In: Statistics and Probability
QUESTION THREE
The administration of an inner-city college has generally assumed
that the average age of a student is no more than 20 years. The
standard deviation of the age of students is known to be 3.6 from
previous data. However, lately the students have appeared to be
older than before, and some administrators say that the average age
could be higher than 20 years. You collect a random age sample of
50 students and calculate a mean of 20.76. At the 90% level of
confidence, can you conclude that the average age of students has
indeed
increased?
[10 Marks]
Describe briefly two purposive sampling techniques
with their uses and limitations.
[5
Marks]
Football fans of both Dockers and Eagles were asked their opinion
of the quality of the facilities at the Subiaco Oval. The following
table cross-classifies the information provided by the fans.
Outstanding
Good
Fair
Unsatisfactory
Total
Dockers
27
35
33
25
120
Eagles
13
15
27
25
80
Total
40
50
60
50
200
At the 99% level of confidence is there a relationship
between the opinion of the quality of the oval and the club the fan
supports?
[10
Marks]
QUESTION FOUR
Give five advantages of a completely randomized design, CRD.
[5 Marks]
Suppose you are interested in developing a counselling
technique to reduce stress within marriages. You randomly select
two samples of married individuals out of ten churches in the
association. You provide Group 1 with group counselling and study
materials. You provide Group 2 with individual counselling and
study materials. At the conclusion of the treatment period, you
measure the level of marital stress in the group members. Here are
the scores:
Group
1
Group 2
:
24.13
22.88
:
5.64
6.14
Are these groups significantly different in marital
stress? Test at 5% level of significance.
[10 Marks]
A manufacturer claims that the average weight of a tin of baked
beans is 440 g and the standard deviation is known to be 20 g. From
a random sample of 100 cans you calculate the average weight to be
435 g. At the 95% level of confidence, is there a change in the
average weight of a can of baked
beans?
[10 Marks]
QUESTION FIVE
A machine which fills orange squash bottles should be set to
deliver 725 ml. A sample of 50 bottles is checked and the mean
quantity is found to be 721 ml and the sample s.d. is 13 ml. Does
this differ significantly from 725 ml at the 1% level? Find the
probability of Type I error for this
test.
[10 Marks]
Prove the formula. [5 Marks]
A random sample of 10 hot drinks from Dispenser A had a mean volume of 203ml and a standard deviation of 3ml. A random sample of 15 hot drinks from Dispenser B gave corresponding values of 206ml and 5ml. The amount dispensed by each machine maybe assumed to be normally distributed. Test at the 5% significance level, the hypothesis that there is no difference in the variability of the volume dispensed by the two machines.
[10 Marks]
QUESTION SIX
A scientist, working in an agricultural research station, believes
there is a relationship between the hardness of the shell of eggs
laid by chickens and the amount of a certain food supplement put
into the diet of the chickens. He selects ten chickens of the same
breed and collects the data given below:
Chicken
A
B
C
D
E
F
G
H
I
J
Food supp x(g)
7.0
9.8
11.6
17.5
7.6
8.2
12.4
17.5
9.5
19.5
Hardness of shells y
1.2
2.1
3.4
6.1
1.3
1.7
3.4
6.2
2.1
7.1
Calculate the equation of the regression line of y on x
Calculate the correlation coefficient, (r).
Calculate the coefficient of determination and interpret its meaning
6)
ΣX | ΣY | Σ(x-x̅)² | Σ(y-ȳ)² | Σ(x-x̅)(y-ȳ) | |
total sum | 120.60 | 34.60 | 186.92 | 44.30 | 90.77 |
mean | 12.06 | 3.46 | SSxx | SSyy | SSxy |
a)
sample size , n = 10
here, x̅ = Σx / n= 12.060 ,
ȳ = Σy/n = 3.460
0.286898839
SSxx = Σ(x-x̅)² = 186.9240
SSxy= Σ(x-x̅)(y-ȳ) = 90.8
estimated slope , ß1 = SSxy/SSxx = 90.8
/ 186.924 = 0.48562
intercept, ß0 = y̅-ß1* x̄ =
-2.39658
so, regression line is Ŷ = -2.3966
+ 0.4856 *x
b) correlation coefficient , r = SSxy/√(SSx.SSy) = 0.9975
c) R² = (SSxy)²/(SSx.SSy) = 0.9950
Approx 99.50% of variation in variable y is explained by variable X