Hi, In Statistics, I am running a maximum-likelihood on SAS 9.4, and I got the f
ID: 3239769 • Letter: H
Question
Hi,
In Statistics, I am running a maximum-likelihood on SAS 9.4,
and I got the following results
The AUTOREG Procedure
Ordinary Least Squares Estimates
SSE
19239.7836
DFE
237
MSE
81.18052
Root MSE
9.01002
SBC
1738.00254
AIC
1731.04961
MAE
6.98533005
AICC
1731.10046
MAPE
210.912182
HQC
1733.85145
Durbin-Watson
2.3543
Regress R-Square
0.1756
Total R-Square
0.1756
Parameter Estimates
Variable
DF
Estimate
Standard
Error
t Value
Approx
Pr > |t|
Intercept
1
-0.4406
0.5829
-0.76
0.4504
urateg
1
-0.4721
0.0665
-7.10
<.0001
Estimates of Autocorrelations
Lag
Covariance
Correlation
-1 9 8 7 6 5 4 3 2 1 0 1 2 3 4 5 6 7 8 9 1
0
80.5012
1.000000
| |********************|
1
-14.3270
-0.177972
| ****| |
Preliminary MSE
77.9514
Estimates of Autoregressive Parameters
Lag
Coefficient
Standard
Error
t Value
1
0.177972
0.064055
2.78
Algorithm converged.
SAS System
The AUTOREG Procedure
Maximum Likelihood Estimates
SSE
18474.378
DFE
236
MSE
78.28126
Root MSE
8.84767
SBC
1733.82498
AIC
1723.39559
MAE
6.81537191
AICC
1723.49772
MAPE
245.544664
HQC
1727.59835
Log Likelihood
-858.69779
Regress R-Square
0.2727
Durbin-Watson
2.0365
Total R-Square
0.2084
Observations
239
Parameter Estimates
Variable
DF
Estimate
Standard
Error
t Value
Approx
Pr > |t|
Intercept
1
-0.4281
0.4706
-0.91
0.3640
urateg
1
-0.5640
0.0619
-9.12
<.0001
AR1
1
0.2171
0.0656
3.31
0.0011
Autoregressive parameters assumed given
Variable
DF
Estimate
Standard
Error
t Value
Approx
Pr > |t|
Intercept
1
-0.4281
0.4706
-0.91
0.3640
urateg
1
-0.5640
0.0600
-9.41
<.0001
And I have no single idea what these means...
Is my data good to use? How do I know?? Please help me! Thanks!!
Ordinary Least Squares Estimates
SSE
19239.7836
DFE
237
MSE
81.18052
Root MSE
9.01002
SBC
1738.00254
AIC
1731.04961
MAE
6.98533005
AICC
1731.10046
MAPE
210.912182
HQC
1733.85145
Durbin-Watson
2.3543
Regress R-Square
0.1756
Total R-Square
0.1756
Explanation / Answer
If you see the two tables named "ordinary least square estimates" and "maximum likelihood estimates" , you can observe the R square values. In first table it is 0.1756 which means only about 17% of variation in data is explained by the model you fitted which implies its not well fitted.In other words the autoregressive model you have fit is useless. Again in the second table you observe the R square value is 0.2084,means only about 21% of the variation in the data is accounted by your model which is too less. So,dont worry about the other figures cause you need to fit another model or need to transform the data or use some other remedy accordingly
Related Questions
drjack9650@gmail.com
Navigate
Integrity-first tutoring: explanations and feedback only — we do not complete graded work. Learn more.