Assignment - Week 10
Assignment - Week 10
NPM : 2206009391
Assignment 9
1) Causal forecasting models are based on a regression model framework, where the variable
of interest depends on one or more explanatory variables. Is it true?
Answer: TRUE
Explanation: Causal forecasting models assume that the variable of interest depends on one
or more explanatory variables that "cause" the forecasts. On the other hand, noncausal
forecasting models are purely time series models in the sense that the forecasts are made
based only upon historical data concerning the variable of interest.
Answer: D
Observations of any variable recorded over time in sequential order are considered a time
series. The time period can be a year, a quarter, a month, a week, a day, or even an hour.
3) The following table includes the information about a monthly time series.
What is the forecast for May when the three-month moving average method is applied?
Answer
An m-period moving average is computed as
Moving Average =
17+19+24
Moving Average=
3
80
Moving Average= =20
3
4) The following table shows the annual revenues (in millions of dollars) of a pharmaceutical
company over the period 1990–2011.
Year 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000
Revenue 830 791 842 891 953 1,036 1,050 1,070 1,127 1,272 1,386
Year 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011
Revenue 1,304 1,379 1,417 1,441 1,525 1,613 1,870 1,593 1,595 2,132 2,330
The scatterplot indicates that the annual revenues have an increasing trend. Linear,
exponential, quadratic, and cubic models were fit to the data starting with t = 1, and the
following output was generated.
Which of the following is a revenue forecast for 2012 found by the polynomial trend equation
with the best fit?
Answer:
Cubic Regression Model
Tc=648 ,7662+91 , 726 x 23+−5 , 7477 x 23 2+0 ,2153 x 23 3
Tc=648 ,7662+2109,698−3040,533+2619,555
Tc = 2337,486
About 2 billion and 337 million dollars
Explanation: The linear, quadratic, and cubic trend equations are polynomial. The cubic
equation always has better MSE and mostly better MAD than the linear and quadratic
equations, so both MSE and MAD are not used to make the comparison. Instead, the adjusted
R2 is used. After concluding on the best polynomial trend equation, substitute its coefficients
by their estimates available from the accompanying table.
1.
Let positive daily S&P 500 returns define up days, and negative daily S&P 500 returns define
down days. A stockbroker wants to know if the up and down days of the S&P 500 occur
randomly. For 30 trading days, there were 17 up days, 13 down days, four runs of up days,
and four runs of down days.
a. Specify the competing hypotheses to determine whether the S&P 500 up and down days
occur at random.
b. What is the value of the Wald-Wolfowitz runs test statistic?
c. At the 5% significance level, what is the decision and conclusion?
Jawaban:
a. The competing hypotheses are
H0: Up and down days occur randomly;
HA: Up and down days do not occur randomly.
b. We have
Rd =Ru =4
R=R d + Ru
R=4+ 4
R=8
Karena jumlah up and down keduanya setidaknya 10,asumsikan bahwa R mengikuti
distribusi normal dengan rata-rata:
n n
μ R= d u +1
n
13 x 17
μ R= +1
30
μ R=8,367
σ R=
√ n d nu (2 nd nu −n)
2
n ( n−1)
σ R =√ 13 x 17 ¿¿ ¿
σ R =1,868
Answer:
a. The competing hypotheses:
H0: p ≥ 0.5
HA: p < 0.5
b. The proportion of plus signs adalah:
x
p=
n
1
p=
14
p=0,0714
Dan statistic valuenya adalah
p−0,50
z=
0,50
√n
0,0714−0,50
z=
0,50
√ 14
z=−3,207
c. At the 1% significance level
critical valuenya adalah
–2.576.
The p-value is
P(Z ≤ −3.207) = 0.0007.
Reject null hypothesis. Kita dapat menyimpulkan stockbroker self-confidence meningkat
karena seminar
3.
A study was conducted to determine if husbands and wives like the same TV shows. Married
couples ranked 15 TV shows, and the Spearman rank correlation coefficient was found to be
rs = 0.47.
a. Specify the competing hypotheses to determine if there is a positive correlation between
the two rankings.
b. Assuming the Spearman rank correlation coefficient follows a normal distribution, what
are the mean and standard deviation of the normal distribution?
c. Assuming the Spearman rank correlation coefficient follows a normal distribution, what is
the value of the test statistic?
d. At the 5% significance level, what is the decision and conclusion?
Answer:
a. The competing hypotheses
H0: ρs ≤ 0
HA: ρs > 0
b. Dengan asumsi distribusi sampel koefisien korelasi peringkat Spearman dapat
diperkirakan dengan distribusi normal, rata-rata nol dan standar deviasi adalah ≈
0,2673. c. Value dari statistic test adalah:
z=r s √ n−1
z=0,47 √15−1
z ≈1,7586
A real estate agent wants to know how the home size (in square feet) of parents compares to
the home size of their children. For a sample of seven parents and their children, the value of
the test statistic for the Wilcoxon signed-rank test for a matched pairs sample is T = T+ = 27.
The differences are calculated as the parent's home size subtracted by the child's home size.
a. Specify the competing hypothesis to determine if the median difference in home size
between parents and children is greater than zero.
b. At the 5% significance level, what is the critical value?
c. At the 5% significance level, what is the decision and conclusion?
Answer:
a. The competing hypotheses:
H0: mD ≤ 0
HA: mD > 0.
b. For a sample size of n = 7 and a 5% significance level for a one-tailed test, using the
table for the critical values for the Wilcoxon signed-rank test we find the critical value
TU = 25. Note that the p-value is between 0.01 and 0.025.
Two-Tailed Test One-Tailed Test
n α=
α = 0,5 α = 0,01 α = 0,01
0,5
5 -- -- 0 --
6 0 -- 2 --
7 2 -- 3 0
8 3 0 5 1
9 5 1 8 3
10 8 3 10 5
11 10 5 13 7
12 13 7 17 9
13 17 9 21 12
14 21 12 25 15
15 25 15 30 19
16 29 19 35 23
17 34 23 41 27
18 40 27 47 32
19 46 32 53 37
20 52 37 60 43
c. Since T > TU reject the null hypothesis. Kami menyimpulkan bahwa perbedaan median
ukuran rumah antara orang tua dan anak-anak lebih besar dari nol.