STA2604 2022 TL 014 0 B Assignment 2
Uploaded by
Ntokozo VilankuluSTA2604 2022 TL 014 0 B Assignment 2
Uploaded by
Ntokozo VilankuluSTA2604/014/0/2022
Tutorial letter 014/0/2022
Forecasting II
STA2604
Year module
Department of Statistics
ASSIGNMENT 02 QUESTIONS
university
Define tomorrow. of south africa
STA2604: Forecasting II
ASSIGNMENT 02
Unique Nr.: 836033
Fixed closing date: 02 September 2022
QUESTION 1
The past 18 weekly sales .yt / for a product are given in the following table.
Week Sales Week Sales
1 98 10 170
2 100 11 200
3 110 12 190
4 150 13 220
5 140 14 210
6 160 15 260
7 200 16 258
8 150 17 270
9 156 18 240
Assume that the model applicable to these data is given by the equation yt D 0 C 1t C t where
t indicates time (here week) with t D 1; 2; : : : ; 18.
(1.1) Use the method of least squares to estimate 0 and 1, then write down the fitted model. [8]
(1.2) Calculate the point forecast and the 95% prediction interval for product sale in week 19. [10]
(1.3) Calculate the coefficient of determination R 2 and the adjusted coefficient of determination
2 .
Radj [10]
(1.4) Test for positive autocorrelation by using the Durbin-Watson statistic with D 0:05. [12]
[40]
2
STA2604/014/0/2022
QUESTION 2
The data in the table below come from the comparison of the growth rates for bacteria types A
and B. The growth y recorded at five equally spaced (and coded) points of time is shown in the
following table.
Time
Bacteria type 2 1 0 1 2
A 8:2 9:3 9:1 10:2 10:6
B 10:1 10:5 12:4 12:7 14:1
(2.1) Fit the linear model
yD 0 C 1 x1 C 2 x2 C 3 x1 x2 C
where x1 D 1 refers to bacteria type B and x1 D 0 refers to bacteria type A, and x2 refers to
the coded time. Use Excel. [6]
(2.2) Predict the growth of type A bacteria at time x2 D 0 and compare the answer with the ob-
served value. [3]
(2.3) Calculate the residuals and plots them against the fitted values. [6]
(2.4) Calculate a 90% confidence interval for the expected growth for type B at time x2 D 1. [4]
(2.5 Calculate a 90% prediction interval for the expected growth for type B at time x2 D 1. [4]
(2.6) Compare the results in parts (2.4) and (2.5). [2]
[25]
3
QUESTION 3
The quarterly sales .yt / on five years, where t denotes time, of a product are given in the following
table:
Year Quarter yt
1 1 12
2 31
3 42
4 21
2 1 13
2 33
3 45
4 19
3 1 15
2 36
3 52
4 21
4 1 15
2 37
3 52
4 22
5 1 24
2 40
3 50
4 23
Assume that the model that fits the data is given by equation
yt D 0 C 1t C 2 Q2 C 3 Q3 C 4 Q4 C t (E)
where Q 2 , Q 3 , and Q 4 are the appropriately defined dummy variables for quarters 2, 3 and 4.
Statistical softwares may give similar results, but here only use excel.
(3.1) Write down the definitions of the dummy variables Q 2 , Q 3 and Q 4 . [6]
(3.2) Plot yt against t for t D 1; 2; : : : ; 20. Use Excel. [4]
(3.3) What type of seasonal variation appears to exist? Explain your answer. [3]
(3.4) Fit model (E), then write down the prediction model. Use Excel. [8]
(3.5) Use the results in part (3.4) to calculate b
y21 and its 95% prediction interval. [9]
[30]
Total: [95]
