ADVANCED BUSINESS RESEARCH

ASSIGNMENT 1

KASHLATIF
BL164017

Chapter 2 Problems Solutions

Question 1
(i)

(ii)

In my opinion, Education of the woman's parents, her income, her marital status, her
job, etc. are all likely to be contained in u. I think these factors determine the number
of children she has. Many of the factors are likely to be correlated with a woman's
level of education. Education of the woman's parents, certainly correlated. Marital
status: correlated. Job: correlated.
Because the omitted explanatory variables are contained in u, and because these
variables are also correlated with education of woman, the regression will not reveal a
causal relationship.

QUESTION 3
(i)
SUMMARY
OUTPUT
Regression Statistics
Multiple R
0.76
R Square
0.577
Adjusted R
Square
0.507
Standard
Error
0.269
Observation
s
8
ANOVA
df
Regression

Residual
Total

6
7

Coefficie
nts
Intercept
ACT

0.568
0.102

SS
0.59402
5
0.43472
5
1.02875

MS
0.59
4
0.07
2

Standar
d Error

t
Stat

0.92842
1
0.03569

0.61
2
2.86

F
8.1986
22

P-value
0.5630
36
0.0286

Significan
ce F
0.028677

Lower
95%
-1.70363
0.014863

Uppe
r
95%
2.84
0.19

Lower
95.0%
1.7036
3
0.0148

Upper
95.0%
3
0

77

63

0= 0.57; 1 = 0.1
The direction of the relationship is positive, as expected. Students with a higher ACT score have
a higher GPA. If the ACT score is zero the GPA would be 0.57, I think this interpretation is not
useful. And If the ACT score increases by 5 points, I expect to observe a 0.5 point increase in
GPA (= 0.1 *5).
(iii) The predicted value of GPA when ACT = 20 is
0.57 + 0.1*20 = 2.57
Even though we don't have an observation with ACT = 20, we can predict using our model.
(iv)About 58% of the variation in GPA is explained by ACT. We see this in the R-squared
statistic, which represents the proportion of the total variation in GPA that is explained
by all the explanatory variables. Since we only have one explanatory variable, R-squared
gives us exactly what the question is looking for.
Question 4
(i)The predicted birth weight when cigs = 0 is 119.77 ounces (7.5 lbs). When cigs = 20,
The predicted birth weight is equal to 119.77 - 0.514 * 20 = 109.5 ounces (6.8 lbs).
I can see from this that mother smoking cigarette is very bad for babys health and weight.
(ii) The regression captures a causal relationship between the child's birth weight and the
mother's smoking habits unless the mother's smoking habits are positively related to
other unobserved factors which also negatively influence birth weight.
(iii) 125 = 119.77 -0.514 *cigs
Solve for cigs:
cigs = -10.2 Smoking cigarettes cannot be negative, so there are other factors in unobserved
factors which effect the health of baby.
(iv) this does not help reconcile your finding from part (iii). So even though some children a
certainly born with birth weights above 120, our model doesn't say much about them. All of the
stuff that causes children to be born heavier than about 120 ounces is unobservable in our model.
Question 5
(i) The marginal propensity to consume when income is zero is -124.84 | when you aren't
making any money, you de-consume (you sell stuff). It is possible.
(ii) Consumption when income is $30,000 is given by

= -124.84 + 0.853*30000 = 25465.16

i.e. $25,465.16.
(iii) Graphing MPC against income is just graphing a constant number (0.853) against income.
That is at line at 0.853.
Question 6
(i)The coefficient of log(distance) is the estimated elasticity of price with respect to distance. It
implies that 1 % increase in the distance increases the price of house by 0.853%-the usual
interpretation of elasticity.
(ii)I think simple regression provides an unbiased estimator of the ceteris paribus elasticity of
price with respect to dist.
(iii) Location of house, quality of building can affect the price of house but they seems
uncorrelated with the distance from the incinerator.
Question 2