Documente Academic
Documente Profesional
Documente Cultură
1.
2.
3.
4.
5.
Seria de timp considerate este rata trimestriala somajului a SUA pentru perioada 1970:12008:4.Prognozele se vor realiza pentru anul 2009.Aceasta este exprimata
procentual(%).Sursa de date o constituie OECD, 2008 Economic Outlook
Database(www.oecd.org ).
UR
11
10
9
8
7
6
5
4
3
1970
1975
1980
1985
1990
1995
2000
2005
UR by Season
11
10
9
8
7
6
5
4
3
Q1
Q2
Q3
Q4
Means by Season
20
Series: UR
Sample 1970Q1 2008Q4
Observations 156
16
12
Mean
Median
Maximum
Minimum
Std. Dev.
Skewness
Kurtosis
6.108001
5.816359
10.67001
3.919484
1.379351
0.906277
3.737479
Jarque-Bera
Probability
24.89000
0.000004
0
4
10
DUR
2.0
1.5
1.0
0.5
0.0
-0.5
-1.0
1970
1975
1980
1985
1990
1995
2000
2005
Modele
AR(1)
AR(2)
MA(1)
MA(2)
MA(3)
ARMA(1,1)
ARMA(1,2)
ARMA(1,3)
ARMA(2,1)
ARMA(3,1)
Criteriul Akaike
0.03
0.04
0.15
0.09
0.03
0.04
0.05
0.04
0.008
0.05
Criteriul Schwartz
0.05
0.08
0.17
0.12
0.08
0.08
0.11
0.12
0.06
0.13
Observation!!!
There are two ways to estimate integrated models in EViews. First, you may generate
a new series containing the differenced data, and then estimate an ARMA model
using the new data. For example, to estimate a Box-Jenkins ARIMA(1, 1, 1) model
for M1, you can enter:
series dm1 = d(m1) equation eq1.ls dm1 c ar(1) ma(1)
Alternatively, you may include the difference operator d directly in the estimation
specification.
For example, the same ARIMA(1,1,1) model can be estimated using the command:
equation eq1.ls d(m1) c ar(1) ma(1)
The latter method should generally be preferred for an important reason. If you define
a new variable, such as DM1 above, and use it in your estimation procedure, then
when you forecast from the estimated model, EViews will make forecasts of the
dependent variable DM1. That is, you will get a forecast of the differenced series. If
you are really interested in forecasts of the level variable, in this case M1, you will
have to manually transform the forecasted value and adjust the computed standard
errors accordingly. Moreover, if any other transformation or lags of M1 are included
as regressors, EViews will not know that they are related to DM1. If, however, you
specify the model using the difference operator expression for the dependent variable,
d(m1), the forecasting procedure will provide you with the option of forecasting the
level variable, in this case M1.
Parametrii modelului sunt semnificativ diferiti de zero, si R2 este sufficient de mare, 44%.
Criteriile informationale Akaike si Schwarz au valori minime.
The Q-statistics are insignificant at all lags, indicating no significant serial correlation in the
residuals(greater p-values).
Probabilitatile f. Mari(>5%) asociate coeficientilor Ljung-Box ne releva independenta
erorilor.
Testul Multiplicatorului lui Lagrange(Breuch-Godfrey) ne releva acelasi lucru:
Erorile sunt heteroscedastice, deoarece prob. aferente coeficientilor Q-stat sunt mai mici de
5%.
Erorile sunt nu normal distribuite, deoarece valoarea testului JB este mult mai mare
decat valoarea tabelata si in plus prob.tinde catre zero.