Scribd
Upload
62 views2 pages

Plotting The ACF and The PACF. Here We Look at The Four Times Series From One Homework Problem

The document discusses using Minitab tools to fit ARMA and ARIMA models to time series data. It shows the autocorrelation and partial autocorrelation plots for four time series. It then demonstrates fitting ARIMA models to each series automatically in Minitab by specifying limits for the p and q values and amount of differencing. The results of the ARIMA model fitting are displayed for each time series, with estimated coefficients, standard errors, t-values and p-values shown.

Uploaded by

totokmulyono
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
62 views2 pages

Plotting The ACF and The PACF. Here We Look at The Four Times Series From One Homework Problem

The document discusses using Minitab tools to fit ARMA and ARIMA models to time series data. It shows the autocorrelation and partial autocorrelation plots for four time series. It then demonstrates fitting ARIMA models to each series automatically in Minitab by specifying limits for the p and q values and amount of differencing. The results of the ARIMA model fitting are displayed for each time series, with estimated coefficients, standard errors, t-values and p-values shown.

Uploaded by

totokmulyono
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

MinitabtoolsforfittingARMAandARIMAmodels:(9/30/09)

Autocorrelation Function for TS_1

Partial Autocorrelation Function for TS_1

(with 5% significance limits for the autocorrelations)

(with 5% significance limits for the partial autocorrelations)

1.0

1.0

0.8

0.8

0.6

0.6

Partial Autocorrelation

Autocorrelation

1.PlottingtheACFandthePACF.Herewelookatthefourtimesseriesfromonehomeworkproblem.

0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8

10

15

20

25
Lag

30

35

40

45

-0.4
-0.6

50

10

15

20

25
Lag

30

35

40

Autocorrelation Function for TS_2

Partial Autocorrelation Function for TS_2


(with 5% significance limits for the partial autocorrelations)

1.0

1.0

0.8

0.8

0.6

0.6

0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8

45

50

(with 5% significance limits for the autocorrelations)

Partial Autocorrelation

Autocorrelation

0.0
-0.2

-1.0
1

0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8

-1.0

-1.0
1

10

15

20

25
Lag

30

35

40

45

50

10

15

20

25
Lag

30

35

40

Autocorrelation Function for TS_3

Partial Autocorrelation Function for TS_3


(with 5% significance limits for the partial autocorrelations)

1.0

1.0

0.8

0.8

0.6

0.6

0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8

45

50

(with 5% significance limits for the autocorrelations)

Partial Autocorrelation

Autocorrelation

0.2

-0.8

-1.0

0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8

-1.0

-1.0
1

10

15

20

25
Lag

30

35

40

45

50

10

15

20

25
Lag

30

35

40

Autocorrelation Function for TS_4

Partial Autocorrelation Function for TS_4


(with 5% significance limits for the partial autocorrelations)

1.0

1.0

0.8

0.8

0.6

0.6

0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8

45

50

(with 5% significance limits for the autocorrelations)

Partial Autocorrelation

Autocorrelation

0.4

0.4
0.2
0.0
-0.2
-0.4
-0.6
-0.8

-1.0

-1.0
1

10

15

20

25
Lag

30

35

40

45

50

10

15

20

25
Lag

30

35

40

45

50

2.FittinganARMAmodelautomatically.Herewelookatthesamefourtimeseriesagain.Tofitthe
model,selectARIMAintheTimeSeriesmenuunderStatinMinitab.Wemustspecifyupperlimits
forpandqandtheamountofdifferencing,ifany.AnARIMAmodelisamodelinwhichtakingoneor
morelag1differencesleadstoanARMAmodel.
TimeSeries#1:HereIusedlimitsof2and2forpandq.
Final Estimates of Parameters
Type
AR
1
AR
2
MA
1
MA
2
Constant
Mean

Coef
-0.0083
-0.0388
-0.9739
-0.9821
-0.05664
-0.05409

SE Coef
0.0737
0.0743
0.0228
0.0040
0.09854
0.09411

T
-0.11
-0.52
-42.75
-244.29
-0.57

P
0.910
0.603
0.000
0.000
0.566

TimeSeries#2:HereIusedlimitsof1and1.(Thefittingfailedwithlimitsof2and2.)
Final Estimates of Parameters
Type
AR
1
MA
1
Constant
Mean

Coef
0.1589
0.1990
-0.02493
-0.02964

SE Coef
1.7078
1.6949
0.05596
0.06654

T
0.09
0.12
-0.45

P
0.926
0.907
0.656

TimeSeries#3:HereIusedlimitsof1and1.
Final Estimates of Parameters
Type
AR
1
MA
1
Constant
Mean

Coef
0.7615
-0.0169
-0.02675
-0.1121

SE Coef
0.0602
0.0924
0.04400
0.1844

T
12.64
-0.18
-0.61

P
0.000
0.855
0.544

TimeSeries#4:HereIusedlimitsof1and1,togetherwith1roundofdifferencing.
Final Estimates of Parameters
Type
AR
1
MA
1
Constant

Coef
0.1814
0.2226
-0.02573

SE Coef
1.6419
1.6274
0.05457

T
0.11
0.14
-0.47

Differencing: 1 regular difference

P
0.912
0.891
0.638

You might also like