Lecture 15: Chapter 7, Section 1
Random Variables
Definitions,Notation
Probability Distributions
Application of Probability Rules
Mean and s.d. of Random Variables; Rules
©2011 Brooks/Cole, Cengage Learning Elementary Statistics: Looking at the Big Picture 1
Looking Back: Review
4 Stages of Statistics
Data Production (discussed in Lectures 1-4)
Displaying and Summarizing (Lectures 5-12)
Probability
Finding Probabilities (discussed in Lectures 13-14)
Random Variables
Sampling Distributions
Statistical Inference
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.2
Learning
Definition
Random Variable: a quantitative variable whose
values are results of a random process
Looking Ahead: In Inference, we’ll want to draw conclusions about
population proportion or mean, based on sample proportion or
mean. To accomplish this, we will explore how sample proportion
or mean behave in repeated samples. If the samples are random,
sample proportion or sample mean are random variables.
Looking Ahead: Sample proportion and
sample mean are very complicated random
variables. We start out by looking at much
simpler random variables.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.3
Learning
Definitions
Discrete Random Variable: one whose
possible values are finite or countably
infinite (like the numbers 1, 2, 3, …)
Continuous Random Variable: one
whose values constitute an entire (infinite)
range of possibilities over an interval
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.4
Learning
Notation
Random Variables are generally denoted with
capital letters such as X, Y, or Z.
The letter Z is often reserved for random
variables that follow a standardized
normal distribution.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.5
Learning
Example: A Simple Random Variable
Background: Toss a coin twice, and let the
random variable X be the number of tails
appearing.
Questions:
What are the possible values of X?
What kind of random variable is X?
Responses:
Possible values: 0, 1, 2
X is a discrete random variable.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.1a p.285 L15.6
Definitions
Probability distribution of a random
variable tells all of its possible values
along with their associated probabilities.
Probability histogram displays possible
values of a random variable along
horizontal axis, probabilities along vertical
axis.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.8
Learning
Definition
Probability distribution of a random
variable tells all of its possible values
along with their associated probabilities.
Looking Back: Last chapter we considered
individual probabilities like the chance of
getting two tails in two coin tosses. Now we take
a more global perspective, considering the
probabilities of all the possible numbers of tails
occurring in two coin tosses.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.9
Learning
Median and Mean of Probability Distribution
Median is the middle value, with half of
values above and half below (equal area
value on histogram).
Mean is average value (“balance point” of
histogram)
Mean equals Median for symmetric
distributions
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.10
Learning
Example: Probability Distribution of a Random
Variable
Background: The random variable X is the number of tails in
two tosses of a coin.
Questions:
What are the probabilities of the possible outcomes?
What is the probability distribution of X?
Responses: Possible outcomes:
Each has probability ¼ so the probability distribution is:
Non-overlapping “Or” RuleP(X=1)=1/2
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.1b p.285 L15.11
Example: Probability Distribution of a Random
Variable
Background: We have the probability distribution of the
random variable X for number of tails in two tosses of a coin.
Question: How do we display and summarize X?
Response: Use probability histogram.
Summarize: (center) mean=median=1
(spread) Typical distance from 1
is a bit less than 1.
(shape) unimodal, symmetric
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.3 p.286 L15.13
Notation; Permissible Probabilities and
Sum-to-One Rule for Probability Distributions
P(X=x) denotes the probability that the random variable X
takes the value x.
Any probability distribution of a discrete random variable X
must satisfy:
where x is any value of X
where are all possible values of X
According to this Rule, if a probability histogram has bars of
width 1, their total area must be 1.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.15
Learning
Interim Table
To construct probability distribution for more
complicated random processes, begin with
interim table showing all possible
outcomes and their probabilities.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.16
Learning
Example: Interim Table and Probability
Distribution
Background: A coin is tossed 3 times and the random
variable X is number of tails tossed.
Questions: What are the possible outcomes, values of X,
and probabilities? How do we find probability that X =1? X
=2?
Response:
Interim Table:
Use Non-overlapping “Or” { }
{ }
Rule to combine probabilities
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.5a p.286 L15.17
Example: Probability Distribution and
Histogram
Background: X is number of tails in 3 coin tosses.
Question: What are the probability distribution of X and
probability histogram?
Response: Use the interim table to determine probabilities.
Use the probability distribution
to sketch the histogram.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.5a-b p.286 L15.19
Example: Summaries from Probability
Histogram
Background: Histogram for number of tails in 3 coin tosses.
Question: What does it show?
Response:
Histogram has
Shape: symmetric, unimodal
Center: median = mean = 1.5 1.5
Spread:
Typical distance from mean a bit less than 1,
Looking Ahead: since 1 and 2 (which are more common) are only
Standard deviation of 0.5 away from 1.5; 0 and 3 (less common) are
R.V. to be introduced
later on.
1.5 away from 1.5.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.5c p.286 L15.21
Definition (Review)
Probability: chance of an event occurring,
determined as the
Proportion of equally likely outcomes comprising
the event; or
Proportion of outcomes observed in the long run
that comprised the event; or
Likelihood of occurring, assessed subjectively.
Looking Back: Principle of equally likely outcomes was
used to establish coin-flip probabilities. For other R.V.s,
like household size, the distribution has been constructed
for us based on long-run observations.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.23
Learning
Example: Different Ways to Assess Probabilities
Background: Census Bureau reported distribution of U.S.
household size in 2000.
Question: What is the difference between how these
probabilities have been assessed, and the way we assessed
probabilities for coin-flip examples?
Response: Coin-flip probabilities are based on
known properties of coin (two equally likely faces).
Household probabilities are based on
long-run observed outcomes (all households in U.S. in 2000).
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.7b p.287 L15.24
Probability Rules (Review)
Probabilities must obey
Permissible Probabilities Rule
Sum-to-One Rule
“Not” Rule
Non-Overlapping “Or” Rule
Independent “And” Rule
General “Or” Rule
General “And” Rule
Rule of Conditional Probability
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.26
Learning
Example: Permissible Probabilities Rule
Background: Household size in U.S. has
Question: How do these probabilities
conform to the Permissible Probabilities
Rule?
Response: All between 0 and 1.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.27
Learning
Example: Sum-to-One Rule
Background: Household size in U.S. has
Question: According to the “Sum-to-One”
Rule, what must be true about the
probabilities in the distribution?
Response: According to the Rule, we have
0.26+0.34+0.16+0.14+0.07+0.02+0.01=1
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.3a p.286 L15.29
Example: “Not” Rule
Background: Household size in U.S. has
Question: According to the “Not” Rule,
what is the probability of a household not
consisting of just one person?
Response:
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.31
Learning
Example: Non-Overlapping“Or” Rule
Background: Household size in U.S. has
Question: According to the Non-overlapping
“Or” Rule, what is the probability of having
fewer than 3 people?
Response: The probability of having fewer
than 3 people is P(X<3)
=P(X=1 or X=2)=P(X=1)+P(X=2)=0.26+0.34=0.60
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.8a-b p.287 L15.33
Example: Independent“And” Rule
Background: Household size in U.S. has
Question: Suppose a polling organization has sampled two
households at random. According to the Independent “And”
Rule, what is the probability that the first has 3 people and the
second has 4 people?
Response: The probability that the first has 3 people and the
second has 4 people is
P(X1=3 and X2=4)
=P(X1=3)P(X2=4)=(0.16)(0.14)=0.0224
where we use X1 to denote number in 1st household,
X2 to denote number in 2nd household.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.8e p.287 L15.35
Example: General“Or” Rule
Background: Household size in U.S. has
Question: Suppose a polling organization has sampled two
households at random. According to the General “Or” Rule,
what is the probability that one or the other has 3 people?
Response: The events overlap: it is possible that both
households have 3 people. P(X1=3 or X2=3) =
P(X1=3)+P(X2=3)-P(X1=3 and X2=3) =
0.16+0.16-(0.16)(0.16) = 0.2944
where we apply the Independent “And” Rule for P(X1=3
and X2=3).
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.8f p.287 L15.37
Example: Rule of Conditional Probability
Background: Household size in U.S. has
Question: Suppose a polling organization samples
only from households with fewer than 3 people.
What is the probability that a household with fewer
than 3 people has only 1 person?
Response: P(X=1 given X<3) =
P(X=1 and X<3) = 0.26 = 0.43
P(X<3) 0.26+0.34
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.8g p.287 L15.39
Mean and Standard Deviation of Random
Variable
Mean of discrete random variable X
Mean is weighted average of values, where each value
is weighted with its probability.
Standard deviation of discrete random variable X
Standard deviation is “typical” distance of values from
mean. Squared standard deviation is the variance.
Looking Back: Greek letters are used because these are the mean
and standard deviation of all the random variables’ values.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.41
Learning
Example: Mean of Random Variable
Background: Household size in U.S. has
Question: What is the mean household size?
Response: 1(0.26)+2(0.34)+…7(0.01) = 2.5 is the
mean household size.
Looking Back: Median is 2 (has 0.5 at or below it).
Mean is greater than median because distribution is
skewed right. Also, mean is less than the “middle”
number, 4, because smaller household sizes are weighted
with higher probabilities.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.10g-h p.288 L15.42
Example: Standard Deviation of R.V.
Background: Household size in U.S. has
Question: What is the standard deviation
of household sizes (typical distance from
the mean, 2.5)?
(a) 0.014 (b) 0.14 (c) 1.4 (d) 14.0
Response: The typical distance of
household sizes from their mean, 2.5,
is 1.4: the closest are 0.5 away (2 and 3),
the farthest is 4.5 away (7). (Or calculate
by hand or with software). Standard
deviation =1.4
A Closer Look: Skewed right most of the spread
arises from values above the mean, not below.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.15c p.288 L15.44
Rules for Mean and Variance
Multiply R.V. by constantits mean and
standard deviation are multiplied by same
constant [or its abs. value, since s.d.>0]
Take sum of two independent R.V.s
mean of sum = sum of means
variance of sum = sum of variances
(variance is squared standard deviation)
Looking Ahead: These rules will help us identify mean and
standard deviation of sample proportion and sample mean.
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.46
Learning
Example: Mean, Variance, and SD of R.V.
Background: Number X rolled on a die has
Question: What are the mean, variance, and
standard deviation of X?
Response:
Mean: same as median 3.5 (because symmetric)
Variance: 2.92 (found by hand or with software)
Standard deviation:1.7 (square root of variance)
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.12 p.288 L15.47
Example: Mean and SD for Multiple of R.V.
Background: Number X rolled on a die has mean 3.5, s.d. 1.7.
Question:What are mean and s.d. of double the roll?
Response: For double the roll, mean is s.d.
is
2(3.5) = 7,
2(1.7) = 3.4.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.15h-i p.289 L15.49
Example: Mean and SD for Sum of R.V.s
Background: Numbers X1, X2 on 2 dice each have mean 3.5,
variance 2.92.
Question:What are mean, variance, and s.d. of total on 2 dice?
Response:Mean variance
s.d. 3.5 + 3.5 = 7, 2.92 + 2.92 = 5.84,
square root of 5.84 = 2.4.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.84 p.340 L15.51
Example: Doubling R.V. or Adding Two R.V.s
Background: Double roll of a die: mean=7, s.d.= 3.4.
Total of 2 dice: mean=7, s.d.= 2.4.
Question: Why is double roll more spread than total of 2 dice?
Response: Doubling roll of 1 die makes extremes [2(1)=2 or
2(6)=12] more likely; totaling 2 dice tends to have low and high
rolls “cancel each other out”.
©2011 Brooks/Cole, Cengage
Learning
Elementary Statistics: Looking at the Big Picture Practice: 7.84b p.340 L15.53
Example: Doubling R.V. or Adding Two R.V.s
This is the key to the benefits of sampling many
individuals: The average of their responses gets us
closer to what’s true for the larger group.
If the numbers on a die were unknown, and you had
to guess their mean value, would you make a better
guess with a single roll or the average of two rolls?
?
? ?
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.55
Learning
Lecture Summary
(Random Variables)
Random variables
Discrete vs. continuous
Notation
Probability distributions: displaying, summarizing
Probability rules applied to random variables
Constructing distribution table
Mean and standard deviation of random variable
Rules for mean and variance
©2011 Brooks/Cole, Cengage Elementary Statistics: Looking at the Big Picture L15.56
Learning
