Concordia University

Department of Electrical and Computer Engineering

ENGR 371 - Probability and Statistics
Drs. Lynch and Ghrayeb
Final Examination April 29, 2010

1) (10 Marks) In a particular area, there are just three makes of cars available: Ford (60% of the total), Renault
(30%) and Honda (10%). The carburetors on Fords have a 0.09 probability of failure, those on Renaults
have a 0.05 chance and those on Hondas have a 0.02 chance of failure. If a car with a failed carburetor is
selected at random, what is the probability that it is a Ford?

2) (10 Marks) A multiple-choice quiz has 200 questions each with 4 possible answers of which only 1 is the
correct answer. What is the probability that sheer guesswork yields from 25 to 30 correct answers for 80
of the 200 problems about which the student has no knowledge? [HINT: approximation may be helpful
here]

3) (10 Marks) Let X and Y represent two random variables whose joint density function is

- , , / 24xy, 0 < x < l , 0 < y < l , x + y < l

fxY^y) = \ o, elsewhere

a) Find fy(y).
b) Are X and Y independent? Explain.
c) Find P(Y < \\X = § ) .

4) (10 Marks) Two independent experiments are being run in which two different types of paints are compared.
Eighteen specimens are painted using type A and the drying time, in hours, is recorded on each. The same
is done with type B .
a) Suppose that the population standard deviations are both known to be 1.0. Assuming that the mean
drying time is equal for the two types of paint, find P(XA~ XB > 1-0), where XA and XB are average .
drying times for samples of size TIA = TIB = 18.
b) Repeat Part (a) w h e n the population standard deviations are unknown, but they are still equal and
estimated to be s — 0.96.

5) (10 Marks) A random sample of 100 automobile owners shows that, in the province of Quebec, an automobile
is driven on the average 2 3 , 500 kilometers per year with a standard deviation of 3900 kilometers.
a) Construct a 9 9 % confidence interval for the average number of kilometers an automobile is driven
annually in Quebec.
b) What can we assert with 9 9 % confidence about the possible size of our error if we estimate the average
number of kilometers driven by car in Quebec to be 2 3 , 500 kilometers per year?

6) (10 Marks) The life in hours for a battery is known to be normally distributed with standard deviation a — 1
hours. A random sample of 16 batteries has a mean life of x — 20.3 hours.
a) Test H : \i = 20 versus Hi : fi > 20 for a = 0.05.
0

b) What is the P-value of the test in part (a)?

c) What is the (3 error for the test in part (a) if the true m e a n is 20.75 hours?
 F o r m u l a S h e e t for E N G R 3 7 1 - Fall 2 0 1 0

• T h e number of permutations of n distinct objects taken r at a time is P n r = (n-r)i •

The number of distinct permutations of n things of which n\ are of one kind, n are of a second kind, . . . , 2

rik are of a k kind is n i !ri2 !---nfc!

th

• T h e number of combinations of n distinct objects taken r at a time is (™) = r ! ^l ); •

r

• P(A UBUC) = P(A) + P(B) + P{C) - P{A n B ) - P(A DC)- P(B n C ) + P ( A n B fl C), where A, 5 ,
and C are any three events.

P ( A | B ) - « P ( Bf) =
~ P(B) where P ( B ) * 0.

• If the events B±,B2, • • •, Pfc constitute a partition of a sample space S such that P{Bi) ^ 0 for i = 1 , 2 , . . . , fc,
then for any event A of 5, P(J4) = £ P(Bi C) A) = J2 P(A\Bi)P(Bi).
i—l i=l

• Bayes's Rule: If the events B^Bi,... constitute a partition of a sample space 5 such that P(Bi) ^ 0
for i = 1 , 2 , . . . , k, then for any event A of S such that P ( A ) 7^ 0

P \A)=
{BT ^ni) , , forr=1)2) ...,*
• P ( x ) = P ( X < a:) where X is a random variable and F(x) is its cumulative distribution function.

• f(x) = P(X = x) is the probability density (distribution or mass) function of random variable X.

• E[X] = J2 f( ) x x
where X is a discrete random variable.
all x

• E[g(X)] = 53 g(x)f(x) where X is a discrete random variable.

all x

E[X] — J xf(x)dx where X is a continuous random variable.

• a - E[(X - fi y] is the variance of X where X is a random variable.

2
x

• Binomial distribution: b(x;n,p) = i^)p q ~ with x n x

\i — np and a = npq. 2

• Geometric distribution: g(x\p) = pq ~ x 1

) x = 1 , 2 , 3 , . . . with yb — l/p and <7 = (1 — p)/p . 2
2

• Negative binomial: f(x) = ( * I i ) p g ~ \ x = r, r + 1, r + 2 , . . . with (JL = r/p and a — r ( l — p)/p .

r ,:E 7 2 2

• Poisson Distribution: A) = - — w i t h \i — A and <r = A. 2

• Normal distribution: f(x) = -jL^e"^'^'l 2(j2

• The distribution of an exponential random variable X is given by

f(x) = l[ P
0,
' *
elsewhere
> U

where ft > 0.

• The mean of an exponential random variable X is f3 and its variance is ft . 2

• The covariance between random variables X and Y is

a X Y = E[(X-fi )(Y- x fi )] = E [XY] - fJ-xHy

Y
 The correlation between random variables X and Y is

PXY
(JXO'Y

If X i , X2, .. ., X n represent a random sample of size n, then the sample variance is defined by the statistic

b
- ~ i
where X is t h e sample mean.

Let X i , X2, . . . X be independent random variables that are all normal with mean fi and standard
n

deviation a. Then the random variable T = x-n£• has t— distribution with v = n — 1 degrees of freedom.
q /

• If z is the mean of a random sample of size n from a population with known variance a , a (1 — a) 100%
2

confidence interval for \i is given by

_ (J _ (J

where z /
a 2 is the z-value leaving an area of a/2 to the right.

• One sided confidence bounds:

• A 100(1 — a) % upper-confidence bound for \i is

a
/JL < X + Z a —=

A 100(1 — a)% lower-confidence bound for \i is

In the case a 2
is unknown, the above expression becomes

£ - *a/2,n-l"7= < M < ^ + *a/2,n-l—P

where s is the sample standard deviation.