How to find the optimal p for AR model
2 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
xiaoli su
le 23 Juil 2015
Commenté : xiaoli su
le 24 Juil 2015
Hi everyone,
I now have a nitrate time series and I have decomposed it with an additive model, which is Y=T+S+R. I hope to find the best-fit AR(p) model for my residuals. I read from some papers that Mann-Wald process could be used. It would be really great if someone could provide a code on how to find the p. Below is my nitrate residuals. Thanks!
0.160157983184890 2.17307720054057 1.52955989565626 1.45006890417194 2.45078566444762 1.82790551974331 2.69034445775899 4.42816184597468 2.34540928553036 2.68279049780604 1.62871903928173 0.508296837837410 -1.62288362596995 1.00584965715162 -0.543055573966803 0.444003915314771 1.52210606035635 2.59531316141792 2.23891089519949 3.05301642518107 3.10129331550264 0.429833321544216 -0.483079342214210 0.722657253107364 -2.30055733593411 -1.25196701104664 -1.31637009539918 -0.531355848351714 0.193111664455751 1.34662635028322 1.17338288183068 1.38414720557814 0.521082891665609 -0.939218305526926 0.469027827480539 3.37592322056800 2.33001561329242 3.25061121894578 1.20307030535913 1.16590066017249 1.22124884474584 0.251845091339198 1.67106041465255 1.28918353716591 1.18477801701926 0.0406356165926184 -0.0849594546340268 -1.09190526778067 -2.24995407529036 -2.44871656287112 -1.47128179369187 -0.438992641112626 0.582514336226620 1.16346937958587 1.01304349966511 0.941625416944357 1.37737869456360 -0.790604913097152 -0.566041187557907 -0.880828206938661 -2.85271821768246 -2.62150501849733 -2.32172834455219 -1.72158039620705 -1.13491462210192 2.23399921602322 -0.185267868131646 0.230972844913491 0.841384917298627 -1.66993989159624 -2.26121737129110 -2.65584559490597 -3.72157680988388 -3.18420481493285 -1.57576934422182 -1.59696260111080 -0.875138030239769 -1.32156539734874 -0.119673685737717 0.327725823073310 0.0342966932243356 -0.746369320904637 -2.41098800583361 -3.41195743268258 -3.19052985189460 -3.45549906417769 -2.47420479670077 -2.27343925682385 -1.84095589118694 -0.720724461530018 -0.385173953153102 -0.0366156505761843 -0.184385984659268 -1.31839320302235 -0.627853090185433 -1.23616372126852 0.594922655285354 0.629612240768162 0.680365300010968 0.0264896376537763 -1.57986819994342 -1.29947797852061 -0.541768674377802 -0.0945515750349948 0.341836886647812 -0.419011535949380 -0.965312627346572 -1.65496446266376 -2.05971929034400 -1.59887091009531 -2.04045905108661 -1.84717592067791 -0.914874961509212 -0.226825944320514 1.11411769358818 0.0414180536968818 0.403965307145579 -1.19572431668572 -1.37686661331702 -2.79685965286833 -2.17045568678267 -2.08344851076809 -1.18137785499350 0.230564069181090 0.881023826115679 0.0227316420702668 -0.530741462255145 -0.357706770380556 0.0349992798340315 -0.698531551231380 -1.05651505209679 -4.02404929588220 -2.89478653203066 -2.49912055925018 -2.47739111070970 -1.41929038776922 -0.575671836068746 -0.598305226348267 0.251380466092211 1.14757395173269 -0.00256120028683160 -1.54793323558635 -1.95875793968587 -4.12723338970539 -2.33071182708796 -1.53588705954159 -0.795498819235224 -0.171239299528854 1.98353804593751 0.109563456423885 -0.767092058369746 0.577760226036623 0.131283870782992 -0.430929367750639 -0.290095279084269 0.705388069662101 1.21076842304542 -0.961248012642317 -1.03140097157006 -0.115282656097797 -1.94334651886554 -0.838662314613278 -1.00965903164102 -0.513147954468758 -0.0424655139564996 -1.40851995472424 -1.22502706929198 0.586615073220280 2.16315422436950 1.62729658344764 0.212002419285794 1.55057952852394 -0.763825535477906 0.377017466540245 0.0813795432783944 0.639249419216544 -0.193509344505306 2.11279500549285 2.01474669169100 -1.00665237203085 0.375245576884251 0.344746729728291 0.435311359332332 -0.988452728663628 0.0468009991004125 0.0158027948844535 1.18002366838849 0.519252337092534 0.898752374136574 0.100515518900615 -0.281874001135344 0.713085731908695 -1.09165752441031 -2.17499757480038 -2.10387414943045 -1.77597944666052 -0.335066915130585 -0.670506325580654 0.393873344689276 -0.213639190840792 -0.828080362030862 -1.39885841850093 -1.82138914777100 -2.41957061596107 1.72474492348582 0.637563669861638 0.321345894997459 -0.755900606466719 -2.14292928117090 -2.80640989885508 -1.73387142881925 -1.20402517258343 -0.536207547007612 -1.73462680671179 -2.56629873921597 -3.79432141264014 -2.94124707742737 -1.04946953428566 -0.898328514383944 0.774783777917767 3.60581389697948 2.61549207606119 2.76878934386290 -0.744105601135384 0.0338708192063266 1.60881035226804 1.63889721452975 1.09333333887146 1.23066646885013 0.306902806757731 0.514602623425335 0.356773715492936 -1.77063737567946 -1.12520039783186 -2.26704433826426 -2.17208048749665 -0.219945266389052 0.984453062438551 4.21439872146615 10.6309936395738 9.58348556531831 4.84058069899181 3.25023931042530 2.76976919525879 1.30981690685228 1.62141267746578 1.80372752879927 1.38985018133276 2.03514418820625 1.38900131579975 -0.0668942244067584 0.495559489466734 -0.124789789022819 0.229564143416563 0.229581547615947 0.273870225215330 1.82887673657471 1.85863130295410 1.18370495705348 0.587686401352863 1.44833920699225 0.397255127351630 0.528218379911014 3.31003088855040 3.85584040582673 3.65225313103201 2.73822933399728 1.88907681036256 1.00744211748783 2.54305547663310 1.16348792049838 0.774428165563654 -0.157960233031073 -0.634385520905799 -0.874163468580525 -0.621292162175251 -0.0626238501330239 0.257947670838141 -0.280817329430694 -0.193811057299531 -0.206486957408366 0.0863852015027977 -0.881223561866039 -0.774924524034874 0.828845879136291 1.08787938602746 -1.24653976888138 -1.39630966371022 -2.43148255990210 -1.19245223716504 -0.186158441667991 2.20900662222907 1.73238951688612 0.953620476563174 2.39637050596023 1.36212834255728 1.19055753649434 1.99474984415139 0.524489482008449 -0.385121619054498 0.361164285519512 -0.610946599977543 -0.0421940147145987 -0.0471701500516536 -0.456328459628708 -0.816938703185762 -0.231329876022817 0.558086756340128 0.347174743043072 4.07052584846602 2.45642428408896 2.17897197679191 0.563416677131806 1.06146458540064 -0.415624030570522 -0.318141367141684 -0.259940878952849 1.61980766225599 0.778375292184820 -0.00854928268634358 0.530197499782492 -0.00279259602867288 0.940064630360165 3.74897112182900 3.04957461793479 2.30278132196951 1.40255150376424 1.38919295895897 0.0974522399136985 0.133559588888423 0.612486007583148 -1.31357977552212 0.332425808712600 -0.741205491332674 1.26801053182205 2.64687581605678 1.38863810792846 1.73500360772908 0.906932585289691 0.0380328362503098 0.0930509169709258 0.471917055711543 0.832802270172159 0.327095283832775 0.200359660833392 -0.307012841445991 -0.207738021525375 2.98568605947524 2.52960714711281 2.30613144267932 1.43821921600583 4.66417826273233 2.41865513621884 1.17408007572535 -0.968475910048146 -1.06672410162164 0.435699070144867 -0.679114644368625 1.52121897631788 1.66340185208439 1.10648173548785 0.756164826820247 1.72841139591265 2.79052923840504 1.06346490465744 -0.0409513640701629 -0.386648549077766 -1.06953794088537 -0.520855978352972 1.45028910589943 1.25068152235183 -0.195976806115778 -1.33073812694643 -0.110896239848139 0.792509125010148 0.900885761268438 0.0725802262867249 -0.498077241674988 -1.13091563691670 -1.05444623295841 -0.307505475660124 -1.27820159064184 -1.73985038542355 -0.0304499151252560 -5.12133439419001 -4.62070827832584 -3.96203870770166 -2.67526216267748 -1.57287548189330 -2.88789757708912 -1.62167717956495 -2.11834897984077 -1.28414942177659 -1.70968674699241 4.62332326199177 -1.62001747194405 1.76553879575708 0.946698274387148 0.0514212307772164 -1.44598453843271 -3.22087248488264 -2.62551236631258 -1.79483316802251 -2.78364617353244 -3.25328781670237 -2.00766635015230 -3.04849754640223 -4.02067948957216 2.85603558089486 3.67835385529082 3.55423560744678 -0.964816690997261 -0.0707405176813029 -1.95922160334534 -1.69738360428939 -1.88503782003342 -1.86352066543747 -0.426740398121506 -0.926412799605548 -1.16743594600959 4.46043791522332 0.513914985385175 -0.609044463692976 0.635867352628874 -1.54670300128928 -1.04902528518743 -1.43602850036557 0.0674760866562765 0.630152029018126 -0.636908900900024 0.0995774943818254 0.0697131407436751 -1.49125420025752 0.793381664670220 0.451581008357960 -3.26734837355430 0.556240070293440 0.611776578161180 -0.970767841251080 0.0538955415366611 -0.587269719335599 -0.663171856487859 0.0461733355598827 -1.80923222131238 -2.01404076954768 0.436753893145947 -0.153887963400423 -0.146658553546792 -0.966911317933161 -0.326916009299530 -0.841601633945901 -1.88577945139227 -0.590785914498639 1.08947074111499 1.08327472192862 -1.99427203217775 0.702078213352839 0.161031670812359 -0.305451395968119 -0.0870631873485989 -1.05615714796908 -0.165003055569557 -0.773529877450035 -2.27154890113051 -1.13039657147099 -0.903981119091473 -1.86901833951195 1.79459369914757 2.51410274444404 1.16521499766946 0.926890728654869 0.286437729040281 -0.598197438814308 -2.16248454264890 -0.796552569763486 -1.39341280067807 -1.80610167425266 -2.10682742810725 -2.98740584776184 -3.87424976333643 0.251032824725939 -0.286696126282760 2.52313840046854 -0.832855802380152 -1.04293216946885 -1.20446048253755 -1.24396971188625 -2.56137115303494 -2.79960122284364 -2.93416817993234 -2.09188780882104 4.93404181737026 6.02886845419852 1.95429829895571 0.760291621472907 0.411885251390097 0.264538642067290 0.607469126764484 0.604118691181675 -0.442123951201132 -0.900795234243940 4.35409660743325 4.04753577531044 0.174624200267637 -0.994390369138215 0.962198273384867 -0.532649610332050 0.390373785351033 -0.889085000205883 0.621704283257200 -0.382187354559718 -0.182271203176635 -0.624783684453552 0.571266947989530 0.0875649126326145 -1.81088786764430 0.836256360715734 0.439003797004706 0.755314711053681 0.484496895502654 -0.453803086288373 0.753144987940602 -0.524587859110426 -1.03181290496145 -0.819866594472480 -0.122657165263506 0.528099596145467 -1.38249438836556 -0.704191361239631 -0.470285127184769 -2.24286389536990 -0.0924744411550401 0.920384369819825 -0.961508756185312 -0.978082804470449 -0.264149055555584 0.188956052699280 -1.13267572632586 -0.310760169150993 -1.35019535689613 -1.99073353500431 -2.53566850718355 -1.48704000260280 -0.860540224622045 -0.981522618881289 -0.0122569541205351 -0.437672201639781 2.75959194904097 -0.798315758938272 5.35121126480248 3.64428561574324 0.276009223763989 -4.23121581557830 -0.717146338991657 -0.867359035645010 -0.709700457898366 -0.819524061391721 -1.57909959586508 -1.10335605361843 1.53743933782821 -1.46168201238514 -2.03099619687850 -2.43676305417185 4.07611935261479 -2.98386917296161 -2.14885749960907 1.67622748050346 0.415044854015996 2.85138005228853 -0.722036694418932 0.0648656475936020 -1.11772421519386 1.62089454035867 -1.06929811336879 1.87109382810374 0.750135030656278 0.113073237845765 -1.77166313103581 1.54871954584262 -0.484093911878955 1.32618970415947 0.273931763217895 2.47184567199632 0.745561821974748 -0.436697879706828 1.03975741733160 0.582856264570025 0.328056260888449 1.15215326084383 1.16185347172814 1.68511716037246 0.213760721416778 -0.0100950887789047 0.728805765045413 -0.746974307410273 3.81753391533404 0.311652508418360 2.93081470622268 0.713524247226995 2.98988303431131
0 commentaires
Réponse acceptée
Roger Wohlwend
le 24 Juil 2015
You could use the Akaike or the Bayesian Information criterion (Matlab function aicbic). Also consult the page "Choosing ARMA lags using BIC" in the Matlab documentation.
A less sophisticated way is to try different values for p, estimate the model in each case and choose the p where the model's residual are free of autocorrelation.
The Matlab function parcorr suggests that the optimal value for p is 1 in your case. Indeed, for p = 1 the model seem to be quite good. The residuals are free of autocorrelation, the R-square is 0.35 and the coefficient is significant.
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Conditional Mean Models dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!