時(shí)間的序列地預(yù)處理

1、應(yīng)用時(shí)間序列分析實(shí)驗(yàn)報(bào)告、上機(jī)練習(xí)(就是每章最后一節(jié)上機(jī)指導(dǎo)部分)1繪制時(shí)序圖dataexample2 1;in putpricel price2;time=intnx('month', '01jul2004'd,n- 1);format time date.;cards ;12.85 15.2113.29 14.2312.41 14.6915.21 13.2714.23 16.7513.56 15.33proc gplot data =example2 1;plot price1*time= 1 price2*time=2/ overlaysymbol1c=b

2、lack v =stari =join;symbol2c=redv =circlei =spli ne;run ;實(shí)驗(yàn)結(jié)果：兩時(shí)間序列重疊顯示時(shí)序圖實(shí)驗(yàn)分析：該時(shí)序圖顯示了price1每年始終圍繞在14附近隨機(jī)波動(dòng)，沒有明顯趨勢(shì)或周期，基本可以視為平穩(wěn)序列。price2每年始終圍繞在15附近隨機(jī)波動(dòng)，沒有明顯趨勢(shì)或周期，也基本可以視為平穩(wěn)序列。2、平穩(wěn)性與純隨機(jī)性檢驗(yàn)1 平穩(wěn)性檢驗(yàn)data example2 2; in putfreq;year=intnx ( 'year' , '1jan1970'd,n- 1);format year year4.;ards

3、;97 154 137.7 149 164 157 188 204 179 210 202 218 209204 211 206 214 217 210 217 219 211 233 316 221 239215 228 219 239 224 234 227 298 332 245 357 301 389;proc arima data =example2 2;iden tifyvar =freq;run ;實(shí)驗(yàn)結(jié)果:刑日帕 of Variable 二 freq胎河1 qf Work I fi名 Series222.941Stain da nd Dev i sit i on5C_92594

4、HuiTitier of Observit ions39圖一La? Covari anceAirtocQrrslat ionsCqrrel at ion3td Error3229.4801685.2S71933,3971293.5361238.697B77.94C439.920375 .215331.83232 .3841.000006.57759C.593670.40Z400.383530.2710.135220.116196.102?$0.08054山山ill山"1*山電嘰山山vhiii'in11 i|»1111 ijiiTii|s bi pi|ia i11pi

5、|i b pqirfB in? rp if 11| 11,TI s T11 I"l! H. i.ilasaa山*J_r山山ill ill 11 a ill 11ip4ifri?rrtirr*nirn<由士啊來* ,:+； -i,"narks two standard errors0 0J6fll2S 0-206757 0.247U2 0.263501 0.277446 0-294194 O.Z8EGG9 0.287Q71 0-28B013圖二：序列FREQ樣本自相關(guān)圖實(shí)驗(yàn)分析：根據(jù)圖一我們可以得出分析變量的名稱為freq ，序列的均值為 222.941 ，序列的標(biāo)準(zhǔn)差

6、為56.82834,觀察值的個(gè)數(shù)為 39個(gè)。圖二的自相關(guān)圖顯示序列子相關(guān)系數(shù)長(zhǎng)期位于零軸的一邊，這是具有單調(diào)趨勢(shì)序列的典型特征，帶長(zhǎng)期遞減趨勢(shì)的。故該序列不平穩(wěn)。2.純隨機(jī)性檢驗(yàn)data example2_2;in put freq;year=intnx ( 'year' , '1jan1970'd,_n_-1);format year year4.;ards ;97 154 137.7 149 164 157 188 204 179 210 202 218 209204 211 206 214 217 210 217 219 211 233 316 221 2

7、39215 228 219 239 224 234 227 298 332 245 357 301 389；proc arima data =example2 2;iden tifyvar =freq;實(shí)驗(yàn)結(jié)果:ToL&sChl-Sjqij&reDFAutocorrBlat ior Check for White NoisePr >ChiSqAutocorre I at ions47,1<,0001g.57S0,5990,402 E.翱40,272實(shí)驗(yàn)分析：檢驗(yàn)結(jié)果顯示，在各階延遲下LB檢驗(yàn)統(tǒng)計(jì)量的 P值都非常?。?lt;0.0001 ），所以可以很大的把握（置信水

8、平 >99.999% ）判定該序列為非白噪聲序列，即非純隨機(jī)序列。二、課后習(xí)題（老師布置的習(xí)題部分）2.1975-1980年夏威夷島莫那羅亞火山（ Mauna loa）每月釋放的 數(shù)據(jù)如下（單位：ppm），見表2-7.330.45330.97331.64332.87333.61333.55331.9330.05328.58328.31329.41330.63331.63332.46333.36334.45334.82334.32333.05330.87329.24328.87330.18331.5332.81333.23334.55335.82336.44335.99334.65332.

9、41331.32330.73332.05333.53334.66335.07336.33337.39337.65337.57336.25334.39332.44332.25333.59334.76335.89336.44337.63338.54339.06338.95337.41335.71333.68333.69335.05336.53337.81338.16339.88340.57341.19340.87339.25337.19335.49336.63337.74338.36（1） 繪制序列時(shí)序圖，并判斷該系列是否平穩(wěn)。data example21;in put price;time=in

10、tnx('mo nth','01jan1975'd,n -1);format time date.;cards ;330.45330.97331.64332.87333.61333.55331.90330.05328.58328.31329.41330.63331.63332.46333.36334.45334.82334.32333.05330.87329.24328.87330.18331.50332.81333.23334.55335.82336.44335.99334.65332.41331.32330.73332.05333.53334.66335.0

11、7336.33337.39337.65337.57336.25334.39332.44332.25333.59334.76335.89336.44337.63338.54339.06338.95337.41335.71333.68333.69335.05336.53337.81338.16339.88340.57341.19340.87339.25337.19335.49336.63337.74338.36；proc gplot data =example2_1;plot price*time=1 ;symbol1 c=blackv =stari =join;run ;實(shí)驗(yàn)結(jié)果：price實(shí)驗(yàn)

12、分析：時(shí)序圖給我們的提供的信息非常明確，夏威夷島莫那羅亞火山(Mauna loa)每月釋放的 時(shí)間序列圖有明顯的遞增趨勢(shì)，所以它不是平穩(wěn)序列。(2)計(jì)算該序列的樣本自相關(guān)系數(shù)。data example2 1;in putprice;time=intnx('mo nth'，01ja n1975'd，n- 1);format time date.;cards ;330.45330.97331.64332.87333.61333.55331.90330.05328.58328.31329.41330.63331.63332.46333.36334.45334.82334.32

13、333.05330.87329.24328.87330.18331.50332.81333.23334.55335.82336.44335.99334.65332.41331.32330.73332.05333.53334.66335.07336.33337.39337.65337.57336.25334.39332.44332.25333.59334.76335.89336.44337.63338.54339.06338.95337.41335.71333.68333.69335.05336.53337.81338.16339.88340.57341.19340.87339.25337.19

14、335.49336.63337.74338.36;proc arima data =example2_1;den tifyvar =price;run ;實(shí)驗(yàn)結(jié)果：Correlati on0.907510.721710.512520.349820.2469 0.20309 0.21021 0.26429 0.36433 0.48472 0.58456 0.60198 0.51841 0.36856 0.20671 0.08138 0.00135 -0.03248(3)繪制該樣本自相關(guān)圖，并解釋該圖形。Autocor re lt i cr»s實(shí)驗(yàn)結(jié)果:09.9327521.00000J

15、 L Hi i Lt Hi 11 Ui - J i 11 all L ill s Lr Hi 11 b 山山 7"山 rp rpi|Bipi|n|ii|ii|ir|iiTir|iifi i|ii|Bi|ii|n|ii|ii|ir|i019.0140501).90751Je 111 U*Lb <> ill >龍山 Ik山山ii ii pr111if j' T111* ! 'Ts rr'T11 rr n1 0.11ZG512?,189S040.721710.1917448E.O9D7180.512E2 L. mi：LlyjJ'pL'

16、;J/ X* !T" n'liprspii qnTlirpJ"-0.228SG043.4747C00.34382*附He出啊聃0.24193252.452361(l.?4S90*弗麻卅制鼻0.24935862.Q172S5V.2009*糊刖甲0.25223772.0878440.210210.25448852.6251000.264290.25舗98S3.81S8210JB433*«：*«* .0.260647104.9145710.4G4720.2678Z711S.B0E8DB0.G0456*常*；*鹹余電申*聊*0.279554125.979

17、3080.6019&0.296045135.1492B40-518410.312E84149.66OB440498BGSO 貶43咋152.O5S2200.20&710JS0D72160.8083340.0813B0.331665170.0134560,001350.332142IE-0.322607-.03243.t0.392142Las Covariance Cor re kt i onStd Eq*arl<s two siandird errors實(shí)驗(yàn)分析：自相關(guān)圖顯示序列子相關(guān)系數(shù)長(zhǎng)期位于零軸的一邊，這是具有單調(diào)趨勢(shì)序列的典型特征,同時(shí)自相關(guān)圖呈現(xiàn)出明顯的正弦波動(dòng)

18、規(guī)律，這是具有周期變化規(guī)律的非平穩(wěn)序列的典型特征。自相關(guān)圖 顯示出來的這兩個(gè)性質(zhì)和該序列時(shí)序圖顯示的帶長(zhǎng)期遞增趨勢(shì)的周期性質(zhì)是非常吻合的。3.1945-1950年費(fèi)城月度降雨量數(shù)據(jù)如下(單位：mm)69.38040.974.984.6101.122595.3100.648.3144.528.338.452.368.637.1148.6218.7131.6112.881.83147.570.196.861.555.6171.7220.5119.463.2181.673.964.8166.948137.780.5105.289.9174.812486.4136.931.535.3112.34316

19、0.89780.562.5158.27.6165.9106.792.263.226.27752.3105.4144.349.5116.154.1148.6159.385.367.3112.859.4(1)計(jì)算該序列的樣本自相關(guān)系數(shù)data example2_2;in putprice;time=intnx('month', '01jan1945'd,_n_- 1);format time yymmdd10.;cards69.380 40.974.984.6101.122595.3100.648.3144.528.338.452.368.637.1148.6218

20、.7131.6112.881.83147.570.196.861.555.6171.7220.5119.463.2181.673.964.8166.948137.780.5105.289.9174.8124 86.4136.931.535.3112.343160.897 80.562.5158.27.6165.9106.792.263.226.27752.3105.4144.349.5116.154.1148.6159.385.367.3112.859.4;proc arima data =example2_2;iden tifyvar =price;run ;實(shí)驗(yàn)結(jié)果：Correlati o

21、n0.012770.04160-.04323-.17869-.25130-.09381-.06778-.071980.013880.109450.217300.31587-.025050.07532-.14121-.20359-.245490.06646(2)判斷該序列的平穩(wěn)性data example2 2;in putprice;time=intnx('month', '1jan1945'd,n- 1);format time yymmdd10. ;cards ;69.380.040.974.984.6101.1225.095.3100.648.3144.5L

22、 28.338.452.368.637.1148.6218.7131.6112.881.831.047.570.196.861.555.6171.7220.5119.463.2181.673.964.8166.948.0137.780.5105.289.9174.8124.086.4136.931.535.3112.343.0160.897.080.562.5158.27.6 165.9106.792.263.226.277.052.3105.4144.349.5116.154.1148.6159.385.367.3112.859.4procgpiotdata =example2 2;plot

23、 price*time=1 ;symboll c=blackv =stari =joi n;run ;實(shí)驗(yàn)結(jié)果:price300 -0 “200 r100 rI1I|iIII11jal*11945-01-011946-01-011947-01-011948-01-011949-01-011950-01-011951-01-01time實(shí)驗(yàn)分析：該序列的時(shí)序圖如上，圖上可以看出該序列在一個(gè)常值附近上下波動(dòng)，且不具有周期 性，判斷該序列為平穩(wěn)序列。（3）判斷該序列的純隨機(jī)性實(shí)驗(yàn)程序：與第二問的程序一樣 實(shí)驗(yàn)結(jié)果:ftutocorreltion Gieck for Th it年 Noiseiqua

24、reChlSqAutocorreIsit torts.52e0.20230.0130.542-j.O43-0J7S-0,251-0,034-2S.3E120.0248-0.0880-0720,0140.10S0.217o.3ie8U.02180.0070-O'0250.075-0, Ml-0.2040.2450,068Chi-f*r >LB檢驗(yàn)統(tǒng)計(jì)量的實(shí)驗(yàn)分析：檢驗(yàn)結(jié)果顯示，在各階延遲下P值都大（0.0001），所以可以很小的把握（置信水平99.999%）判定該序列為白噪聲序列，即純隨機(jī)序列。5.表2-9數(shù)據(jù)是某公司在 2000-2003年期間每月的銷售量。銷售量2000 年20

25、01 年2002 年2003 年1月1531341451172月1871752031783月2342431891494月2122272141785月3002982952486月2212562202027月2012372311628月1751651741359月12312411912010月104106859611月8587679012月78747563(1)繪制該序列時(shí)序圖及樣本自相關(guān)圖。da.t a e2tainpLi?sZ_3 : input nuiLber3： tine二intiLK nonthT, I i an20D0T g:format time ywiddl0< :cards

26、:tE3IS?2421230022120117E123104S57S134ITS243227298256237I £51241068774145203139214295220231174119呂5677511717814917824820218213E1209690S3prdgd'ts=eK?mi.pl2:3:plot numbcx=*ntini?=i:sraibcjlA etlack v=gtar i=join: proc arj.ia data=eK：aiiple2_3: identify var=nujnber:run:實(shí)驗(yàn)結(jié)果:timeCovari ante4202.8733109.0141920.S88 841再弭 -1345.1B6 -2600.791 -3030 JE8 -2644.355 -1427.302 47.8434241402.5722436 43 3071.9B6Correla