Module 10: Discrete Random Variables + Normal Review

(10.1) Discrete Random Variables

Def. A random variable has a finite or countable

list of possible values.

Def. The of a discrete random variable lists all

possible values of X and their probabilities.

A probability distribution must satisfy two rules:

1. Every probability is between and .

2. All probabilities add to .

ex. Grades in a very large statistics class follow this distribution.

Grade A B C D F

Grade points X 4 3 2 1 0
Probability .15 .35 .30 .16 .04

1. Is this a legitimate probability distribution? Why?

2. Find P (X < 3).

3. Find P (X ≤ 3).
 M10 - 2

(10.2) Probability Histograms

A histogram shows the probability distribution of a

discrete random variable.

ex. Draw the probability histogram for the grade-points distribution.

P (x)
.40

.30

.20

.10

x
0 1 2 3 4

x 0 1 2 3 4

P (X = x) .04 .16 .30 .35 .15

Class activity. Which grade point value has the largest probability?
What does that mean in context?
 M10 - 3

(10.3) Mean or Expected Value

Def. The of a discrete random variable is its long-

run average value.

X
µ= xP (x).

ex. Find the expected grade points for the class.

x 4 3 2 1 0

P (x) .15 .35 .30 .16 .04

µ = (4)(.15) + (3)(.35) + (2)(.30) + (1)(.16) + (0)(.04)

µ=

Interpret this value in context.

 M10 - 4

(10.4) When Is a Count Binomial?

A binomial random variable counts the number of successes in a fixed

number of trials.

Conditions for a binomial distribution:

1. There is a fixed number of trials, n.

2. The trials are independent.
3. Each outcome is either a success or a failure.
4. The probability of success, p, is the same for every trial.

If these conditions hold, then

X = number of successes ∼ Binomial(n, p).

ex. For each situation, decide whether X is binomial. If yes, identify

n and p.

1. Toss a fair coin 20 times and record the number of heads.

2. Toss a fair coin until we see 10 heads. Record the number of tosses.

3. Guess on a 50-question multiple-choice exam with 4 choices per

question. Count the number correct.
 M10 - 5

(10.5) The Binomial Formula

If X ∼ Binomial(n, p), then

 
n x
P (X = x) = p (1 − p)n−x, x = 0, 1, 2, . . . , n.
x

The number of ways to arrange x successes among n trials is

 
n n!
= .
x x!(n − x)!

NOTE: 0! = 1 and 1! = 1.

The mean and standard deviation of a binomial random variable are

p
µ = np, σ= np(1 − p).

Mini-challenge. What does x represent in the binomial formula?

 M10 - 6

(10.6) Binomial Example: Three Coin Tosses

Toss a fair coin three times and let X = number of heads.

1. Write all possible outcomes.

2. Write the sample space for X.

3. Complete the probability distribution.

x 0 1 2 3

P (X = x)

4. Use the binomial formula to find P (X = 2).

 
3
P (X = 2) = (.5)2(.5)1 =
2
5. Find the mean and standard deviation.

µ = np =

p
σ= np(1 − p) =
 M10 - 7

(10.7) Binomial Example: Medication Side Effects

A medication causes side effects in 35% of patients. Eight patients at a

clinic are currently receiving the medication. Let

X = number of patients who experience side effects.

1. Is X binomial? What assumptions do we need?

2. What are n and p?

3. Write the sample space for X.

4. How many patients would we expect to experience side effects?

µ = np =
5. Find the standard deviation.
p
σ= np(1 − p) =
 M10 - 8

(10.8) More Binomial Practice

Continue using X ∼ Binomial(8, .35).

1. Find the probability that exactly 6 patients experience side effects.

 
8
P (X = 6) = (.35)6(.65)2
6

2. Find the probability that exactly 3 patients experience side effects.

 
8
P (X = 3) = (.35)3(.65)5
3

3. Find the probability that at least one patient experiences side effects.

P (X ≥ 1) = 1 − P (X = 0)
 M10 - 9

(10.9) Normal Review: SAT Scores

SAT section scores are approximately normal with mean 500 and stan-
dard deviation 100.

X ∼ N (500, 100).

1. What proportion of students score above 700?

700 − 500
z= =
100
Area to the left:
Area to the right:

2. What proportion of students score between 400 and 500?

z400 = , z500 =

3. What score corresponds to the top 10%?

Cumulative probability to the left:
z-score:

x = µ + zσ =
 M10 - 10

(10.10) Normal Review: Central Areas

Continue with SAT scores, X ∼ N (500, 100).

1. Between what two values will we find the central 95% of scores?

2. Between what two values will we find the central 90% of scores?
Hint: central 90% leaves 5% in each tail.

z.05 = , z.95 =

Lower cutoff =

Upper cutoff =

SAT score
500 − 3100

500 − 2100

500 − 100

500

500 + 100

500 + 2100

500 + 3100
 M10 - 11

(10.11) Can This Distribution Be Normal?

ex. Camera prices have a mean of $500 and a standard deviation of

$200.

Could the distribution of camera prices be normal? Explain.

NOTE: A normal distribution extends in both directions forever. If

a normal model would give a realistic chance of impossible values, we
should be cautious.

ex. A bottle-filling machine fills lotion bottles labeled 236 mL. Suppose
the bottle contents are approximately normal.

1. If the machine mean is set at 236 mL, about what percent of bottles
are underfilled?

2. Why might a company set the machine mean slightly higher than
the label amount?
 M10 - 12

(10.12) Module 10 Review

Idea Meaning

Discrete random variable Finite or countable possible values

Probability distribution Lists values and probabilities
P
Expected value Long-run average, µ = xP (x)
Binomial distribution Counts successes in fixed indepen-
dent trials
Binomial mean µ = np
p
Binomial standard devia- σ = np(1 − p)
tion
Normal review Use z = (x − µ)/σ and table areas

Class activity. In your own words, explain the difference between a

discrete random variable and a continuous random variable.