0% found this document useful (0 votes)
14 views5 pages

ITSM Software Data Analysis Models

The document presents an analysis of various datasets using ARMA and GARCH models, including wine sales, accidental deaths, signal data, U.S. population, strikes, and lake data. Each plot reveals distinct trends and seasonal patterns, with notable findings such as upward trends in wine sales and seasonal peaks in accidental deaths. Additionally, regression models are applied to lake and U.S. population data to identify trends and fluctuations.

Uploaded by

shivam125156
Copyright
© All Rights Reserved
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
0% found this document useful (0 votes)
14 views5 pages

ITSM Software Data Analysis Models

The document presents an analysis of various datasets using ARMA and GARCH models, including wine sales, accidental deaths, signal data, U.S. population, strikes, and lake data. Each plot reveals distinct trends and seasonal patterns, with notable findings such as upward trends in wine sales and seasonal peaks in accidental deaths. Additionally, regression models are applied to lake and U.S. population data to identify trends and fluctuations.

Uploaded by

shivam125156
Copyright
© All Rights Reserved
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

NAME:T.

HARIKISHAN REDDY
[Link]: 125156038

ITSM SOFTWARE EXPLORATION

Plot 1 (WINE)
# of Data Points = 142
Sample Mean = .1478E+04..
Sample Variance = .281998E+06
[Link](Sample Mean) = .103981E+03
MODEL:
ARMA Model:
X(t) = Z(t)
Garch Model for Z(t):
Z(t) = sqrt(h(t)) e(t)
h(t) = 1.000000
{e(t)} is IID N(0,1)

It appears from the graph that the sales have an upward trend and
a seasonal pattern with a peak in July and a trough in January.
zero mean model cant be used

Plot 2 (DEATH)
# of Data Points = 72
Sample Mean = .8788E+04
Sample Variance = .905656E+06
[Link](Sample Mean) = .168390E+03
MODEL:
ARMA Model:
X(t) = Z(t)
Garch Model for Z(t):
Z(t) = sqrt(h(t)) e(t)
h(t) = 1.000000
{e(t)} is IID N(0,1)

the monthly accidental death figures show a strong seasonal pattern, with the maximum for
each year occurring in July and the minimum for each year occurring in February. The presence
of a trend is much less apparent than in the wine sales.

It shows a repeating annual pattern with peaks in July and troughs in February, strongly
suggesting a seasonal factor with period 12
PLOT 3 (SIGNAL)
# of Data Points = 200
Sample Mean = .0189
Sample Variance = 1.140845
[Link](Sample Mean) = .124599
MODEL:
ARMA Model:
X(t) = Z(t)
Garch Model for Z(t):
Z(t) = sqrt(h(t)) e(t)
h(t) = 1.000000
{e(t)} is IID N(0,1)

The waveform of the signal is quite close to that of the true signal in this case, although its
amplitude is somewhat smaller.

PLOT 4 (USPOP)

# of Data Points = 21

Sample Mean = .8578E+08


Sample Variance = .587522E+16
[Link](Sample Mean) = .301090E+08
MODEL:

ARMA Model:
X(t) = Z(t)
Garch Model for Z(t):
Z(t) = sqrt(h(t)) e(t)
h(t) = 1.000000
{e(t)} is IID N(0,1)

The graph suggests the possibility of fitting a quadratic or exponential trend to the data
The graph of the population data, contains no apparent periodic [Link] mean model
cant be used

PLOT 5 (STRIKES)
# of Data Points = 30
Sample Mean = .4503E+04
Sample Variance = .676789E+06
[Link](Sample Mean) = .283595E+03
MODEL:
ARMA Model:
X(t) = Z(t)
Garch Model for Z(t):
Z(t) = sqrt(h(t)) e(t)
h(t) = 1.000000
{e(t)} is IID N(0,1)

The annual numbers of strikes in the U.S.A. for the years 1951–1980 appear to fluctuate
erratically about a slowly changing level.

PLOT 6 (LAKE)
# of Data Points = 98
Sample Mean = 9.0041
Sample Variance = 1.720177
[Link](Sample Mean) = .299376
MODEL:
ARMA Model:
X(t) = Z(t)
Garch Model for Z(t):
Z(t) = sqrt(h(t)) e(t)
h(t) = 1.000000
{e(t)} is IID N(0,1)

There are two interesting features of the graph of the residuals. The first is the absence of any
discernible trend. The second is the smoothness of the graph

Plot 7 (regression model [Link])

Method: Least Squares


Y(t) = M(t) + X(t)
Trend Function:
M(t) = 10.202037 t^0 - .024201111 t^1
ARMA Model:
X(t) = Z(t)
WN Variance = 1.000000
Fig 1-9

Method: Generalized Least Squares


Y(t) = M(t) + X(t)
Trend Function:
M(t) = 10.202037 t^0 - .024201111 t^1
ARMA Model:
X(t) = Z(t)
WN Variance = 1.000000
Coeff Value Std Error
0 10.20203661 .20358661
1 -.02420111 .00357087

Plot 8 (regression model [Link])


Method: Least Squares
Y(t) = M(t) + X(t)
Trend Function:
M(t) = .69579203E+07 t^0 - .21598699E+07 t^1 + .65063386E+06 t^2
ARMA Model:
X(t) = Z(t)
WN Variance = 1.000000
Coeff Value
0 .69579203E+07
1 -.21598699E+07
2 .65063386E+06

PLOT 9:(HARMONIC REGRESSION-DEATHS)


ITSM::(Regression estimates)
Method: Least Squares

Y(t) = M(t) + X(t)

Trend Function:
M(t) = .27174620E+18 t^0
+ .16568958E+34 Cos(2*pi*t0/N) + .00000000 Sin(2*pi*t0/N)
- .16568958E+34 Cos(2*pi*t0/N) + .00000000 Sin(2*pi*t0/N)

ARMA Model:
X(t) = Z(t)
WN Variance = 1.000000

Coeff Value
0 .27174620E+18
1 .16568958E+34
2 .00000000
3 -.16568958E+34
4 .000

You might also like