Você está na página 1de 14

Langkah-langkah Pemodelan Trend Analisis

Model Regresi
Regression Analysis: Data versus T
The regression equation is
Data = 146729 + 2179 T
Predictor
Constant
T

Coef
146729
2178.59

S = 33049.2

SE Coef
5122
52.58

R-Sq = 91.2%

T
28.64
41.44

P
0.000
0.000

R-Sq(adj) = 91.1%

Analysis of Variance
Source
Regression
Residual Error
Total

DF
1
166
167

SS
1.87534E+12
1.81314E+11
2.05666E+12

MS
1.87534E+12
1092252343

F
1716.95

P
0.000

Unusual Observations
Obs
37
102
133
158
164
165

T
37
102
133
158
164
165

Data
296647
298160
522497
573337
569753
579638

Fit
227337
368945
436481
490946
504017
506196

SE Fit
3569
2711
3606
4630
4896
4941

Residual
69310
-70785
86016
82391
65736
73442

St Resid
2.11R
-2.15R
2.62R
2.52R
2.01R
2.25R

R denotes an observation with a large standardized residual.

Residual Plots for Data


Normal Probability Plot

Versus Fits
100000

99.9
99

Residual

Percent

90
50
10

0
-50000

1
0.1

50000

-100000

-50000

0
Residual

50000

100000

100000

200000

Histogram
100000

18

Residual

Frequency

500000

Versus Order

24

12
6
0

300000
400000
Fitted Value

50000
0
-50000

-60000 -30000

0
30000
Residual

60000

90000

20

40

60 80 100 120 140 160


Observation Order

PLOT RESIDUAL
Probability Plot of RESI1
Normal

99.9

Mean
StDev
N
KS
P-Value

99

Percent

95
90
80
70
60
50
40
30
20
10
5
1
0.1

-100000

-50000

0
RESI1

50000

100000

-1.43440E-10
32950
168
0.054
>0.150

TIME SERIES PLOT


Time Series Plot of Data
600000

500000

Data

400000

300000

200000

100000
1

17

34

51

68

85
Index

102

119

136

153

PLOT ACF
Autocorrelation Function for Data

(with 5% significance limits for the autocorrelations)


1.0
0.8

Autocorrelation

0.6
0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8
-1.0
1

10

15

20
Lag

25

30

35

40

PLOT PACF
Partial Autocorrelation Function for Data

(with 5% significance limits for the partial autocorrelations)


1.0

Partial Autocorrelation

0.8
0.6
0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8
-1.0
1

10

15

20
Lag

25

30

35

40

TREND LINIER MODEL


Trend Analysis Plot for Data
Linear Trend Model
Yt = 146729 + 2179*t

600000

Variable
Actual
Fits

500000

Accuracy Measures
MA PE
9
MA D
27239
MSD
1079249339

Data

400000

300000
200000
100000
1

17

34

51

68

85 102 119 136 153


Index

TREND KUADRATIK MODEL


Trend Analysis Plot for Data

Quadratic Trend Model


Yt = 203289 + 182*t + 11.812*t**2
600000

Variable
Actual
Fits

500000

A ccuracy Measures
MAPE
6
MAD
16368
MSD
461904358

Data

400000

300000
200000
100000
1

17

34

51

68

85 102 119 136 153


Index

TREND GROWTH CURVE MODEL


Trend Analysis Plot for Data
Growth Curve Model
Yt = 179718 * (1.00660**t)

600000

Variable
Actual
Fits

500000

A ccuracy Measures
MAPE
6
MAD
18471
MSD
550548773

Data

400000

300000
200000
100000
1

17

34

51

68

85 102 119 136 153


Index

TREND MODEL S-CURVE


Trend Analysis Plot for Data

S-Curve Trend Model


Yt = (10**7) / (-1937.13 + 1988.56*(0.999893**t))
Variable
Actual
Fits

600000

Curve Parameters
Intercept
194458
A symptote
-5162
A sym. Rate
1

Data

500000
400000

Accuracy Measures
MAPE
5
MAD
16301
MSD
463296235

300000
200000
100000
1

2a.

17

34

51

68

85 102 119 136 153


Index

title1 'Intervention Data for Ozone Concentration';


title2 '(Box and Tiao, JASA 1975 P.70)';
data air;
input ozone @@;
label ozone = 'Ozone Concentration'
x1
= 'Intervention for post 1960 period'
summer = 'Summer Months Intervention'
winter = 'Winter Months Intervention';
date = intnx( 'month', '31dec1954'd, _n_ );
format date monyy.;
month = month( date );
year = year( date );
x1 = year >= 1960;
summer = ( 5 < month < 11 ) * ( year > 1965 );
winter = ( year > 1965 ) - summer;
datalines;
2.7 2.0 3.6 5.0 6.5 6.1 5.9 5.0 6.4 7.4 8.2
4.1 4.5 5.5 3.8 4.8 5.6 6.3 5.9 8.7 5.3 5.7
3.0 3.4 4.9 4.5 4.0 5.7 6.3 7.1 8.0 5.2 5.0
3.7 3.1 2.5 4.0 4.1 4.6 4.4 4.2 5.1 4.6 4.4
2.9 2.4 4.7 5.1 4.0 7.5 7.7 6.3 5.3 5.7 4.8
1.7 2.0 3.4 4.0 4.3 5.0 5.5 5.0 5.4 3.8 2.4
2.2 2.5 2.6 3.3 2.9 4.3 4.2 4.2 3.9 3.9 2.5
2.4 1.9 2.1 4.5 3.3 3.4 4.1 5.7 4.8 5.0 2.8
1.7 3.2 2.7 3.0 3.4 3.8 5.0 4.8 4.9 3.5 2.5
1.6 2.3 2.5 3.1 3.5 4.5 5.7 5.0 4.6 4.8 2.1
2.1 2.9 2.7 4.2 3.9 4.1 4.6 5.8 4.4 6.1 3.5
1.8 1.9 3.7 4.4 3.8 5.6 5.7 5.1 5.6 4.8 2.5
1.8 2.5 2.6 1.8 3.7 3.7 4.9 5.1 3.7 5.4 3.0
2.1 2.6 2.8 3.2 3.5 3.5 4.9 4.2 4.7 3.7 3.2
2.0 1.7 2.8 3.2 4.4 3.4 3.9 5.5 3.8 3.2 2.3
1.3 2.3 2.7 3.3 3.7 3.0 3.8 4.7 4.6 2.9 1.7
1.8 2.0 2.2 3.0 2.4 3.5 3.5 3.3 2.7 2.5 1.6
1.5 2.0 3.1 3.0 3.5 3.4 4.0 3.8 3.1 2.1 1.6
.
.
.
.
.
.
.
.
.
.
.
;
proc arima data=air;

3.9
5.7
4.7
4.0
2.7
2.0
2.2
2.9
2.4
1.4
1.9
1.5
1.8
1.8
2.2
1.3
1.2
1.3
.

/*--- Identify and seasonally difference ozone series ---*/


identify var=ozone(12) crosscorr=( x1(12) summer winter ) noprint;
/*--- Fit a multiple regression with a seasonal MA model ---*/
/*--by the maximum likelihood method ---*/
estimate q=(1)(12) input=( x1 summer winter )
noconstant method=ml itprint;
/*--- Forecast ---*/
forecast lead=12 id=date interval=month;
run;

3.
Intervention Data for Ozone Concentration
13:07 Sunday, January 3, 2012
(Box and Tiao, JASA 1975 P.70)

The ARIMA Procedure


Preliminary Estimation
Initial Moving Average
Estimates
Estimate
1

-0.29241

Initial Moving Average


Estimates
Estimate
12

0.40740

White Noise Variance Est

0.944969

Conditional Least Squares Estimation


Iteration
0
1
2
3
4

SSE
154.53
146.20
145.88
145.88
145.88

MA1,1

-0.29241
-0.29256
-0.30071
-0.29976
-0.29983

MA2,1
0.40740
0.59844
0.59239
0.59242
0.59234

NUM1
-1.13490
-1.20292
-1.26173
-1.26246
-1.26243

NUM2
-0.11731
-0.29784
-0.26252
-0.26150
-0.26154

NUM3
0.05581
-0.11572
-0.08247
-0.08197
-0.08196

Lambda
0.00001
1E-6
1E-7
1E-8
1E-9

R Crit
1
0.230552
0.046601
0.001345
0.000125

Maximum Likelihood Estimation


Iter
0
1
2
3
4

Loglike
-249.07778
-245.89135
-245.88484
-245.88482
-245.88481

MA1,1
-0.29983
-0.26830
-0.26653
-0.26689
-0.26684

MA2,1
0.59234
0.76634
0.76623
0.76661
0.76665

NUM1
-1.26243
-1.34490
-1.33046
-1.33070
-1.33062

NUM2
-0.26154
-0.23984
-0.23939
-0.23936
-0.23936

NUM3
-0.08196
-0.07578
-0.08025
-0.08020
-0.08021

Lambda
0.00001
1E-6
1E-7
1E-8
1E-9

R Crit
1
0.169445
0.008044
0.000603
0.000073

Lanjutan dari output Exempel SAS


ARIMA Estimation Optimization Summary
Estimation Method
Parameters Estimated
Termination Criteria
Iteration Stopping Value
Criteria Value
Alternate Criteria
Alternate Criteria Value
Maximum Absolute Value of Gradient
R-Square Change from Last Iteration
Objective Function
Objective Function Value
Marquardt's Lambda Coefficient
Numerical Derivative Perturbation Delta
Iterations

Maximum Likelihood
5
Maximum Relative Change in Estimates
0.001
0.000195
Relative Change in Objective Function
1.247E-8
0.00712
0.000073
Log Gaussian Likelihood
-245.885
1E-9
0.001
4

Intervention Data for Ozone Concentration


13:07 Sunday, January 3, 2012
(Box and Tiao, JASA 1975 P.70)

The ARIMA Procedure


Maximum Likelihood Estimation
Parameter

Estimate

Standard
Error

t Value

Approx
Pr > |t|

Lag

MA1,1
MA2,1
NUM1
NUM2
NUM3

-0.26684
0.76665
-1.33062
-0.23936
-0.08021

0.06710
0.05973
0.19236
0.05952
0.04978

-3.98
12.83
-6.92
-4.02
-1.61

<.0001
<.0001
<.0001
<.0001
0.1071

1
12
0
0
0

Variance Estimate
Std Error Estimate
AIC
SBC
Number of Residuals

0.634506
0.796559
501.7696
518.3602
204

Variable
ozone
ozone
x1
summer
winter

Shift
0
0
0
0
0

Lanjutan
Correlations of Parameter Estimates
Variable
Parameter
ozone
ozone
x1
summer
winter

MA1,1
MA2,1
NUM1
NUM2
NUM3

ozone
MA1,1

ozone
MA2,1

x1
NUM1

summer
NUM2

winter
NUM3

1.000
0.090
-0.039
0.062
-0.034

0.090
1.000
-0.169
0.211
0.022

-0.039
-0.169
1.000
-0.124
-0.107

0.062
0.211
-0.124
1.000
0.097

-0.034
0.022
-0.107
0.097
1.000

Autocorrelation Check of Residuals


Lag

Square

DF

6
12
18
24
30
36

7.47
10.21
14.53
19.99
27.00
32.65

4
10
16
22
28
34

To
ChiSq
0.1132
0.4220
0.5593
0.5834
0.5180
0.5336

ChiPr >
--------------------Autocorrelations-------------------0.017
-0.024
0.054
0.003
-0.072
0.022

0.054
-0.059
0.006
-0.074
-0.035
-0.099

0.043
-0.047
-0.110
-0.074
0.023
-0.006

Model for variable ozone


Period(s) of Differencing

12

No mean term in this model.


Moving Average Factors
Factor 1: 1 + 0.26684 B**(1)
Factor 2: 1 - 0.76665 B**(12)

0.101
0.014
0.028
0.098
-0.028
0.087

-0.022
0.032
-0.042
-0.038
-0.107
-0.046

0.140
0.072
0.043
0.043
0.100
0.053

Intervention Data for Ozone Concentration


13:07 Sunday, January 3, 2012
(Box and Tiao, JASA 1975 P.70)
The ARIMA Procedure
Input Number 1
Input Variable
Period(s) of Differencing
Overall Regression Factor

x1
12
-1.33062

Input Number 2
Input Variable
Overall Regression Factor

summer
-0.23936

Input Number 3
Input Variable
Overall Regression Factor

winter
-0.08021

Forecasts for variable ozone


Obs
217
218
219
220
221
222
223
224
225
226
227
228

Forecast

Std Error

1.4205
1.8446
2.4567
2.8590
3.1501
2.7211
3.3147
3.4787
2.9405
2.3587
1.8588
1.2898

0.7966
0.8244
0.8244
0.8244
0.8244
0.8244
0.8244
0.8244
0.8244
0.8244
0.8244
0.8244

95% Confidence Limits


-0.1407
0.2287
0.8408
1.2431
1.5342
1.1053
1.6989
1.8629
1.3247
0.7429
0.2429
-0.3260

2.9817
3.4604
4.0725
4.4748
4.7659
4.3370
4.9306
5.0946
4.5564
3.9746
3.4746
2.9057

Você também pode gostar