Scribd
Upload
38 views6 pages

Figure 1. Original Series of Gold Prices

The document presents results from time series analysis of gold price data. It includes figures and tables showing the original price series, first differenced series, autocorrelation functions, unit root tests, ARIMA model identification and fitting. The ARIMA(6,1,1) model was found to best fit the first differenced series based on having the lowest AIC and SIC values.

Uploaded by

x2
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
38 views6 pages

Figure 1. Original Series of Gold Prices

The document presents results from time series analysis of gold price data. It includes figures and tables showing the original price series, first differenced series, autocorrelation functions, unit root tests, ARIMA model identification and fitting. The ARIMA(6,1,1) model was found to best fit the first differenced series based on having the lowest AIC and SIC values.

Uploaded by

x2
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Figure 1.

Original series of gold prices

2,000.0
1,800.0
1,600.0
1,400.0
1,200.0
1,000.0
800.0
600.0
400.0
200.0
0.0

Figure 2. First difference series of gold prices


250
200
150
100
50
0

GoldPrice

-50
-100
-150
-200
-250

Figure 3. Sample ACF and PACF for original gold price data

Figure 4 Sample ACF and PACF for gold price series in the first difference.

Table-1: Augmented Dickey-Fuller test for the original gold price data
Null Hypothesis: GOLDPRICE has a unit root
Exogenous: Constant
Lag Length: 1 (Automatic based on SIC, MAXLAG=13)
t-Statistic
Augmented Dickey-Fuller test statistic
-0.620746
Test critical values:
1% level
-3.469451
5% level
-2.878618
10% level
-2.575954
*MacKinnon (1996) one-sided p-values.

Prob.*
0.8616

Table-2: Augmented Dickey-Fuller test for the gold price series in the first difference
Null Hypothesis: D(GOLDPRICE) has a unit root
Exogenous: Constant
Lag Length: 1 (Automatic based on SIC, MAXLAG=13)
t-Statistic
Augmented Dickey-Fuller test statistic
-15.52339
Test critical values:
1% level
-3.469451
5% level
-2.878618
10% level
-2.575954
*MacKinnon (1996) one-sided p-values.

Prob.*
0.0000

Table-3: Model identification and Coefficient Estimates for ARIMA (p d q) Models


ARIMA (p d q)
(1, 1, 1)
(1, 1, 2)
(1, 1, 3)
(2, 1, 1)
(2, 1, 2)
(2, 1, 3)

AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)

Coefficients
0.106047
-0.441020
-0.296879
-0.236397
-0.245517
0.101481
-0.093900
-0.319091
0.239066
-0.427767
-0.109091
0.144297

t-value
0.463007
-2.134855
-3.675108
-2.871710
-3.069583
1.227456
-1.103118
-3.938108
0.660331
-1.263958
-1.304945
1.712438

AIC
10.67960

SIC
10.73850

10.66644

10.72535

10.69518

10.75409

10.68022

10.73938

10.75480

10.81396

10.74729

10.80645
4

(3, 1, 1)
(3, 1, 2)
(3, 1, 3)
(4, 1, 1)
(4, 1, 2)
(4, 1, 3)
(5, 1, 1)
(5, 1, 2)
(5, 1, 3)
(6, 1, 1)
(6, 1, 2)
(6, 1, 3)

AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)
AR term (p)
MA term (q)

0.133269
-0.344045
0.190634
-0.147873
0.448660
-0.231910
-0.190062
-0.302480
-0.241404
-0.126036
-0.224696
0.103312
0.090020
-0.363054
0.089824
0.157534
0.089824
0.157534
0.220617
-0.348688
0.199419
-0.208918
0.259375
0.212981

1.633356
-4.425587
2.226769
-1.705487
1.488713
-0.702514
-2.268055
-3.799197
-2.936047
-1.532243
-2.667543
1.222146
1.063088
-4.678860
0.965559
-2.546003
1.056538
1.889657
2.655773
-4.477398
2.358548
-2.505328
3.069211
2.513623

10.67453

10.73395

10.73495

10.79437

10.74109

10.80051

10.66648

10.72617

10.72355 10.78323
10.72565

10.78533

10.69707

10.75701

10.77408

10.83403

10.76961

10.82955

10.66445

10.72466

10.74926

10.80947

10.72477

10.78498

Table-4: Statistical Results for ARIMA (6 1 1) Models


Dependent Variable: GOLDPRICE
Method: Least Squares
Sample (adjusted): 7 156
Included observations: 150 after adjustments
Convergence achieved after 7 iterations
Backcast: 6
Variable
Coefficient Std. Error t-Statistic
Prob.
C
9.567548
3.397195
2.816308
0.0055
AR(6)
0.220617
0.083071
2.655773
0.0088
MA(1)
-0.348688
0.077877 -4.477398
0.0000
Durbin-Watson stat
1.962464 Akaike info criterion
10.66445
F-statistic
12.15826 Schwarz criterion
10.72466
Prob(F-statistic)
0.000013

You might also like