne Carl simulain experimen in which daa are simulaed fr prflis f small, medium and large scks. The individual scks in he hree prflis are characerised by varying prbabiliies f nn-rading, which are esimaed using he empirical nn-rading frequencies fr he hree FTSE indices. The simulain resuls sugges ha nn-synchrnus rading leads spillver effecs in reurns, alhugh he simulaed spillver effecs are n as large as hse ha are bserved empirically. Similarly, he simulain evidence suggess ha nn-synchrnus rading cann explain he bserved paern f spillver effecs in vlailiy. We herefre cnclude ha ur empirical resuls are cnsisen wih a marke in which infrmain is firs incrpraed in he prices f large scks befre being impunded in he prices f small scks. The remainder f he paper is rganized as fllws. The fllwing secin describes he daa ha we use in he sudy. Secin 3 gives deails f he empirical mehdlgy. Secin 4 reprs he resuls. Secin 5 presens he resuls f he Mne Carl simulain. Secin 6 ffers a summary and cnclusin.. Daa Descripin The empirical analysis uses cninuusly cmpunded daily sck reurns fr he FTSE 100, FTSE 50 and FTSE Small Cap indices frm 1 January December 00, bained frm Daasream (a al f 4,435 bservains). The FTSE 4

5 100, FTSE 50 and FTSE Small Cap indices are marke-weighed indices ha accun fr apprximaely 85 percen, 1 percen and 3 percen f he FTSE All Share index, respecively, a he end f 00. We use shr hrizn reurns because we wan analyse spillver effecs in bh he mean and vlailiy f he hree series, bu ime series variain in cndiinal vlailiy ends be much weaker fr lnger hrizn reurns. Fr he sub-perid analysis, we spli he full sample in w equal subperids. The firs sub-sample is frm 1 January June 1994, while he secnd sub-sample is frm 1 July December 00. Table 1 reprs summary saisics fr he hree reurn series fr he full sample. Panel A reprs he mean, sandard errr, skewness and excess kursis cefficiens and he Jarque-Bera saisic es he null hyphesis ha reurns are nrmally disribued. All hree series are negaively skewed and highly lepkuric, and he Jarque-Bera saisic rejecs he null hyphesis f nrmaliy very srngly. Panel B f Table 1 reprs he firs fur aucrrelain cefficiens fr reurns and squared reurns fr each index, geher wih Ljung-Bx prmaneau saisics. Fr all hree indices, reurns are serially crrelaed, alhugh he magniude f he serial crrelain decreases wih capialisain. Squared reurns are highly serially crrelaed fr all hree series, indicaing he presence f vlailiy clusering. In cnras wih he paern f serial crrelain in reurns, he magniude f he serial crrelain in squared reurns increases wih capialisain, implying ha ACH effecs are srnger fr large scks han fr small scks. [Table 1] 3. Mehdlgy 3.1 Mdelling he eurns and Vlailiies f he Indices As a benchmark, we firs mdel he dynamic prperies f he reurns and vlailiies f he FTSE 100, FTSE 50 and FTSE Small Cap reurn series wihu spillver effecs. We use he fllwing mulivariae A-GJ-GACH-M mdel fr he hree indices i, j=1,, 3 5

6 4 i = α 0 + n= 1, α + γ h + c OCT 87 + c ASIA 97 + c 3 JAN n + c 4 n MON i ii, + ε 1 (1) h i = β 0 + β 1 i 1 + β ε 1 + λi 1ε d 3 JAN h + d 4 MON I d OCT d ASIA () h ( h h ) = ρ (3) ij, ij ii, jj, where, is he reurn f prfli i in perid, ψ N ( 0, H ) i ε, ψ 1 is he se f 1 all infrmain available a ime 1 and H = ] is he cndiinal cvariance [ h ij, marix. I i 1 is a dummy variable ha is equal ne if he lagged shck reurns, 1, ε is negaive, and zer herwise. OCT87 is a dummy variable ha is equal ne fr bservains beween 19/10/87 and 4/11/87 and zer herwise. ASIA97 is a dummy variables ha is equal ne fr bservains beween 3/10/97 and 8/10/97 and zer herwise. JAN is a dummy variable ha is equal ne fr he firs week in January and zer herwise. Mndays and zer herwise. MON is a dummy variable ha is equal ne fr The A(4) specificain fr he mean equain (1) was chsen n he basis f he Schwarz Bayesian Crierin (SBC) frm a general AMA(p,q) specificain, alhugh he mdel seleced by he Akaike Infrmain Crierin (AIC) led bradly similar empirical resuls. We have specified a GACH-in-mean erm, wih he cndiinal variance f each index included as an explanary variable in he respecive mean equain. This is expli as much infrmain in esimaing expeced reurns, raher han impse a paricular asse pricing resricin, and is cmmn in he lieraure. See, fr example, Hama, Masulis and Ng (1990), Cnrad, Gulekin and Kaul (1991), Ng, Chang and Chu (1991) and Thedssiu and Lee (1993). 6

7 The mdel fr he cndiinal cvariance marix, given by () and (3), is based n he cnsan crrelain (CCO) specificain f he mulivariae GACH mdel f Bllerslev (1990). The mdel specifies he cndiinal variance f each index as a univariae GACH mdel, wih he cndiinal cvariance f any w series i and j deermined by he cndiinal variances, h ii, and h jj,, and he cnsan crrelain cefficien, ρ ij. While here are several mulivariae GACH mdels chse frm, he CCO mdel has he advanage f being parsimnius and hence grealy reduces he cmpuainal effr required esimae he mdel, generally leading mre reliable parameer esimaes. 3 This is paricularly impran in he presen case wing he large number f parameers be esimaed. The GACH(1,1) specificain fr he cndiinal variance in equain () was chsen fr he sake f parsimny. In rder ensure he rbusness f ur resuls, we mdify he CCO mdel in several ways. Firsly, i is well dcumened ha vlailiy respnds asymmerically gd and bad news and, mrever, ha vlailiy spillvers can be significanly undersaed if his asymmeric effec is ignred. 4 T capure he asymmeric effec f news n vlailiy, we use he GJ specificain f he mulivariae GACH mdel and include a dummy variable fr negaive reurn shcks (see Glsen, Jagannahan and unkle, 1993). Secndly, allw fr uliers in he daa, we include dummy variables in bh he reurn and vlailiy equains fr perids f exreme marke mvemens. The large negaive reurns in inernainal equiy markes during he week fllwing he sck marke crash f 19 Ocber 1987 are well dcumened. S is he increase in he cndiinal vlailiy f reurns. 5 Fllwing Aggarwal, Inclan and Leal (1999), we include in he full sample and he firs sub-sample, a dummy variable fr he w weeks fllwing he sck marke crash f We als allw fr he 1997 Asian financial crisis by including in he full sample and he secnd subsample, a dummy variable fr he week ha marked he sar f he crisis (see Wang, u and Firh, 00). Lasly, we als include dummy variables in bh he mean equain and he variance equain fr he well-knwn January and Mnday effecs. Many sudies have shwn ha reurns are sysemaically higher during he firs week 3 See Engle and Krner (1995), Krner and Ng (1998). 4 See Glsen, Jagannahan and unkle (1993), Engle and Ng (1993), Bae and Karlyi (1994), Wang, ui and Firh (00) and Hung, Lee and S (003). 7

8 f January han in her mnhs f he year, and lwer n Mndays han n her days f he week. 6 A number f sudies, including Cnrad, Gulekin and Kaul (1991), have als fund ha here are similar calendar effecs in he vlailiy f reurns. 3. Mdelling Spillver Effecs Beween he Indices T analyse he reurn and vlailiy spillvers beween he FTSE 100, FTSE 50 and FTSE Small Cap indices, we mdify he A-GJ-GACH-M mdel given by (1)-(3) include in he mean and variance equains fr each index, he lagged shcks he means and vlailiies f he her w indices. Specifically, capure spillver effecs in he mean equain fr index we include he firs lag f he reurns f each f he indices i j. T capure spillver effecs in he vlailiy equain fr index we include he firs lag f he squared reurn shcks f each f he indices mdel including spillvers fr indices i, j= 1,, 3 is herefre given by i j. The, = α + α + γ h + c OCT 87 + c ASIA 97 i + c n= 1 MON n + n 3 w j= 1, j i j i ii, j, 1 + ε 1 + c 3 JAN (4) h i = β 0 + β 1hi 1 + β ε 1 + λi I 1ε 1 + d 1OCT87 + d ASIA97 + d 3 JAN + d 4 MON + 3 z j j= 1, j i ε j, 1 (5) h ( h h ) = ρ (6) ij, ij ii, jj, The parameer w i, j measures he parial impac n he reurns f index i f pas reurn shcks f he w remaining indices, while he parameer z, measures he parial i j impac n he vlailiy f index i f pas vlailiy shcks he w remaining indices. We esimae he mulivariae GACH mdel, bh wih and wihu spillver 5 See ll (1988), Schwer (1990), Aggarwal, Inclan and Leal (1999). 6 Fr evidence f he January effec, see, fr example, Tinic and Wes (1984), Laknishk and Smid (1988) and Draper and Paudyal (1997). 8

9 effecs, by quasi-maximum likelihd wih a nrmal cndiinal disribuin (see Bllerslev and Wlridge, 199). We use he BFGS algrihm wih a cnvergence crierin f applied he funcin value. bus errrs are cmpued ha are valid under nn-nrmaliy (see Whie, 198). 4. Empirical esuls 4.1 Mulivariae A(4)-GJ GACH(1,1)-M esuls Table reprs he esimaed parameers f he mulivariae A(4)-GJ- GACH(1,1)-M mdel fr each he hree indices, given by equains (1), () and (3), geher wih Ljung-Bx es saisics fr he sandardized residuals (LB(4)) and he squared sandardized residuals (LB (4)). Fr all hree indices, he sum f he esimaed GACH parameers, β 1 + β, suggess ha vlailiy is sainary bu highly persisen. In paricular, he half-life f vlailiy fr he FTSE 100, FTSE 50 and FTSE Small Cap indices is 0.88 days, 9.74 days and days, respecively. 7 The GACH-in-mean cefficien, γ i, is significanly psiive fr all hree indices, implying ha higher vlailiy is assciaed wih higher expeced reurns, which is cnsisen wih risk aversin. The cefficien f he asymmery erm, λ i, is significanly psiive fr he FTSE 100 index, implying ha bad news has a larger impac n he vlailiy f he FTSE 100 index han gd news des. The asymmery erm is als psiive fr he FTSE 50 and FTSE Small Cap indices, bu n saisically significan. As expeced, he esimaed crrelain cefficiens, amng he hree indices are psiive and highly significan. ρ ij, There is srng evidence f he effec f he Ocber 1987 crash n he reurns and cndiinal variances f he hree indices. In paricular, reurns are very significanly negaive during he crash, and fr he FTSE 50 and FTSE Small Cap indices, vlailiy is significanly higher. The Asian crisis had a significan negaive impac n reurns all hree indices, and a marginally significan psiive impac n vlailiy. The 7 The half-life is cmpued as hi = ln( 1/ ) / ln( β 1 + β + λi / ) under he assumpin ha he reurn disribuin is symmeric. 9

10 January effec is insignifican fr reurns, bu has a psiive impac n vlailiy, which is significan fr he FTSE 50 index, and marginally significan fr he FTSE 100 and FTSE Small Cap indices. The Mnday effec is significanly negaive fr FTSE 100 and FTSE 50 reurns, and marginally significanly negaive fr FTSE Small Cap reurns. Fr vlailiy, he Mnday dummy is significanly negaive fr he FTSE 50 index, and negaive wih marginal significance fr he FTSE 100 index. The LB (4) saisics sugges ha he mulivariae GACH(1,1) specificain successfully capures he serial crrelain in squared reurns fr each f he hree indices. The LB(4) saisics shw ha here is significan serial crrelain in he residuals fr he hree indices. Hwever, i will be seen belw ha his serial crrelain is significanly reduced nce we include reurn and vlailiy spillvers in he mdel. Alernaive AMA specificains f he mean equain (paricularly hse seleced by he AIC, which generally include lnger lags f bh he A and MA cmpnens) failed eliminae his serial crrelain. [Table ] Table 3 reprs he esimaed parameers f he mulivariae A(4)-GJ GACH(1,1)-M mdel wih spillver effecs fr each he hree indices, given by equains (4), (5) and (6). Cmparing Table and Table 3, i can be seen ha he inrducin f he spillver effecs in he mdel generally has nly a small effec n he esimaed parameer values fr he mean and variance equains f he hree indices. Mrever, he inrducin f spillver effecs significanly reduces he serial crrelain in he residuals. The LB(4) saisic is nw insignifican fr he FTSE Small Cap Index, and cnsiderably reduced fr he FTSE 100 and FTSE 50 indices. Again, alernaive AMA specificains f he mean equain failed cmpleely eliminae he remaining serial crrelain. Hwever, he chice f mdel fr he mean reurn fr hese series des n significanly affec he resuls n mean and vlailiy spillvers ha are repred belw, and alers nne f he qualiaive cnclusins. 8 8 esuls bained using alernaive specificains f he mean equain are available frm he auhrs. 10

11 Table 3 shws ha here are very significan reurn and vlailiy spillvers beween he FTSE 100, FTSE 50 and FTSE Small Cap indices. Mrever, hese spillver effecs are highly asymmeric. In paricular, here are significan psiive spillver effecs in reurns frm he FTSE 100 index he FTSE 50 and FTSE Small Cap indices. There is als a marginally significan psiive spillver frm he FTSE 50 index he FTSE Small Cap index. In cnras, here are n saisically significan spillver effecs frm he prflis f smaller scks he prflis f larger scks. Cnsisen wih he findings f previus sudies fr he US cied abve, we herefre find ha here are very significan asymmeric spillver effecs frm he reurns f large scks he reurns f small scks. Fr cndiinal vlailiy, he spillver effecs are mre cmplex. We again find ha here are significan spillver effecs frm he FTSE 100 index bh he FTSE 50 index and he FTSE Small Cap index and frm he FTSE 50 index he FTSE Small Cap index. These findings are cnsisen wih hse f Cnrad, Gulekin and Kaul (1991) fr he US. Hwever, we als find ha here is evidence f feedback in vlailiy frm smaller scks larger scks, wih a significan negaive spillver beween he FTSE 50 index and he FTSE 100 index, implying ha an increase in he vlailiy f he FTSE 50 index is assciaed wih a subsequen decrease in he vlailiy f he FTSE 100 index. There is als a psiive spillver in vlailiy frm he FTSE Small Cap index he FTSE 100 index, and a marginally significan psiive spillver frm he FTSE Small Cap index he FTSE 50 index. In rder shed mre ligh n he bserved spillver paerns, we cnduc he same analysis using each f he w sub-samples. [Table 3] 4. Sub-Perid Analysis Table 4 presens he resuls fr he firs sub-sample, while Table 5 presens he resuls fr he secnd sub-sample. The paern f reurn spillvers fr bh sub-samples are very similar hse repred fr he full sample. We again find ha he spillver effecs in reurns are highly asymmeric in bh sub-samples. There are highly significan psiive spillver effecs in reurns frm he FTSE 100 index bh he 11

12 FTSE 50 and FTSE Small Cap indices. The evidence f asymmery is even mre prnunced fr he secnd sub-sample, wih an addiinal significan psiive reurn spillver frm he FTSE 50 index he FTSE Small Cap index. There are marginally significan negaive spillvers frm he FTSE Small Cap index he FTSE 50 index in he secnd sub-sample, and frm he FTSE 50 index he FTSE 100 index in he firs sub-sample. Fr cndiinal vlailiy, he psiive spillver effecs frm he FTSE 100 index he FTSE 50 index and he FTSE Small Cap index ha are presen in he full sample are als presen in he w sub-samples. The psiive spillver frm he FTSE 50 index he FTSE Small Cap index ha is presen in he full sample is significan fr he secnd sub-sample, bu n fr he firs sub-sample. The psiive spillver effec frm he FTSE Small Cap index he FTSE 100 index ha is presen in he full sample, is marginally significan in he firs sub-sample, bu absen in he secnd subsample. Hwever, in he secnd sub-sample, here is a significanly psiive spillver frm he FTSE Small Cap index he FTSE 50 index ha is nly marginally significan in bh he full sample and he firs sub-sample. The significan negaive spillver frm he FTSE 50 index he FTSE 100 index ha is presen in he full sample is insignifican in bh sub-samples. The resuls f his secin herefre sugges ha he spillver effecs in reurns and vlailiy frm larger sck prflis smaller sck prflis are rbus wih respec he ime-perid cnsidered. The spillvers in bh reurns and vlailiy end be srnger in he secnd sub-sample han he firs sub-sample. Hwever, here remain sme marginally significan feedback effecs in vlailiy frm he prflis f smaller scks he prflis f larger scks, bu hese vary smewha wih he ime-perid cnsidered. The negaive spillver frm he FTSE 50 index he FTSE 100 index is n presen in eiher f he w sub-samples, casing dub n is rbusness and suggesing ha i culd be, sme exen, spurius. [Tables 4 and 5] 1

13 5. The Effec f Nn-synchrnus Trading n eurn and Vlailiy Spillvers Many previus sudies (fr example, L and Mackinlay, 1990a, 1990b) repr evidence ha nn-synchrnus rading can penially induce an asymmery in he ransmissin mechanisms f reurns beween large and small scks. T invesigae he penial effecs f nn-synchrnus rading n ur resuls, we emply he simulain experimens used in Cnrad, Gulekin and Kaul (1991) and Kadlec and Paersn (1999). These simulain experimens are based n he nn-synchrnus rading mdel firs develped by Schles and Williams (1977) and laer generalised by L and MacKinlay (1990a). Suppse ha he unbservable laen cninuusly cmpunded reurns mdel. i, f N securiies are generaed by he fllwing single-facr i, = α i + β i M + ε, i= 1,..., N (7) where M N(0, ) is a zer-mean cndiinally heerscedasic cmmn facr ~ h M, and ε i ~ N(0, h ) is a zer-mean idisyncraic nise erm ha is emprally and, ε crss-secinally independen a all leads and lags. When M is he reurn n he marke prfli, equain (7) represens he marke mdel f Sharpe (1964). We assume ha he cndiinal vlailiy f GACH(1,1) mdel. M is generaed by he fllwing asymmeric h ε (8) M, = a0 + a1hm, 1 + am 1 + a3i 1 M, 1 In rder calibrae his mdel, we esimae i fr he FTSE All Share index fr he full sample perid. This yields parameer esimaes ˆ a =.73*, ˆ1 = a, a ˆ = and a ˆ3 = Using hese parameer esimaes, and seing he iniial cndiinal variance, h M,, he esimaed uncndiinal variance f he FTSE All Share index, we use equain (8) generae he cndiinally heerscedasic facr reurn, M. We hen use equain (7) generae he individual sck reurns, Fr all scks, β i is se equal uniy, and α i is se equal zer. Fllwing Kadlec i. 13

14 and Paersn (1999), in rder esimae he variance f ε, we firs randmly selec 100 scks frm he FTSE All Share index a he end f 00. We regress he daily reurns f each f hese individual scks n a cnsan and he daily reurn n he FTSE All share index. We hen calculae he average variance f he residuals bained frm hese regressins and use his as an esimae f h ε. We nw inrduce nn-synchrnus rading in he simulain mdel. If securiy i rades in perid +1 bu did n rade in perid, is bserved reurn, i 1, +, a + 1 is simply he sum f is laen reurns ha perid and is laen reurns fr all pas cnsecuive perids in which i did n rade. Hence, he bserved reurn,,, is i given by he fllwing schasic prcess. = k= 0 i, X ( k) k, i= 1,..., N (9) where he randm weigh X i, ( k) is an indicar variable ha akes he value 1 when securiy i rades a ime bu has n raded in any f he k previus perids, and akes he value 0 herwise. T simulae he bserved reurn,,, we firs simulae 4435 daily laen reurns,,, i i fr 10 large, 10 medium and 10 small scks. We generae he nn-rading hisry fr each individual sck frm a Bernulli prcess, using he empirical nn-rading frequencies f he FTSE 100, he FTSE 50 and he FTSE Small Cap indices. These empirical nn-rading frequencies are , and , respecively. 9 Once he laen reurns and he nn-rading hisry f large, medium and small scks are generaed, an bserved reurn fr each individual sck is cmpued using equain (9). The daily reurns fr individual small, medium and large scks are hen aggregaed in small, medium, and large prflis respecively. As a benchmark, we als simulae he reurn and vlailiy ransmissins under he assumpin f n nn- 9 These nn-rading frequencies are cmpued frm he daily daa fr he individual scks ha cmprise each f he FTSE 100, FTSE 50 and FTSE Small Cap indices beween 1 January 1986 and 31 December

15 synchrnus rading. In his case, we simply repea he simulain described abve, bu wih he hree nn-rading prbabiliies se zer. The simulains are underaken using 1000 replicains. T examine he reurn ransmissin mechanisms acrss he hree prflis, we esimae he fllwing regressin fr each index i = 1,, 3. γ +, (10) = 0+ γ 11, 1+ γ, 1+ γ 33, 1 u where γ 0 is a cnsan, and γ 1, γ and γ 3 are he cefficiens f he lagged reurns f prflis f he large, medium and small sck prflis respecively. The vlailiy ransmissin mechanisms acrss all hree prflis are invesigaed by esimaing he fllwing regressin. ˆ ω ˆ ˆ ˆ ˆ + (11) u = 0 + ω1u1, 1 + ωu, 1 + ω3u3, 1 + ω4 I 1u 1 v where ω 0 is a cnsan, and ω 1, ω and ω 3 are he cefficiens f he lagged squared reurn shcks f prflis f he large, medium and small sck prflis respecively. These equains are analgus he mulivariae asymmeric GACH mdel wih spillver effecs ha is used in he empirical analysis in he previus secin. Table 6 reprs he resuls fr he reurn ransmissins. Panel A shws evidence f asymmeric reurn spillvers frm larger sck prflis smaller sck prflis when nn-synchrnus rading is allwed fr in he simulain prcess, alhugh here is ne case ha indicaes a reurn spillver frm a smaller sck prfli a larger sck prfli. This asymmery in reurn spillver effecs is cnsisen wih he empirical resuls repred in he previus secin. Hwever, he esimaed crssauregressive parameers in he simulain are cnsiderably lwer han hse bserved in he empirical analysis. When we assume n nn-synchrnus rading in he simulain prcess, hese spillver effecs disappear alms cmpleely. These resuls herefre sugges ha nn-synchrnus rading may explain a prprin f he asymmeric spillver effecs beween he FTSE 100, FTSE 50 and FTSE Small Cap indices, bu is n able accun fr all f i. This is cnsisen wih he findings f 15

16 L and MacKinlay (1990a and 1990b), wh find ha nn-synchrnus rading, while generaing significan reurn spillvers beween large and small scks, is insufficien explain he magniude f lagged crss-crrelains in sck reurns bserved in he US. [Table 6] Table 7 suggess ha nn-synchrnus rading is als unlikely fully explain he bserved spillver effecs in vlailiy beween he FTSE 100, FTSE 50 and FTSE Small Cap indices. When here is n nn-synchrnus rading, here is a symmeric paern f vlailiy spillvers beween he large, medium and small prflis (which arises frm he single facure naure f he simulain mdel). In cnras wih he simulain evidence fr reurn spillvers, he inrducin f nn-synchrnus rading has n disinguishable effec n he paern f spillvers in vlailiy. Furhermre, he esimaed lagged crss-crrelains in squared residuals bserved in he simulain wih nn-synchrnus rading are n significanly differen frm hse bserved in he simulain wih n nn-synchrnus rading. Thus, i is unlikely ha nnsynchrnus rading wuld be able accun fr he asymmeric paern f vlailiy spillvers ha is bserved in pracice. [Table 7] 6. Cnclusin In his paper, we invesigae reurn and vlailiy spillver effecs beween large and small scks in he UK sck marke using he mulivariae A-GJ GACH-M mdel. We find ha he reurns and vlailiies f large scks are impran in predicing he fuure dynamics f smaller scks, bu ha he reurns and vlailiies f smaller scks have much less impac n he fuure dynamics f large scks. Our empirical resuls sugges ha infrmain flw has an influence n he paern f he ransmissin mechanisms beween large and small scks. Marke-wide infrmain is firs incrpraed in he prices f large scks befre being impunded in he prices f small scks. In her wrds, he prices f small scks respnd wih a delay 16

17 he arrival f marke-wide infrmain. Simulain evidence suggess ha nnsynchrnus rading can accun fr sme f he spillver effecs in reurns, bu n all f i. Similarly, he simulain evidence suggess ha nn-synchrnus rading is unlikely accun fr he spillver effecs in vlailiy. The resuls are cnsisen wih previus sudies ha find a similar paern f reurn and vlailiy spillvers fr he US, and are penially useful fr a range f applicains in finance ha rely n frecass f reurns and vlailiies. 17

18 eferences Aggarwal,., C. Inclan, and. Leal (1999), Vlailiy in Emerging Sck Markes, Jurnal f Financial and Quaniaive Analysis, Vl. 34, N. 1, pp Badrinah, S.G., J.. Kale, and T.H. Ne (1995), Of Shepherds, Sheep and he Crss- Aucrrelains in Equiy eurns, eview f Financial Sudies, Vl. 8, N., pp Bae, K.-H., and G.A. Karlyi (1994), Gd News, Bad News and Inernainal Spillvers f Sck eurn Vlailiy beween Japan and he U.S., Pacific-Basin Finance Jurnal, Vl., pp Bllerslev, T. (1990), Mdelling he Cherence in Shr un Nminal Exchange aes: A Mulivariae Generalized ACH Mdel, eview f Ecnmics and Saisics, Vl. 7, pp Bllerslev, T.,.Y. Chu, and K.F. Krner (199), ACH Mdelling in Finance: A eview f Thery and Empirical Evidence, Jurnal f Ecnmerics, Vl. 5, pp Bllerslev, T. and J. Wldridge (199), Quasi-Maximum Likelihd Esimain and Inference in Dynamic Mdels wih Time-Varying Cvariances, Ecnmeric eviews, Vl. 11, pp Budukh, J., M. ichardsn, and. Whielaw (1994), A Tale f Three Schls: Insighs n Aucrrelains f Shr-Hrizn eurns, eview f Financial Sudies, Vl. 7, pp Campbell, J., A. L and A. MacKinlay (1997), The Ecnmerics f Financial Markes, Princen Universiy Press, New Jersey. Chan, K. (1993), Imperfec Infrmain and Crss-aucrrelain amng Sck Prices Jurnal f Finance, Vl. 48, pp Cnrad, J., M. Gulekin, and G. Kaul (1991), Asymmeric Predicabiliy f Cndiinal Variances, eview f Financial Sudies, Vl. 4, pp Draper, P., and K. Paudyal (1997), Micrsrucure and Seasnaliy in he UK Equiy Marke, Jurnal f Business Finance and Accuning, Vl. 4, pp Engle,.F., and K.F. Krner (1995), Mulivariae Simulaneus Generalized ACH, Ecnmeric Thery, Vl. 11, N. 1, pp Engle,.F., and V.K. Ng (1993), Measuring and Tesing he Impac f News n Vlailiy, Jurnal f Finance, V. 48, N. 5, pp Glsen, L.,. Jagannahan, and D. unkle (1993), Seasn Paerns in he Vlailiy f Sck Index Excess eurns, Jurnal f Finance, Vl. 48, pp

19 Grinbla, M., S. Timan, and. Wermers (1995), Mmenum Invesmen Sraegies, Prfli Perfrmance, and Herding: A Sudy f Muual Fund Behavir, American Ecnmic eview, Vl. 85, pp Hama, Y.,.W. Masulis, and V.K. Ng (1990), Crrelains in Price Changes and Vlailiy acrss Inernainal Sck Markes, The eview f Financial Sudies, Vl. 3, N., pp Hasan, I., and B.B. Francis (1998), Macrecnmic Facrs and he Asymmeric Predicabiliy f Cndiinal Variances, Eurpean Financial Managemen, Vl. 4, N., pp Hung, M.W., C.F. Lee, and L.C. S (003), The Impac f Freign-lised Single Sck Fuures n he Dmesic Underlying Sck Markes, Applied Ecnmics Leers, Vl. 10, N.9, pp Kadlec, G.B., and D.M. Paersn (1999), A Transacins Daa Analysis f Nnsynchrnus Trading, The eview f Financial Sudies, Vl. 1, N. 3, pp Keim, D., and A. Madhavan (1995), Anamy f he Trading Prcess: Empirical Evidence n he Behavir f Insiuinal Traders, Jurnal f Financial Ecnmics, Vl. 37, pp Krner, K., and V.K. Ng (1998), Mdeling Asymmeric Cmvemen f Asse eurns, eview f Financial Sudies, Vl. 11, N. 4. Laknishk, J., and S. Smid (1988), Are Seasnal Anmalies eal?: A Niney Year Perspecive, eview f Financial Sudies, Vl. 1, pp L, A. W., and A. C. MacKinlay (1990a), An Ecnmeric Analysis f Nnsynchrnus Trading, Jurnal f Ecnmerics, Vl. 45, pp L, A. W., and A. C. MacKinlay (1990b), When are Cnsrarian Prfis due Shck Marke Overreacin?, eview f Financial Sudies, Vl. 3, pp McQueen, G., M. Pinegar, and S. Thrley (1996), Delayed eacin Gd News and he Crss-Aucrrelain f Prfli eurns, Jurnal f Finance, Vl. 51, N. 3, pp Mech, T. (1993), Prfli Aucrrelain, Jurnal f Financial Ecnmics, Vl. 34, pp Ng, V.K.,.P. Chang and. Chu (1991), An Examinain f he Behavir f Inernainal Sck Marke Vlailiy, in: S. Ghn hee and sia P. Chang, eds., Pacific-Basin Capial Marke esearch, Vl. (Nrh-Hlland, Amserdam), Pp ll,. (1988), The Inernainal Crash f Ocber 1987, Financial Analyss Jurnal, Sepember-Ocber, pp

20 ss, S.A. (1989), Infrmain and Vlailiy: The N-Arbirage Maringale Apprach Timing and esluin Irrelevancy, Jurnal f Finance, Vl. 44, pp Schles, M., and J. Williams (1977), Esimaing Beas frm Nnsynchrnus Daa, Jurnal f Financial Ecnmics, Vl. 5, pp Schwer, G.W. (1990), Sck Vlailiy and he Crash f 87, The eview f Financial Sudies, Vl. 3, N. 1, pp Sharpe, W.F. (Sep. 1964), Capial Asse Prices: A Thery f Marke Equilibrium under Cndiins f isk, Jurnal f Finance, pp Thedssiu, P. and U. Lee (1993), Mean and Vlailiy Spillvers acrss Majr Nainal Sck Markes: Furher Empirical Evidence, Jurnal f Financial esearch, Vl. 16, N. 4, pp Tinic, S. M. and.. Wes (1984), isk and eurn: January vs he es f he Year, Jurnal f Financial Ecnmics, Vl. 13, pp Wang, S.S., O.M. u and M. Firh (00), eurn and Vlailiy Behavir f Dually-raded Scks: he Case f Hng Kng, Jurnal f Inernainal Mney and Finance, Vl. 1, pp Whie, H., 198, Maximum Likelihd Esimain f Misspecified Mdels, Ecnmerica 50,

21 Table 1 Descripive Saisics and Aucrrelains Panel A: Descripive Saisics Index Mean S Dev Skewness Kursis JB Saisic FTSE ** FTSE ** FTSE SC ** Panel B: Aucrrelains FTSE 100 FTSE 50 FTSE SC FTSE 100 FTSE 50 FTSE SC ρ ** 0.** 0.30** 0.51** 0.35** 0.9** ρ -0.04** 0.1** 0.0** 0.9** 0.1** 0.16** ρ -0.04** 0.08** 0.18** 0.18** 0.14** 0.1** 3 ρ ** 0.14** 0.0** 0.18** 0.34** 0.5** LB(4) 30.18** ** 913.3** 1,791.39** 1,335.64** ** Nes: Panel A reprs he mean, sandard deviain and skewness and excess kursis cefficiens, and he Jarque-Bera es saisic fr nrmaliy. Panel B reprs he firs fur aucrrelains fr he reurns and squared reurns f each index and furh-rder Ljung-Bx saisics. * and ** dene saisical significance a he 5% level and he 1% level respecively. 1

22 Table The Mulivariae A(4)-GJ GACH(1,1)-M Mdel FTSE 100 FTSE 50 FTSE Small Cap Ceff -sa Ceff -sa Ceff -sa α α ** ** ** α ** ** α ** ** α ** ** γ i * * ** c ** ** ** c ** ** * c c ** ** β 0 x ** ** * β ** ** ** β ** ** ** λ i ** d 1x * * d x d 3x ** d 4x * ρ FTSE100,FTSE ** ρ FTSE100,FTSESC ** ρ FTSE50,FTSESC ** LB(4) [0.00] [0.00] [0.00] LB (4) [0.8].5457 [0.64] [0.9] Nes: The able reprs he esimain fr he mulivariae A(4)-GJ GACH(1,1)-M mdel given by 4 = α i,0 + α i, n n + γ ihii, + c1oct 87 + c ASIA 97 + ci,3jan + c4mon + ε n= 1 hi = β 0 + β1hi 1 + βε 1+ λi I 1ε 1 + d1oct87 + d ASIA97 + d3jan + d 4MON h = ρ ( h h ) ij, ij i jj, -saisics are in parenhesis. * and ** dene saisical significance a he 5% level and he 1% level respecively. LB(4) and LB (4) are he furh-rder Ljung-Bx saisics fr sandardized residuals and squared sandardized residuals, respecively. The p-values f hese saisics are repred in parenheses.

23 Table 3 The Mulivariae A(4)-GJ GACH(1,1)-M Mdel wih Spillvers FTSE 100 FTSE 50 FTSE Small Cap Ceff -sa Ceff -sa Ceff -sa α * α ** ** α ** ** α * * ** α ** ** γ i ** ** ** c ** ** ** c ** ** * c c ** w FTSE ** ** w FTSE w FTSESC β 0 x ** ** β ** ** ** β ** ** ** λ i ** d 1x d x * * d 3x * d 4x * * z FTSE ** ** z FTSE ** * z FTSESC * ρ FTSE100,FTSE ** ρ FTSE100,FTSESC ** ρ FTSE50,FTSESC ** LB(4) [0.03] [0.00] [0.17] LB (4) [0.74] 1.80 [0.87] [0.88] Nes: The able reprs he esimain fr he mulivariae A(4)-GJ GACH(1,1)-M mdel wih spillver effecs, given by 4 3 = 0 + α n n + γ ihii, + c1oct + ci, ASIA 97 + ci,3jan + ci,4mon + w j n= 1 j= 1, j i α 87 + ε 3 1hi 1 + βε 1 + λii 1ε 1 + d1oct87 + d ASIA + d3jan + d4mon + z j j= 1, j i h, = β,0 + β 97 ii h i = ρ ( h h ) ij, ij i jj, -saisics are in parenhesis. * and ** dene saisical significance a he 5% level and he 1% level respecively. LB(4) and LB (4) are he furh-rder Ljung-Bx saisics fr sandardized residuals and squared sandardized residuals, respecively. The p-values f hese saisics are repred in parenheses. j, 1 ε j, 1 3

24 Table 4 The Mulivariae A(4)-GJ GACH(1,1)-M Mdel wih Spillvers ver he perid: 1 s Jan h Jun 1994 FTSE 100 FTSE 50 FTSE Small Cap Ceff -sa Ceff -sa Ceff -sa α α ** * α * * α * * ** α ** ** γ i c * ** ** c c ** ** * w FTSE ** ** w FTSE w FTSESC β 0 x ** ** * β ** ** ** β ** * * λ i d 1x * * d 3x d 4x z FTSE ** ** z FTSE z FTSESC ρ FTSE100,FTSE ** ρ FTSE100,FTSESC ** ρ FTSE50,FTSESC ** LB(4) 5.44 [0.5] [0.05] [0.03] LB (4).064 [0.7] 1.84 [0.86] [0.94] Nes: The able reprs he esimain fr he mulivariae A(4)-GJ GACH(1,1)-M mdel wih spillver effecs, given by 4 3 = α i,0 + α i, n n + γ ihii, + ci,1oct 87 + c3jan + c 4MON + wi, j j, 1 + ε i, n= 1 j= 1, j i 3 1hi 1 + βε 1 + λii 1ε 1 + d1oct + d3jan + d4mon + z j j= 1, j i hi = β0 + β 87 h = ρ ( h h ) ij, ij i jj, -saisics are in parenhesis. * and ** dene saisical significance a he 5% level and he 1% level respecively. LB(4) and LB (4) are he furh-rder Ljung-Bx saisics fr sandardized residuals and squared sandardized residuals, respecively. The p-values f hese saisics are repred in parenheses. ε j, 1 4

25 Table 5 The Mulivariae A(4)-GJ GACH(1,1)-M Mdel wih Spillvers ver he perid: 1 s Jul s Dec 00 FTSE 100 FTSE 50 FTSE Small Cap Ceff -sa Ceff -sa Ceff -sa α * α ** ** ** α ** ** ** α ** * ** α ** ** γ i * ** c ** ** * c * c w FTSE ** ** w FTSE * w FTSESC β 0 x ** ** * β ** ** ** β ** ** ** λ i ** ** d x ** ** d 3x d 4x ** ** z FTSE ** * z FTSE ** z FTSESC * - - ρ FTSE100,FTSE ** ρ FTSE100,FTSESC ** ρ FTSE50,FTSESC ** LB(4) [0.18] [0.0] [0.40] LB (4) [0.5] [0.97] [0.54] Nes: The able reprs he esimain fr he mulivariae A(4)-GJ GACH(1,1)-M mdel wih spillver effecs, given by 4 3 = α 0 + α i, n n + γ ihi + c ASIA 97 + ci,3jan + c 4MON + w j j, 1 + ε n= 1 j= 1, j i 3 1hi 1 + βε 1 + λii 1ε 1 + d ASIA + d3jan + d4mon + z j j= 1, j i hi = β0 + β 97 h = ρ ( h h ) ij, ij i jj, -saisics are in parenhesis. * and ** dene saisical significance a he 5% level and he 1% level respecively. LB(4) and LB (4) are he furh-rder Ljung-Bx saisics fr sandardized residuals and squared sandardized residuals, respecively. The p-values f hese saisics are repred in parenheses. ε j, 1 5

26 Table 6 Simulain esuls fr Nn-Synchrnus rading: eurns Panel A: Nn-synchrnus Trading, 1 1 3, 1 1, (0.81) , (-1.0) (-1.43), (14.49)** (5.30)** (4.64)** 3, (19.80)** (6.18)** (-1.1) Panel B: Synchrnus Trading, 1 1 3, 1 1, (-0.1) , (0.08) (0.47), (0.64) (-0.41) (0.18) 3, (0.73) (-0.86) (-0.51) Nes: 1,,, and are he simulaed bserved reurns f large, medium and small sck 3, prflis respecively. The able reprs he average cefficiens in he regressin = γ 0+ γ 11, 1+ γ, 1+ γ 33, 1+ u fr each index i = 1,, 3. Fr he nn-synchrnus rading case, he nn-rading prbabiliies are se he empirical nn-rading frequencies f , and Fr he synchrnus rading case, he nn-rading prbabiliies are se equal zer. The simulain is based n 1000 replicains. -saisics are repred in parenheses. * and ** dene saisical significance a he 5% level and he 1% level respecively. 6

27 Table 7 Simulain esuls fr Nn-Synchrnus Trading: Vlailiy Panel A: Nn-synchrnus Trading u ˆ1, u ˆ, u ˆ3, u ˆ1, 1 u ˆ, 1 u ˆ3, (31.31)** (4.67)** (15.5)** (34.88)** (40.94)** (15.68)** (5.96)** (34.44)** (5.41)** Panel B: Synchrnus Trading u ˆ1, u ˆ, u ˆ3, u ˆ1, 1 u ˆ, 1 u ˆ3, (31.81)** (4.06)** (15.79)** (3.99)** (43.41)** (16.0)** (5.8)** (34.05)** (11.55)** Nes: u ˆ, uˆ and u are he simulaed squared residuals f large, medium and small sck ˆ 1,, 3, u = 0 1 1, 1, 1 3 3, prflis respecively. The able reprs he average cefficiens in he regressin ˆ ω + ω uˆ + ω uˆ + ω uˆ + ω I uˆ + v fr each index i = 1,, 3. Fr he nnsynchrnus rading case, he nn-rading prbabiliies are se he empirical nn-rading frequencies f , and Fr he synchrnus rading case, he nn-rading prbabiliies are se equal zer. The simulain is based n 1000 replicains. -saisics are repred in parenheses. * and ** dene saisical significance a he 5% level and he 1% level respecively. 7

Brace-Gatarek-Musiela model

Brace-Gatarek-Musiela model Chaper 34 Brace-Gaarek-Musiela mdel 34. Review f HJM under risk-neural IP where f ( T Frward rae a ime fr brrwing a ime T df ( T ( T ( T d + ( T dw ( ( T The ineres rae is r( f (. The bnd prices saisfy

More information

GMM Estimation of the Number of Latent Factors

GMM Estimation of the Number of Latent Factors GMM Esimain f he Number f aen Facrs Seung C. Ahn a, Marcs F. Perez b March 18, 2007 Absrac We prpse a generalized mehd f mmen (GMM) esimar f he number f laen facrs in linear facr mdels. he mehd is apprpriae

More information

PRINCE SULTAN UNIVERSITY Department of Mathematical Sciences Final Examination Second Semester (072) STAT 271.

PRINCE SULTAN UNIVERSITY Department of Mathematical Sciences Final Examination Second Semester (072) STAT 271. PRINCE SULTAN UNIVERSITY Deparmen f Mahemaical Sciences Final Examinain Secnd Semeser 007 008 (07) STAT 7 Suden Name Suden Number Secin Number Teacher Name Aendance Number Time allwed is ½ hurs. Wrie dwn

More information

Section 12 Time Series Regression with Non- Stationary Variables

Section 12 Time Series Regression with Non- Stationary Variables Secin Time Series Regressin wih Nn- Sainary Variables The TSMR assumpins include, criically, he assumpin ha he variables in a regressin are sainary. Bu many (ms?) ime-series variables are nnsainary. We

More information

and Sun (14) and Due and Singlen (19) apply he maximum likelihd mehd while Singh (15), and Lngsa and Schwarz (12) respecively emply he hreesage leas s

and Sun (14) and Due and Singlen (19) apply he maximum likelihd mehd while Singh (15), and Lngsa and Schwarz (12) respecively emply he hreesage leas s A MONTE CARLO FILTERING APPROACH FOR ESTIMATING THE TERM STRUCTURE OF INTEREST RATES Akihik Takahashi 1 and Seish Sa 2 1 The Universiy f Tky, 3-8-1 Kmaba, Megur-ku, Tky 153-8914 Japan 2 The Insiue f Saisical

More information

10.7 Temperature-dependent Viscoelastic Materials

10.7 Temperature-dependent Viscoelastic Materials Secin.7.7 Temperaure-dependen Viscelasic Maerials Many maerials, fr example plymeric maerials, have a respnse which is srngly emperaure-dependen. Temperaure effecs can be incrpraed in he hery discussed

More information

MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.265/15.070J Fall 2013 Lecture 15 10/30/2013. Ito integral for simple processes

MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.265/15.070J Fall 2013 Lecture 15 10/30/2013. Ito integral for simple processes MASSACHUSETTS INSTITUTE OF TECHNOLOGY 6.65/15.7J Fall 13 Lecure 15 1/3/13 I inegral fr simple prcesses Cnen. 1. Simple prcesses. I ismery. Firs 3 seps in cnsrucing I inegral fr general prcesses 1 I inegral

More information

An application of nonlinear optimization method to. sensitivity analysis of numerical model *

An application of nonlinear optimization method to. sensitivity analysis of numerical model * An applicain f nnlinear pimizain mehd sensiiviy analysis f numerical mdel XU Hui 1, MU Mu 1 and LUO Dehai 2 (1. LASG, Insiue f Amspheric Physics, Chinese Academy f Sciences, Beijing 129, China; 2. Deparmen

More information

Productivity changes of units: A directional measure of cost Malmquist index

Productivity changes of units: A directional measure of cost Malmquist index Available nline a hp://jnrm.srbiau.ac.ir Vl.1, N.2, Summer 2015 Jurnal f New Researches in Mahemaics Science and Research Branch (IAU Prduciviy changes f unis: A direcinal measure f cs Malmquis index G.

More information

independenly fllwing square-r prcesses, he inuiive inerpreain f he sae variables is n clear, and smeimes i seems dicul nd admissible parameers fr whic

independenly fllwing square-r prcesses, he inuiive inerpreain f he sae variables is n clear, and smeimes i seems dicul nd admissible parameers fr whic A MONTE CARLO FILTERING APPROACH FOR ESTIMATING THE TERM STRUCTURE OF INTEREST RATES Akihik Takahashi 1 and Seish Sa 2 1 The Universiy f Tky, 3-8-1 Kmaba, Megur-ku, Tky 153-8914 Japan 2 The Insiue f Saisical

More information

GAMS Handout 2. Utah State University. Ethan Yang

GAMS Handout 2. Utah State University. Ethan Yang Uah ae Universiy DigialCmmns@UU All ECAIC Maerials ECAIC Repsiry 2017 GAM Handu 2 Ehan Yang yey217@lehigh.edu Fllw his and addiinal wrs a: hps://digialcmmns.usu.edu/ecsaic_all Par f he Civil Engineering

More information

The Impact of Nonresponse Bias on the Index of Consumer Sentiment. Richard Curtin, Stanley Presser, and Eleanor Singer 1

The Impact of Nonresponse Bias on the Index of Consumer Sentiment. Richard Curtin, Stanley Presser, and Eleanor Singer 1 The Impac f Nnrespnse Bias n he Index f Cnsumer Senimen Richard Curin, Sanley Presser, and Eleanr Singer 1 Inrducin A basic ene f survey research is he abslue preference fr high respnse raes. A lw respnse

More information

5.1 Angles and Their Measure

5.1 Angles and Their Measure 5. Angles and Their Measure Secin 5. Nes Page This secin will cver hw angles are drawn and als arc lengh and rains. We will use (hea) represen an angle s measuremen. In he figure belw i describes hw yu

More information

An Introduction to Wavelet Analysis. with Applications to Vegetation Monitoring

An Introduction to Wavelet Analysis. with Applications to Vegetation Monitoring An Inrducin Wavele Analysis wih Applicains Vegeain Mniring Dn Percival Applied Physics Labrary, Universiy f Washingn Seale, Washingn, USA verheads fr alk available a hp://saff.washingn.edu/dbp/alks.hml

More information

DEPARTMENT OF ECONOMICS AND FINANCE COLLEGE OF BUSINESS AND ECONOMICS UNIVERSITY OF CANTERBURY CHRISTCHURCH, NEW ZEALAND

DEPARTMENT OF ECONOMICS AND FINANCE COLLEGE OF BUSINESS AND ECONOMICS UNIVERSITY OF CANTERBURY CHRISTCHURCH, NEW ZEALAND DEPARTMENT OF ECONOMICS AND FINANCE COLLEGE OF BUSINESS AND ECONOMICS UNIVERSITY OF CANTERBURY CHRISTCHURCH, NEW ZEALAND Asymmery and Leverage in Condiional Volailiy Models Michael McAleer WORKING PAPER

More information

Practical Considerations when Estimating in the Presence of Autocorrelation

Practical Considerations when Estimating in the Presence of Autocorrelation CS-BIGS (): -7 008 CS-BIGS hp://www.benley.edu/csbigs/vl-/jaggia.pdf Pracical Cnsiderains when Esimaing in he Presence f Aucrrelain Sanjiv Jaggia Orfalea Cllege f Business, Cal Ply, USA Alisn Kelly-Hawke

More information

The Components of Vector B. The Components of Vector B. Vector Components. Component Method of Vector Addition. Vector Components

The Components of Vector B. The Components of Vector B. Vector Components. Component Method of Vector Addition. Vector Components Upcming eens in PY05 Due ASAP: PY05 prees n WebCT. Submiing i ges yu pin ward yur 5-pin Lecure grade. Please ake i seriusly, bu wha cuns is wheher r n yu submi i, n wheher yu ge hings righ r wrng. Due

More information

AP Physics 1 MC Practice Kinematics 1D

AP Physics 1 MC Practice Kinematics 1D AP Physics 1 MC Pracice Kinemaics 1D Quesins 1 3 relae w bjecs ha sar a x = 0 a = 0 and mve in ne dimensin independenly f ne anher. Graphs, f he velciy f each bjec versus ime are shwn belw Objec A Objec

More information

Solutions to Odd Number Exercises in Chapter 6

Solutions to Odd Number Exercises in Chapter 6 1 Soluions o Odd Number Exercises in 6.1 R y eˆ 1.7151 y 6.3 From eˆ ( T K) ˆ R 1 1 SST SST SST (1 R ) 55.36(1.7911) we have, ˆ 6.414 T K ( ) 6.5 y ye ye y e 1 1 Consider he erms e and xe b b x e y e b

More information

Comparing Means: t-tests for One Sample & Two Related Samples

Comparing Means: t-tests for One Sample & Two Related Samples Comparing Means: -Tess for One Sample & Two Relaed Samples Using he z-tes: Assumpions -Tess for One Sample & Two Relaed Samples The z-es (of a sample mean agains a populaion mean) is based on he assumpion

More information

Kinematics Review Outline

Kinematics Review Outline Kinemaics Review Ouline 1.1.0 Vecrs and Scalars 1.1 One Dimensinal Kinemaics Vecrs have magniude and direcin lacemen; velciy; accelerain sign indicaes direcin + is nrh; eas; up; he righ - is suh; wes;

More information

THE DETERMINATION OF CRITICAL FLOW FACTORS FOR NATURAL GAS MIXTURES. Part 3: The Calculation of C* for Natural Gas Mixtures

THE DETERMINATION OF CRITICAL FLOW FACTORS FOR NATURAL GAS MIXTURES. Part 3: The Calculation of C* for Natural Gas Mixtures A REPORT ON THE DETERMINATION OF CRITICAL FLOW FACTORS FOR NATURAL GAS MIXTURES Par 3: The Calculain f C* fr Naural Gas Mixures FOR NMSPU Deparmen f Trade and Indusry 151 Buckingham Palace Rad Lndn SW1W

More information

Visco-elastic Layers

Visco-elastic Layers Visc-elasic Layers Visc-elasic Sluins Sluins are bained by elasic viscelasic crrespndence principle by applying laplace ransfrm remve he ime variable Tw mehds f characerising viscelasic maerials: Mechanical

More information

Financial Econometrics Jeffrey R. Russell Midterm Winter 2009 SOLUTIONS

Financial Econometrics Jeffrey R. Russell Midterm Winter 2009 SOLUTIONS Name SOLUTIONS Financial Economerics Jeffrey R. Russell Miderm Winer 009 SOLUTIONS You have 80 minues o complee he exam. Use can use a calculaor and noes. Try o fi all your work in he space provided. If

More information

Licenciatura de ADE y Licenciatura conjunta Derecho y ADE. Hoja de ejercicios 2 PARTE A

Licenciatura de ADE y Licenciatura conjunta Derecho y ADE. Hoja de ejercicios 2 PARTE A Licenciaura de ADE y Licenciaura conjuna Derecho y ADE Hoja de ejercicios PARTE A 1. Consider he following models Δy = 0.8 + ε (1 + 0.8L) Δ 1 y = ε where ε and ε are independen whie noise processes. In

More information

Convex Stochastic Duality and the Biting Lemma

Convex Stochastic Duality and the Biting Lemma Jurnal f Cnvex Analysis Vlume 9 (2002), N. 1, 237 244 Cnvex Schasic Dualiy and he Biing Lemma Igr V. Evsigneev Schl f Ecnmic Sudies, Universiy f Mancheser, Oxfrd Rad, Mancheser, M13 9PL, UK igr.evsigneev@man.ac.uk

More information

XIV Encuentro de Economía Pública Santander, 1 y 2 de febrero de 2007

XIV Encuentro de Economía Pública Santander, 1 y 2 de febrero de 2007 IV Encuenr de Ecnmía Pública Sanander y 2 de febrer de 2007 DOES CORRUPTION AFFECT EFFICIENC AND PRODUCTIVIT CHANGE? AN AGGREGATE FRONTIER ANALSIS SALINAS-JIMÉNEZ Mª del Mar Insiu de Esudis Fiscales and

More information

Asymmetry and Leverage in Conditional Volatility Models*

Asymmetry and Leverage in Conditional Volatility Models* Asymmery and Leverage in Condiional Volailiy Models* Micael McAleer Deparmen of Quaniaive Finance Naional Tsing Hua Universiy Taiwan and Economeric Insiue Erasmus Scool of Economics Erasmus Universiy Roerdam

More information

Granger Causality Among Pre-Crisis East Asian Exchange Rates. (Running Title: Granger Causality Among Pre-Crisis East Asian Exchange Rates)

Granger Causality Among Pre-Crisis East Asian Exchange Rates. (Running Title: Granger Causality Among Pre-Crisis East Asian Exchange Rates) Granger Causaliy Among PreCrisis Eas Asian Exchange Raes (Running Tile: Granger Causaliy Among PreCrisis Eas Asian Exchange Raes) Joseph D. ALBA and Donghyun PARK *, School of Humaniies and Social Sciences

More information

Estimation of euro currency in circulation outside the euro area 1

Estimation of euro currency in circulation outside the euro area 1 EXTERNAL STATISTICS DIVISION ECB-PUBLIC 6 April 2017 ETS/2017/091 Esimain f er crrency in circlain side he er area 1 1. Inrdcin Recen empirical evidence n crrency in circlain has shwn a significan incnsisency

More information

Diebold, Chapter 7. Francis X. Diebold, Elements of Forecasting, 4th Edition (Mason, Ohio: Cengage Learning, 2006). Chapter 7. Characterizing Cycles

Diebold, Chapter 7. Francis X. Diebold, Elements of Forecasting, 4th Edition (Mason, Ohio: Cengage Learning, 2006). Chapter 7. Characterizing Cycles Diebold, Chaper 7 Francis X. Diebold, Elemens of Forecasing, 4h Ediion (Mason, Ohio: Cengage Learning, 006). Chaper 7. Characerizing Cycles Afer compleing his reading you should be able o: Define covariance

More information

A Specification Test for Linear Dynamic Stochastic General Equilibrium Models

A Specification Test for Linear Dynamic Stochastic General Equilibrium Models Journal of Saisical and Economeric Mehods, vol.1, no.2, 2012, 65-70 ISSN: 2241-0384 (prin), 2241-0376 (online) Scienpress Ld, 2012 A Specificaion Tes for Linear Dynamic Sochasic General Equilibrium Models

More information

CHAPTER 7 CHRONOPOTENTIOMETRY. In this technique the current flowing in the cell is instantaneously stepped from

CHAPTER 7 CHRONOPOTENTIOMETRY. In this technique the current flowing in the cell is instantaneously stepped from CHAPTE 7 CHONOPOTENTIOMETY In his echnique he curren flwing in he cell is insananeusly sepped frm zer sme finie value. The sluin is n sirred and a large ecess f suppring elecrlye is presen in he sluin;

More information

Microwave Engineering

Microwave Engineering Micrwave Engineering Cheng-Hsing Hsu Deparmen f Elecrical Engineering Nainal Unied Universiy Ouline. Transmissin ine Thery. Transmissin ines and Waveguides eneral Sluins fr TEM, TE, and TM waves ; Parallel

More information

Dynamic Econometric Models: Y t = + 0 X t + 1 X t X t k X t-k + e t. A. Autoregressive Model:

Dynamic Econometric Models: Y t = + 0 X t + 1 X t X t k X t-k + e t. A. Autoregressive Model: Dynamic Economeric Models: A. Auoregressive Model: Y = + 0 X 1 Y -1 + 2 Y -2 + k Y -k + e (Wih lagged dependen variable(s) on he RHS) B. Disribued-lag Model: Y = + 0 X + 1 X -1 + 2 X -2 + + k X -k + e

More information

Vectorautoregressive Model and Cointegration Analysis. Time Series Analysis Dr. Sevtap Kestel 1

Vectorautoregressive Model and Cointegration Analysis. Time Series Analysis Dr. Sevtap Kestel 1 Vecorauoregressive Model and Coinegraion Analysis Par V Time Series Analysis Dr. Sevap Kesel 1 Vecorauoregression Vecor auoregression (VAR) is an economeric model used o capure he evoluion and he inerdependencies

More information

Time series Decomposition method

Time series Decomposition method Time series Decomposiion mehod A ime series is described using a mulifacor model such as = f (rend, cyclical, seasonal, error) = f (T, C, S, e) Long- Iner-mediaed Seasonal Irregular erm erm effec, effec,

More information

EXCHANGE RATE ECONOMICS LECTURE 3 ASYMMETRIC INFORMATION AND EXCHANGE RATES. A. Portfolio Shifts Model and the Role of Order Flow

EXCHANGE RATE ECONOMICS LECTURE 3 ASYMMETRIC INFORMATION AND EXCHANGE RATES. A. Portfolio Shifts Model and the Role of Order Flow EXCHANGE RATE ECONOMICS LECTURE 3 ASYMMETRIC INFORMATION AND EXCHANGE RATES A. Porfolio Shifs Model and he Role of Order Flow Porfolio shifs by public cause exchange rae change no common knowledge when

More information

ACE 564 Spring Lecture 7. Extensions of The Multiple Regression Model: Dummy Independent Variables. by Professor Scott H.

ACE 564 Spring Lecture 7. Extensions of The Multiple Regression Model: Dummy Independent Variables. by Professor Scott H. ACE 564 Spring 2006 Lecure 7 Exensions of The Muliple Regression Model: Dumm Independen Variables b Professor Sco H. Irwin Readings: Griffihs, Hill and Judge. "Dumm Variables and Varing Coefficien Models

More information

DEPARTMENT OF STATISTICS

DEPARTMENT OF STATISTICS A Tes for Mulivariae ARCH Effecs R. Sco Hacker and Abdulnasser Haemi-J 004: DEPARTMENT OF STATISTICS S-0 07 LUND SWEDEN A Tes for Mulivariae ARCH Effecs R. Sco Hacker Jönköping Inernaional Business School

More information

CALENDAR ANOMALIES AND CAPITAL MARKET EFFICIENCY: LISTED PROPERTY TRUST INVESTMENT STRATEGIES

CALENDAR ANOMALIES AND CAPITAL MARKET EFFICIENCY: LISTED PROPERTY TRUST INVESTMENT STRATEGIES CALENDAR ANOMALIES AND CAPITAL MARKET EFFICIENCY: LISTED PROPERTY TRUST INVESTMENT STRATEGIES ABSTRACT VINCENT PENG Universiy of Wesern Sydney This sudy focuses on he efficien marke hypohesis (EMH) and

More information

Coherent PSK. The functional model of passband data transmission system is. Signal transmission encoder. x Signal. decoder.

Coherent PSK. The functional model of passband data transmission system is. Signal transmission encoder. x Signal. decoder. Cheren PSK he funcinal mdel f passand daa ransmissin sysem is m i Signal ransmissin encder si s i Signal Mdular Channel Deecr ransmissin decder mˆ Carrier signal m i is a sequence f syml emied frm a message

More information

Unit-I (Feedback amplifiers) Features of feedback amplifiers. Presentation by: S.Karthie, Lecturer/ECE SSN College of Engineering

Unit-I (Feedback amplifiers) Features of feedback amplifiers. Presentation by: S.Karthie, Lecturer/ECE SSN College of Engineering Uni-I Feedback ampliiers Feaures eedback ampliiers Presenain by: S.Karhie, Lecurer/ECE SSN Cllege Engineering OBJECTIVES T make he sudens undersand he eec negaive eedback n he llwing ampliier characerisics:

More information

Volatility. Many economic series, and most financial series, display conditional volatility

Volatility. Many economic series, and most financial series, display conditional volatility Volailiy Many economic series, and mos financial series, display condiional volailiy The condiional variance changes over ime There are periods of high volailiy When large changes frequenly occur And periods

More information

A Dynamic Model of Economic Fluctuations

A Dynamic Model of Economic Fluctuations CHAPTER 15 A Dynamic Model of Economic Flucuaions Modified for ECON 2204 by Bob Murphy 2016 Worh Publishers, all righs reserved IN THIS CHAPTER, OU WILL LEARN: how o incorporae dynamics ino he AD-AS model

More information

Tourism forecasting using conditional volatility models

Tourism forecasting using conditional volatility models Tourism forecasing using condiional volailiy models ABSTRACT Condiional volailiy models are used in ourism demand sudies o model he effecs of shocks on demand volailiy, which arise from changes in poliical,

More information

Unit Root Time Series. Univariate random walk

Unit Root Time Series. Univariate random walk Uni Roo ime Series Univariae random walk Consider he regression y y where ~ iid N 0, he leas squares esimae of is: ˆ yy y y yy Now wha if = If y y hen le y 0 =0 so ha y j j If ~ iid N 0, hen y ~ N 0, he

More information

INFLUENCE OF WIND VELOCITY TO SUPPLY WATER TEMPERATURE IN HOUSE HEATING INSTALLATION AND HOT-WATER DISTRICT HEATING SYSTEM

INFLUENCE OF WIND VELOCITY TO SUPPLY WATER TEMPERATURE IN HOUSE HEATING INSTALLATION AND HOT-WATER DISTRICT HEATING SYSTEM Dr. Branislav Zivkvic, B. Eng. Faculy f Mechanical Engineering, Belgrade Universiy Predrag Zeknja, B. Eng. Belgrade Municipal DH Cmpany Angelina Kacar, B. Eng. Faculy f Agriculure, Belgrade Universiy INFLUENCE

More information

ON THE COMPONENT DISTRIBUTION COEFFICIENTS AND SOME REGULARITIES OF THE CRYSTALLIZATION OF SOLID SOLUTION ALLOYS IN MULTICOMPONENT SYSTEMS*

ON THE COMPONENT DISTRIBUTION COEFFICIENTS AND SOME REGULARITIES OF THE CRYSTALLIZATION OF SOLID SOLUTION ALLOYS IN MULTICOMPONENT SYSTEMS* METL 006.-5.5.006, Hradec nad Mravicí ON THE OMPONENT DISTRIUTION OEFFIIENTS ND SOME REGULRITIES OF THE RYSTLLIZTION OF SOLID SOLUTION LLOYS IN MULTIOMPONENT SYSTEMS* Eugenij V.Sidrv a, M.V.Pikunv b, Jarmír.Drápala

More information

Standard models used for monetary policy analysis typically assume that households and

Standard models used for monetary policy analysis typically assume that households and Cenennial Issue Annuncemens and he Rle f Plicy Guidance Carl E. Walsh By prviding guidance abu fuure ecnmic develpmens, cenral banks can affec privae secr expecains and decisins. This can imprve welfare

More information

Econ107 Applied Econometrics Topic 7: Multicollinearity (Studenmund, Chapter 8)

Econ107 Applied Econometrics Topic 7: Multicollinearity (Studenmund, Chapter 8) I. Definiions and Problems A. Perfec Mulicollineariy Econ7 Applied Economerics Topic 7: Mulicollineariy (Sudenmund, Chaper 8) Definiion: Perfec mulicollineariy exiss in a following K-variable regression

More information

Business Cycles. Approaches to business cycle modeling

Business Cycles. Approaches to business cycle modeling Business Cycles 73 Business Cycles Appraches business cycle mdeling Definiin: Recurren paern f dwnswings and upswings: Acrss many indusries Wih cmmn paern f c-mvemen amng majr variables Oupu Emplymen Invesmen

More information

Bias in Conditional and Unconditional Fixed Effects Logit Estimation: a Correction * Tom Coupé

Bias in Conditional and Unconditional Fixed Effects Logit Estimation: a Correction * Tom Coupé Bias in Condiional and Uncondiional Fixed Effecs Logi Esimaion: a Correcion * Tom Coupé Economics Educaion and Research Consorium, Naional Universiy of Kyiv Mohyla Academy Address: Vul Voloska 10, 04070

More information

Forecasting optimally

Forecasting optimally I) ile: Forecas Evaluaion II) Conens: Evaluaing forecass, properies of opimal forecass, esing properies of opimal forecass, saisical comparison of forecas accuracy III) Documenaion: - Diebold, Francis

More information

Exponential Weighted Moving Average (EWMA) Chart Under The Assumption of Moderateness And Its 3 Control Limits

Exponential Weighted Moving Average (EWMA) Chart Under The Assumption of Moderateness And Its 3 Control Limits DOI: 0.545/mjis.07.5009 Exponenial Weighed Moving Average (EWMA) Char Under The Assumpion of Moderaeness And Is 3 Conrol Limis KALPESH S TAILOR Assisan Professor, Deparmen of Saisics, M. K. Bhavnagar Universiy,

More information

Lecture 3: Resistive forces, and Energy

Lecture 3: Resistive forces, and Energy Lecure 3: Resisive frces, and Energy Las ie we fund he velciy f a prjecile ving wih air resisance: g g vx ( ) = vx, e vy ( ) = + v + e One re inegrain gives us he psiin as a funcin f ie: dx dy g g = vx,

More information

Chapter 15. Time Series: Descriptive Analyses, Models, and Forecasting

Chapter 15. Time Series: Descriptive Analyses, Models, and Forecasting Chaper 15 Time Series: Descripive Analyses, Models, and Forecasing Descripive Analysis: Index Numbers Index Number a number ha measures he change in a variable over ime relaive o he value of he variable

More information

Money in OLG Models. 1. Introduction. Econ604. Spring Lutz Hendricks

Money in OLG Models. 1. Introduction. Econ604. Spring Lutz Hendricks Mne in OLG Mdels Ecn604. Spring 2005. Luz Hendricks. Inrducin One applicain f he mdels sudied in his curse ha will be pursued hrughu is mne. The purpse is w-fld: I prvides an inrducin he ke mdels f mne

More information

ESTIMATION OF DYNAMIC PANEL DATA MODELS WHEN REGRESSION COEFFICIENTS AND INDIVIDUAL EFFECTS ARE TIME-VARYING

ESTIMATION OF DYNAMIC PANEL DATA MODELS WHEN REGRESSION COEFFICIENTS AND INDIVIDUAL EFFECTS ARE TIME-VARYING Inernaional Journal of Social Science and Economic Research Volume:02 Issue:0 ESTIMATION OF DYNAMIC PANEL DATA MODELS WHEN REGRESSION COEFFICIENTS AND INDIVIDUAL EFFECTS ARE TIME-VARYING Chung-ki Min Professor

More information

American Society for Quality

American Society for Quality American Sciey fr Qualiy Nnparameric Esimain f a Lifeime Disribuin When Censring Times Are Missing Auhr(s): X. Jan Hu, Jerald F. Lawless, Kazuyuki Suzuki Surce: Technmerics, Vl. 4, N. 1 (Feb., 1998), pp.

More information

Types of Exponential Smoothing Methods. Simple Exponential Smoothing. Simple Exponential Smoothing

Types of Exponential Smoothing Methods. Simple Exponential Smoothing. Simple Exponential Smoothing M Business Forecasing Mehods Exponenial moohing Mehods ecurer : Dr Iris Yeung Room No : P79 Tel No : 788 8 Types of Exponenial moohing Mehods imple Exponenial moohing Double Exponenial moohing Brown s

More information

RAPIDLY ADAPTIVE CFAR DETECTION BY MERGING INDIVIDUAL DECISIONS FROM TWO-STAGE ADAPTIVE DETECTORS

RAPIDLY ADAPTIVE CFAR DETECTION BY MERGING INDIVIDUAL DECISIONS FROM TWO-STAGE ADAPTIVE DETECTORS RAPIDLY ADAPIVE CFAR DEECION BY MERGING INDIVIDUAL DECISIONS FROM WO-SAGE ADAPIVE DEECORS Analii A. Knnv, Sung-yun Chi and Jin-a Kim Research Cener, SX Engine Yngin-si, 694 Krea kaa@ieee.rg; dkrein@nesx.cm;

More information

Large-scale Distance Metric Learning with Uncertainty

Large-scale Distance Metric Learning with Uncertainty i Large-scale Disance Meric Learning wih Uncerainy Qi Qian Jiasheng Tang Ha Li Shenghu Zhu Rng Jin Alibaba Grup, Bellevue, WA, 98004, USA {qi.qian, jiasheng.js, liha.lh, shenghu.zhu, jinrng.jr}@alibaba-inc.cm

More information

Lecture 3: Exponential Smoothing

Lecture 3: Exponential Smoothing NATCOR: Forecasing & Predicive Analyics Lecure 3: Exponenial Smoohing John Boylan Lancaser Cenre for Forecasing Deparmen of Managemen Science Mehods and Models Forecasing Mehod A (numerical) procedure

More information

Fiscal Policy under Balanced Budget and Indeterminacy: A New Keynesian Perspective *

Fiscal Policy under Balanced Budget and Indeterminacy: A New Keynesian Perspective * Fiscal Plicy under Balanced Budge and Indeerminacy: A ew Keynesian Perspecive * Givanni Di Barlme Universiy f Teram Marc Manz Minisry f Ecnmics and OECD February, 2008 Absrac. We invesigae he effec f fiscal

More information

Department of Economics East Carolina University Greenville, NC Phone: Fax:

Department of Economics East Carolina University Greenville, NC Phone: Fax: March 3, 999 Time Series Evidence on Wheher Adjusmen o Long-Run Equilibrium is Asymmeric Philip Rohman Eas Carolina Universiy Absrac The Enders and Granger (998) uni-roo es agains saionary alernaives wih

More information

Lecture 5. Time series: ECM. Bernardina Algieri Department Economics, Statistics and Finance

Lecture 5. Time series: ECM. Bernardina Algieri Department Economics, Statistics and Finance Lecure 5 Time series: ECM Bernardina Algieri Deparmen Economics, Saisics and Finance Conens Time Series Modelling Coinegraion Error Correcion Model Two Seps, Engle-Granger procedure Error Correcion Model

More information

Motion Along a Straight Line

Motion Along a Straight Line PH 1-3A Fall 010 Min Alng a Sraigh Line Lecure Chaper (Halliday/Resnick/Walker, Fundamenals f Physics 8 h ediin) Min alng a sraigh line Sudies he min f bdies Deals wih frce as he cause f changes in min

More information

Revelation of Soft-Switching Operation for Isolated DC to Single-phase AC Converter with Power Decoupling

Revelation of Soft-Switching Operation for Isolated DC to Single-phase AC Converter with Power Decoupling Revelain f Sf-Swiching Operain fr Islaed DC Single-phase AC Cnverer wih wer Decupling Nagisa Takaka, Jun-ichi Ih Dep. f Elecrical Engineering Nagaka Universiy f Technlgy Nagaka, Niigaa, Japan nakaka@sn.nagakau.ac.jp,

More information

The lower limit of interval efficiency in Data Envelopment Analysis

The lower limit of interval efficiency in Data Envelopment Analysis Jurnal f aa nelpmen nalysis and ecisin Science 05 N. (05) 58-66 ailable nline a www.ispacs.cm/dea lume 05, Issue, ear 05 ricle I: dea-00095, 9 Pages di:0.5899/05/dea-00095 Research ricle aa nelpmen nalysis

More information

Chapter 5. Heterocedastic Models. Introduction to time series (2008) 1

Chapter 5. Heterocedastic Models. Introduction to time series (2008) 1 Chaper 5 Heerocedasic Models Inroducion o ime series (2008) 1 Chaper 5. Conens. 5.1. The ARCH model. 5.2. The GARCH model. 5.3. The exponenial GARCH model. 5.4. The CHARMA model. 5.5. Random coefficien

More information

Physics 111. Exam #1. September 28, 2018

Physics 111. Exam #1. September 28, 2018 Physics xam # Sepember 8, 08 ame Please read and fllw hese insrucins carefully: Read all prblems carefully befre aemping slve hem. Yur wrk mus be legible, and he rganizain clear. Yu mus shw all wrk, including

More information

FITTING OF A PARTIALLY REPARAMETERIZED GOMPERTZ MODEL TO BROILER DATA

FITTING OF A PARTIALLY REPARAMETERIZED GOMPERTZ MODEL TO BROILER DATA FITTING OF A PARTIALLY REPARAMETERIZED GOMPERTZ MODEL TO BROILER DATA N. Okendro Singh Associae Professor (Ag. Sa.), College of Agriculure, Cenral Agriculural Universiy, Iroisemba 795 004, Imphal, Manipur

More information

Financial crises and stock market volatility transmission: evidence from Australia, Singapore, the UK, and the US

Financial crises and stock market volatility transmission: evidence from Australia, Singapore, the UK, and the US Universiy of Wollongong Research Online Faculy of Commerce - Papers (Archive) Faculy of Business 2009 Financial crises and sock marke volailiy ransmission: evidence from Ausralia, Singapore, he UK, and

More information

Testing the Random Walk Model. i.i.d. ( ) r

Testing the Random Walk Model. i.i.d. ( ) r he random walk heory saes: esing he Random Walk Model µ ε () np = + np + Momen Condiions where where ε ~ i.i.d he idea here is o es direcly he resricions imposed by momen condiions. lnp lnp µ ( lnp lnp

More information

Week 7: Dynamic Price Setting

Week 7: Dynamic Price Setting 00 Week 7: Dynamic Price Seing Week 7: Dynamic Price Seing Rmer begins Chaer 7 n dynamic new Keynesian mdels wih a general framewrk fr dynamic rice seing In ur analysis f menu css and real/nminal rigidiy

More information

A unit root test based on smooth transitions and nonlinear adjustment

A unit root test based on smooth transitions and nonlinear adjustment MPRA Munich Personal RePEc Archive A uni roo es based on smooh ransiions and nonlinear adjusmen Aycan Hepsag Isanbul Universiy 5 Ocober 2017 Online a hps://mpra.ub.uni-muenchen.de/81788/ MPRA Paper No.

More information

OBJECTIVES OF TIME SERIES ANALYSIS

OBJECTIVES OF TIME SERIES ANALYSIS OBJECTIVES OF TIME SERIES ANALYSIS Undersanding he dynamic or imedependen srucure of he observaions of a single series (univariae analysis) Forecasing of fuure observaions Asceraining he leading, lagging

More information

Impact Switch Study Modeling & Implications

Impact Switch Study Modeling & Implications L-3 Fuzing & Ordnance Sysems Impac Swich Sudy Mdeling & Implicains Dr. Dave Frankman May 13, 010 NDIA 54 h Annual Fuze Cnference This presenain cnsiss f L-3 Crprain general capabiliies infrmain ha des

More information

Fractional Order Disturbance Observer based Robust Control

Fractional Order Disturbance Observer based Robust Control 201 Inernainal Cnference n Indusrial Insrumenain and Cnrl (ICIC) Cllege f Engineering Pune, India. May 28-30, 201 Fracinal Order Disurbance Observer based Rbus Cnrl Bhagyashri Tamhane 1, Amrua Mujumdar

More information

The Buck Resonant Converter

The Buck Resonant Converter EE646 Pwer Elecrnics Chaper 6 ecure Dr. Sam Abdel-Rahman The Buck Resnan Cnverer Replacg he swich by he resnan-ype swich, ba a quasi-resnan PWM buck cnverer can be shwn ha here are fur mdes f pera under

More information

Stability of the SDDRE based Estimator for Stochastic Nonlinear System

Stability of the SDDRE based Estimator for Stochastic Nonlinear System 26 ISCEE Inernainal Cnference n he Science f Elecrical Engineering Sabiliy f he SDDRE based Esimar fr Schasic Nnlinear Sysem Ilan Rusnak Senir Research Fellw, RAFAEL (63, P.O.Bx 225, 322, Haifa, Israel.;

More information

Introduction D P. r = constant discount rate, g = Gordon Model (1962): constant dividend growth rate.

Introduction D P. r = constant discount rate, g = Gordon Model (1962): constant dividend growth rate. Inroducion Gordon Model (1962): D P = r g r = consan discoun rae, g = consan dividend growh rae. If raional expecaions of fuure discoun raes and dividend growh vary over ime, so should he D/P raio. Since

More information

Monetary policymaking and inflation expectations: The experience of Latin America

Monetary policymaking and inflation expectations: The experience of Latin America Moneary policymaking and inflaion expecaions: The experience of Lain America Luiz de Mello and Diego Moccero OECD Economics Deparmen Brazil/Souh America Desk 8h February 7 1999: new moneary policy regimes

More information

Outline. lse-logo. Outline. Outline. 1 Wald Test. 2 The Likelihood Ratio Test. 3 Lagrange Multiplier Tests

Outline. lse-logo. Outline. Outline. 1 Wald Test. 2 The Likelihood Ratio Test. 3 Lagrange Multiplier Tests Ouline Ouline Hypohesis Tes wihin he Maximum Likelihood Framework There are hree main frequenis approaches o inference wihin he Maximum Likelihood framework: he Wald es, he Likelihood Raio es and he Lagrange

More information

Ecological Archives E A1. Meghan A. Duffy, Spencer R. Hall, Carla E. Cáceres, and Anthony R. Ives.

Ecological Archives E A1. Meghan A. Duffy, Spencer R. Hall, Carla E. Cáceres, and Anthony R. Ives. Ecological Archives E9-95-A1 Meghan A. Duffy, pencer R. Hall, Carla E. Cáceres, and Anhony R. ves. 29. Rapid evoluion, seasonaliy, and he erminaion of parasie epidemics. Ecology 9:1441 1448. Appendix A.

More information

13.3 Term structure models

13.3 Term structure models 13.3 Term srucure models 13.3.1 Expecaions hypohesis model - Simples "model" a) shor rae b) expecaions o ge oher prices Resul: y () = 1 h +1 δ = φ( δ)+ε +1 f () = E (y +1) (1) =δ + φ( δ) f (3) = E (y +)

More information

Review of HAARP Experiment and Assessment of Ionospheric Effects

Review of HAARP Experiment and Assessment of Ionospheric Effects Third AL PI ympsium Kna, Hawaii Nvember 9-3, 009 Review f HAARP Experimen and Assessmen f Inspheric Effecs T. L. Ainswrh, Y. Wang, J.-. Lee, and K.-. Chen Naval Research Labrary, Washingn DC, UA CRR, Nainal

More information

DISTANCE PROTECTION OF HVDC TRANSMISSION LINE WITH NOVEL FAULT LOCATION TECHNIQUE

DISTANCE PROTECTION OF HVDC TRANSMISSION LINE WITH NOVEL FAULT LOCATION TECHNIQUE IJRET: Inernainal Jurnal f Research in Engineering and Technlgy eissn: 9-6 pissn: -78 DISTANCE PROTECTION OF HVDC TRANSMISSION LINE WITH NOVEL FAULT LOCATION TECHNIQUE Ruchia Nale, P. Suresh Babu Suden,

More information

3.1 More on model selection

3.1 More on model selection 3. More on Model selecion 3. Comparing models AIC, BIC, Adjused R squared. 3. Over Fiing problem. 3.3 Sample spliing. 3. More on model selecion crieria Ofen afer model fiing you are lef wih a handful of

More information

Internal Audit Report NGO: Tagore Society for Rural Development

Internal Audit Report NGO: Tagore Society for Rural Development 1 I N T E G R A T E D C O A S T A L Z O N E M A N A G E M E N T P R O J E C T W E S T B E N G A L N G O : T a g r e S c i e y f r R u r a l D e v e l p m e n C n e n s Secin I: Audi Scpe and Apprach:...

More information

Storm Time Ring Current - Atmosphere Interactions: Observations and Modeling

Storm Time Ring Current - Atmosphere Interactions: Observations and Modeling Srm Time Ring Curren - Amsphere Ineracins: Observains and Mdeling V. Jrdanva 1, C. Muikis 1, L. Kisler 1, H. Masui 1, P. Puhl-Quinn 1, and Y. Khyainsev 2 (1) Space Science Cener, Universiy f New Hampshire,

More information

Optimization of Four-Button BPM Configuration for Small-Gap Beam Chambers

Optimization of Four-Button BPM Configuration for Small-Gap Beam Chambers Opimizain f Fur-Bun BPM Cnfigurain fr Small-Gap Beam Chamers S. H. Kim Advanced Phn Surce Argnne Nainal Larary 9700 Suh Cass Avenue Argnne, Illinis 60439 USA Asrac. The cnfigurain f fur-un eam psiin mnirs

More information

Bayesian Dynamic Factor Analysis of a Simple Monetary DSGE Model

Bayesian Dynamic Factor Analysis of a Simple Monetary DSGE Model WP//29 Bayesian Dynamic Facr Analysis f a Simple Mneary DSGE Mdel Maxym Kryshk 20 Inernainal Mneary Fund WP//29 IMF Wrking Paper IMF Insiue Bayesian Dynamic Facr Analysis f a Simple Mneary DSGE Mdel Prepared

More information

How to Deal with Structural Breaks in Practical Cointegration Analysis

How to Deal with Structural Breaks in Practical Cointegration Analysis How o Deal wih Srucural Breaks in Pracical Coinegraion Analysis Roselyne Joyeux * School of Economic and Financial Sudies Macquarie Universiy December 00 ABSTRACT In his noe we consider he reamen of srucural

More information

Return and volatility spillover between large and small stocks in Bursa Malaysia

Return and volatility spillover between large and small stocks in Bursa Malaysia Inernaional Journal of Business and Social Science Vol. No. ; February 011 Reurn and volailiy spillover beween large and small socks in Bursa Malaysia Wei-Chong Choo a a Faculy of Economics and Managemen,

More information

On Measuring Pro-Poor Growth. 1. On Various Ways of Measuring Pro-Poor Growth: A Short Review of the Literature

On Measuring Pro-Poor Growth. 1. On Various Ways of Measuring Pro-Poor Growth: A Short Review of the Literature On Measuring Pro-Poor Growh 1. On Various Ways of Measuring Pro-Poor Growh: A Shor eview of he Lieraure During he pas en years or so here have been various suggesions concerning he way one should check

More information

Computer Simulates the Effect of Internal Restriction on Residuals in Linear Regression Model with First-order Autoregressive Procedures

Computer Simulates the Effect of Internal Restriction on Residuals in Linear Regression Model with First-order Autoregressive Procedures MPRA Munich Personal RePEc Archive Compuer Simulaes he Effec of Inernal Resricion on Residuals in Linear Regression Model wih Firs-order Auoregressive Procedures Mei-Yu Lee Deparmen of Applied Finance,

More information

Ramsey model. Rationale. Basic setup. A g A exogenous as in Solow. n L each period.

Ramsey model. Rationale. Basic setup. A g A exogenous as in Solow. n L each period. Ramsey mdel Rainale Prblem wih he Slw mdel: ad-hc assumpin f cnsan saving rae Will cnclusins f Slw mdel be alered if saving is endgenusly deermined by uiliy maximizain? Yes, bu we will learn a l abu cnsumpin/saving

More information

Modeling Economic Time Series with Stochastic Linear Difference Equations

Modeling Economic Time Series with Stochastic Linear Difference Equations A. Thiemer, SLDG.mcd, 6..6 FH-Kiel Universiy of Applied Sciences Prof. Dr. Andreas Thiemer e-mail: andreas.hiemer@fh-kiel.de Modeling Economic Time Series wih Sochasic Linear Difference Equaions Summary:

More information