Econometrie

Problema 1. Se considera datele din problema 3, proiectul 1.

a) Fie biofarm_problema1&3.WF1

- Series rrbrd. View/Correlogram/level.

Date: 01/03/10 Time: 15:01

Sample: 1 300

Included observations: 245

Autocorrelation Partial Correlation AC PAC Q-Stat Prob

.|* | |* | 1 0.111 0.111 3.0306 0.082

.|. | |. | 2 -0.003 -0.015 3.0325 0.220

.|. | |. | 3 -0.004 -0.002 3.0366 0.386

.|. | |. | 4 -0.013 -0.012 3.0786 0.545

.|. | |. | 5 0.014 0.017 3.1262 0.681

.|. | |. | 6 0.006 0.003 3.1360 0.792

.|* | |* | 7 0.076 0.076 4.6120 0.707

.|. | |. | 8 0.018 0.001 4.6990 0.789

.|* | |* | 9 0.067 0.068 5.8392 0.756

.|* | |. | 10 0.066 0.053 6.9655 0.729

.|* | |* | 11 0.087 0.080 8.9300 0.628

.|* | |* | 12 0.114 0.100 12.313 0.421

Toti coeficientii de autocorelatie respectiv de autocorelatie partiala sunt nesemnificativi.

Pentru k=12 avem Qcalculat=12.313 iar probabilitatea corespunzatoare P=0.421 >5%=0.05 rezulta primii 12 coeficienti de autocorelatie sunt nesemnificativi (un difera semnificativ de zero). Rezulta nu exista corelatii (dependente) liniare in seria rentabilitatilor.

Problema 2. Modele stochastice de tip ARIMA respectiv GARCH. Se considera o serie de timp nestationara ce reda evolutia cursului USD in raport cu LEU-ul de frecventa lunara.

Fie workfile curs_RON/USD.wf1

- Series: curs_USD

a) Specificati modelul ARIMA(p.d.q) adecvat

a1) d=?

Din graficul de mai sus putem observa ca variabila este nestationara, astfel este necesara diferentierea.

Pare a fi stationara, in jurul uniei constante diferita de zero. Se aplica si testul ADF, pe seria diferentiata; View/Unit root test/ (1st difference, intercept)

Null Hypothesis: D(CURS_USD) has a unit root

Exogenous: Constant

Lag Length: 0 (Automatic based on SIC, MAXLAG=10)

t-Statistic Prob.*

Augmented Dickey-Fuller test statistic -6.633751 0.0000

Test critical values: 1% level -3.550396

5% level -2.913549

10% level -2.594521

*MacKinnon (1996) one-sided p-values.

Prob =0.0000<5% deci ipoteza nula se respinge.Seria diferentiata este stationara in jurul unei constante. Prin urmare d=1.

a2) p=?, q=?

View/Correlogram; 1st difference

Date: 01/09/10 Time: 12:05

Sample: 2005M01 2009M11

Included observations: 57

Autocorrelation Partial Correlation AC PAC Q-Stat Prob