Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
st: arima output differs significantly from SPSS & SAS
From
Arash Mahdian <[email protected]>
To
statalist <[email protected]>
Subject
st: arima output differs significantly from SPSS & SAS
Date
Tue, 4 Dec 2012 13:56:35 -0600
Using the same timeseries, SAS and SPSS give very similar result, but
arima v1, arima(3,0,3) results significantly different.
What am I doing wrong?
SAS:
proc arima data = ts;
identify var = v1(0);
estimate q=3 p=3;
run;
Estimated Mean: 22.17413
Autoregressive Factors: 1 - 0.87954 B**(1) - 0.8268 B**(2) + 0.81088 B**(3)
Moving Average Factors: Factors: 1 + 0.50825 B**(1) - 0.44647 B**(2) -
0.04756 B**(3)
SPSS:
TSMODEL
/MODELSUMMARY PRINT=[MODELFIT]
/MODELSTATISTICS DISPLAY=YES MODELFIT=[ SRSQUARE]
/SERIESPLOT OBSERVED FORECAST
/OUTPUTFILTER DISPLAY=ALLMODELS
/AUXILIARY CILEVEL=95 MAXACFLAGS=24
/MISSING USERMISSING=EXCLUDE
/MODEL DEPENDENT=V1
PREFIX='Model'
/ARIMA AR=[3,2,1] DIFF=0 MA=[3,2,1]
TRANSFORM=NONE CONSTANT=YES
/AUTOOUTLIER DETECT=OFF.
ARIMA Model Parameters
Estimate SE t Sig.
V1-Model_1 V1 No Transformation Constant 22.345 .394 56.645 .000
AR Lag 1 .882 .788 1.120 .263
Lag 2 .820 1.423 .576 .565
Lag 3 -.806 .679 -1.187 .236
MA Lag 1 -.504 .788 -.639 .523
Lag 2 .446 .341 1.309 .191
Lag 3 .049 .047 1.024 .306
Stata:
------------------------------------------------------------------------------
| OPG
v1 | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
v1 |
_cons | 22.83358 1.416263 16.12 0.000 20.05775 25.6094
-------------+----------------------------------------------------------------
ARMA |
ar |
L1. | 2.8964 .0114307 253.39 0.000 2.873996 2.918804
L2. | -2.855047 .0221336 -128.99 0.000 -2.898428 -2.811666
L3. | .9580439 .0109376 87.59 0.000 .9366066 .9794812
|
ma |
L1. | -1.629885 .0329863 -49.41 0.000 -1.694537 -1.565233
L2. | .4782177 .0559995 8.54 0.000 .3684607 .5879747
L3. | .1738528 .0301204 5.77 0.000 .1148179 .2328877
-------------+----------------------------------------------------------------
/sigma | 1.127603 .0231053 48.80 0.000 1.082318 1.172889
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/faqs/resources/statalist-faq/
* http://www.ats.ucla.edu/stat/stata/