QUANT READINESS COURSE

PROFESSOR JEAN-PAUL BALDWIN

 1

FUNCTIONS
1.1 - FUNCTIONS: INTRODUCTION

• We often describe one quantity in terms of another.

• The amount of your paycheck if you are paid hourly depends on the
number of hours you worked.
• The cost at the gas station depends on the number of gallons of gas
pumped into your car.
• The distance traveled by car moving at a constant speed depends on the
time traveled.

• Generalizing, if the value of the variable y depends on the value of the

variable x, then y is the dependent variable and x is the independent
variable.
1.2 - FUNCTIONS: NOTATION

• We use the notation 𝑦 = 𝑓 𝑥 called function notation, to express this

and read as “f of x.”

• Examples:

𝑓 𝑥 = 2𝑥 + 3
𝑓 𝑥 = −𝑥 ! + 5𝑥 − 3
1.2 - FUNCTIONS:

Graphing in Two Dimensions:

• A clear way to graph the functional relationship between two variables is
with a graph.

• We do this by using the Cartesian Coordinate System.

• The independent variable is measured in terms of horizontal distance.
• The dependent variables is measured in terms of vertical distance.
1.2 - FUNCTIONS:

Each of the pairs of numbers (3,1), (-5,6) and (4,-1) is an example of an

ordered pair.

The position of any point in this plane is determined by referring to the

horizontal number line, the x-axis, and the vertical number line, the y-
axis.
1.3 - LINEAR FUNCTIONS:

• A function that can be defined by 𝑓(𝑥) = 𝑚𝑥 + 𝑏 for real numbers m

(slope) and b (intercept) is a linear function.

• Example: 𝑥 − 4𝑦 = 5

Qqqq x – 4y = 5
-4y = -x + 5
" $
y = #𝑥 − #
1.3 - LINEAR FUNCTIONS:

• A linear function defined by 𝑓 𝑥 = 𝑏 (whose graph is a horizontal line) is

sometimes called a constant function. The domain of any linear function
is (−∞, +∞).

• Examples: 𝑦 = 5
1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

• Consider two linear functions:

(a) 𝑦 = 𝑓 𝑥
(b) 𝑦 = 𝑔 𝑥

• There are an infinite number of (x,y) pairs that

satisfies equation (a) and an infinite number that
satisfies equation (b)

• But, there is only one pair that satisfies both

equations.
1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

• Consider two linear functions:

(a) 𝑦 = 𝑓 𝑥
(b) 𝑦 = 𝑔 𝑥

• There are an infinite number of (x,y) pairs that

satisfies equation (a) and an infinite number that
satisfies equation (b)

• But, there is only one pair that satisfies both

equations

• That is the point where the graphs for the two

equations intersect (𝑥 ∗ , 𝑦 ∗ )
1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

• There are three possibilities for the solution set of linear system in two
variables.
1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

The two graphs intersect in a single

point. The coordinates of this point
give the only solution of the system. In
this case the system is consistent, and
the equations are independent.
1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

The graphs are parallel lines. In this

case the system is inconsistent; that
is, there is no solution common to
both equations of the system.
1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

The graphs are the same line. In this

case the equations are dependent,
since any solution of one equation of
the system is also a solution of the
other.
1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

Linear systems can be solved algebraically by the substitution

method.
Step 1: Solve one of the equation for either variable.

Step 2: Substitute for that variable in the other equation. The result should be
an equation with just one variable.

Step 3: Solve the equation from Step 2.

Step 4: Find the other value. Substitute the result from Step 3 into the
equation from Step 1.

Step 5: Check the solution in both of the original equation.

1.3 - LINEAR FUNCTIONS: SOLVING SYSTEMS OF EQUATIONS

Example:
Solve the system: 3𝑥 + 2𝑦 = 13
4𝑥 − 1𝑦 = −1

Step 1: Step 4: y = 4x + 1 => 4(1) + 1 = 5

4x – 1y = -1
-1y = -4x -1
y = 4x + 1

Step 2: Step 5: 3(1) + 2(5) = 13

3x + 2y = 13 4(1) - 1(5) = -1
3x + 2(4x+1) = 13

Step 3:
3x + 8x + 2 = 13
1.4 - NON-LINEAR FUNCTIONS: NOTATION

• In this previous section, we studied linear (first-degree polynomial)

functions, defined as 𝑓 𝑥 = 𝑚𝑥 + 𝑏. Now we consider more general
polynomial functions.

• A polynomial function of degree n is defined by:

• 𝑓 𝑥 = 𝑎& 𝑥 & + 𝑎&'"𝑥 &'" + ⋯ + 𝑎"𝑥 + 𝑎(
• For real numbers 𝑎& , 𝑎&'", … , 𝑎" and 𝑎( where 𝑎( ≠ 0 and n is a whole
number.
1.4 - NON-LINEAR FUNCTIONS: NOTATION

• Polynomial function can be used to approximate data.

• They are usually valid for small intervals, and they allow us to predict
what might happen for values just outside the intervals.
1.4 - NON-LINEAR FUNCTIONS: NOTATION

Example:
The number of airports in the United Stated during the period from 1970
through 1997 can be approximated by the polynomial function defined by:

𝑓 𝑥 = −6.77𝑥 ! + 445.34𝑥 + 11,279

where x = 0 represents 1970, x = 1 represents 1971, and so on. Use this

function to approximate the number of airports in each given year.
1.4 - NON-LINEAR FUNCTIONS: NOTATION

Example: 𝑓 𝑥 = −6.77𝑥 ! + 445.34𝑥 + 11,279.82

Year X Output
1970 0 11279
1971 1 11718.39
1972 2 12143.4
. . .
. . .
. . .
2003 33 18603.5
1.4 - NON-LINEAR FUNCTIONS: EVALUATING

• Another polynomial function, defined by 𝑓 𝑥 = 𝑥 !, is the squaring

function. For this function, every real number is paired with its square.
The input can be any real number, so the domain is (−∞,+∞).
1.4 - NON-LINEAR FUNCTIONS: EVALUATING

• The cubing function is defined by 𝑓 𝑥 = 𝑥 ). Every real number is

paired with its cube. The domain and range are both (−∞,+∞).
 2

Describing Sets of
Data
2.1 – CATEGORICAL DATA: SUMMARIZING & VISUALIZING

• Two methods for summarizing and visualizing include graphical and

numerical.
2.1 – CATEGORICAL DATA: SUMMARIZING & DISPLAYING

• Frequency Table: Records counts for each of the categories of the

variable.
• Consider the dataset below:
CEO Company Age Salary (millions $) Degree
1 Lorene Schultz Jones General Partners 60 40 Bachelors
2 Darren Francis HP Gorgan Base Bank 64 27 MBA
3 Penny Kelly Macrosoft 41 22 Masters
4 Lauren French Rosewood Capital 54 19.4 PhD
5 Herbert Perkins Forest Retailers 67 16.3 MBA
6 James Lynch Pear 56 15 MBA
7 Elias Olson CX Enterprises 57 14.5 Bachelors
. . . . . .
. . . . . .
. . . . . .
47 Ray Jimenez Global Travel Agents 47 0.8 Bachelors
48 Wayne Mccoy Commonwealth Joe Coffee 48 0.7 MBA
49 Yolanda Hogan Mario Brothers Bagels 62 0.7 Bachelors
50 Toni Park Unicorn Inc 32 0.5 None
2.1 – CATEGORICAL DATA: SUMMARIZING & DISPLAYING

Degree Frequency Percent Cumulative Percent

Bachelors 14 28 28
Law 3 6 34
Masters 9 18 52
MBA 15 30 82
None 3 6 88
PhD 6 12 100
2.1 – CATEGORICAL DATA: SUMMARIZING & DISPLAYING

• Area Principle:

Area Principle:

Area occupied by a part of the

graph should correspond to
the magnitude of the value it
represents.
2.1 – CATEGORICAL DATA: SUMMARIZING & DISPLAYING

• Bar and Pie Chart:

2.2 – CATEGORICAL DATA: EXPLORING TWO VARIABLES

• Contingency Tables (cross tabulation / crosstab).

• Matrix format that displays frequency distributions of variables.

• Shows how individuals are distributed along each variable depending on,
or contingent on, the value of all other variables.
2.2 – CATEGORICAL DATA: EXPLORING TWO VARIABLES

Sport Preference

Football Soccer Rugby

USA 33 10 9 52

Country South Korea 10 35 10 55

Australia 12 9 32 53

55 54 52 160
2.3 – QUANTITATIVE DATA: GRAPHICAL MEASURES

• Pie charts and bar charts are not compatible with quantitative data.

• Histogram: Categories are divided into intervals and the counts of these
intervals are plotted as the height of the bars.

• Stem-and-Leaf Plot: Similar to histograms; however, they also show the

individual values.
2.3 – QUANTITATIVE DATA: GRAPHICAL MEASURES

• Examples:
Stem Leaf
2 9
3 024456788
4 0111224577788
5 0002334556667888
6 0112224579
7 0
2.4 – QUANTITATIVE DATA: CENTRAL TENDENCY

• Most numerical methods used to describe quantitative data sets

measure one of two data characteristics:

• The central tendency of the set of measurements.

• The variability – the spread of the data.

• Important central tendencies include the mean, median, mode.

2.4 – QUANTITATIVE DATA: CENTRAL TENDENCY

• Mean – The sum of measurement divided by the number of

observations contained in the data set.
𝑆𝑎𝑚𝑝𝑙𝑒 𝑚𝑒𝑎𝑛 𝑥̅ 𝑃𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑚𝑒𝑎𝑛 µ

• Median – The middle number of the measurements arranged in

ascending (or descending) order.

• Mode – The measurement that occurs most frequently in the data set.
2.4 – QUANTITATIVE DATA: CENTRAL TENDENCY

CEO Age
Mean 49.8
Standard Error 1.538883773
Median 50
Mode 41
Standard Deviation 10.88155151
Sample Variance 118.4081633
Kurtosis -0.942645546
Skewness -0.108636665
Range 41
Minimum 29
Maximum 70
Sum 2490
Count 50
2.4 – QUANTITATIVE DATA: CENTRAL TENDENCY

• Detecting Skewness by Comparing the Mean and the Median

If the data set is

skewed to the right,
then the median is
less than the mean.
2.4 – QUANTITATIVE DATA: CENTRAL TENDENCY

• Detecting Skewness by Comparing the Mean and the Median

If the data set is

symmetric, the
mean equals the
median.
2.4 – QUANTITATIVE DATA: CENTRAL TENDENCY

• Detecting Skewness by Comparing the Mean and the Median

If the data set is

skewed to the left,
the mean is less
than (to the left of)
the median.
2.5 – QUANTITATIVE DATA: VARIANCE & STANDARD DEVIATION

• Measures of central tendency only provides a limited description of

the data.
• We need to understand the variability (or spread) of the data to help visualize the
shape of the data.

• Range: The range of the data is equal to the largest measurement

minus the smallest measurement.

• Sample Variance: The sample variance of n measurements is equal to

the sum of the squared deviations from the mean divided by (n-1).
2.5 – QUANTITATIVE DATA: VARIANCE & STANDARD DEVIATION

∑ & !
89"(𝑥8 − 𝑥)
̅
𝑠! =
𝑛−1

∑&89"(𝑥8 − 𝑥)̅ !
𝑠=
𝑛−1

• Example: (𝑥" − 𝑥)̅ ! +(𝑥! − 𝑥)̅ ! +(𝑥# − 𝑥)̅ !

!
𝑠 =
2
𝑥" = 60 𝑥! = 64 𝑥) = 41 ⇒ 𝑥̅ = 55 (60 − 55)! +(64 − 55)! +(41 − 55)!
𝑠! =
2

(%)!'(()!'("))!
𝑠! = = 151
!
2.5 – QUANTITATIVE DATA: VARIANCE & STANDARD DEVIATION

• Symbols for Population and Standard Deviations

𝑠! = 𝑆𝑎𝑚𝑝𝑙𝑒 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒
𝑠 = 𝑆𝑎𝑚𝑝𝑙𝑒 𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛
𝜎! = 𝑃𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒
𝜎 = 𝑃𝑜𝑝𝑢𝑙𝑎𝑡𝑖𝑜𝑛 𝑠𝑡𝑎𝑛𝑑𝑎𝑟𝑑 𝑑𝑒𝑣𝑖𝑎𝑡𝑖𝑜𝑛
2.6 – QUANTITATIVE DATA: INTERPRETING THE STANDARD DEVIATION

• Chebyshev’s Rule vs. Empirical Rule

• Chebyshev’s Rule applies to any data set, regardless of the shape of the
frequency distribution of the data.

• Empirical Rule is a rule of thumb that applies to data sets with frequency
distributions that are mound-shaped and symmetric.
2.6 – QUANTITATIVE DATA: INTERPRETING THE STANDARD DEVIATION

• Chebyshev’s Rule

• No useful information is provided on the fraction of measurement that

fall within 1 standard deviation of the mean.
• At least 75% will fall within 2 standard deviation of the mean.
• At least 8/9 of the measurements will fall within 3 standard deviations of
the mean.
2.6 – QUANTITATIVE DATA: INTERPRETING THE STANDARD DEVIATION

• Empirical Rule

• Approximately 68% of the measurements will fall within 1 standard

deviations of the mean.
• Approximately 95% of the measurements will fall within 2 standard
deviations of the mean.
• Approximately 99.7% of the measurements will fall within 3 standard
deviations of the mean.
2.6 – QUANTITATIVE DATA: INTERPRETING THE STANDARD DEVIATION

• Example:

𝑥̅ = 49.8 49.8 ± 1. 10.88 = 38.92, 60.68

𝑠 = 10.88 49.8 ± 2. 10.88 = 28.04, 71.56
49.8 ± 3. 10.88 = 17.16, 82.44
 3

Probability
3.1 – PROBABILITY: INTRODUCTION

• For any random phenomenon, each attempt, or trial, generates an

outcome.
• An event refers to outcomes or combinations of outcomes.
• The collection of all possible outcomes is referred to as the sample
space.
3.1 – PROBABILITY: INTRODUCTION

• Examples Applicant FICO Score Qualify? Running

% Qualify
1 760 Yes 100
2 620 No 50
3 770 Yes 67
. . . .
. . . .
99 640 No 46
100 740 Yes 47
3.1 – PROBABILITY: INTRODUCTION

• For one applicant: Applicant FICO Score Qualify? Running

% Qualify
𝑆 = {𝑄, 𝑁) 1 760 Yes 100
2 620 No 50
• For two applicants: 3 770 Yes 67
. . . .
𝑆 = {𝑄𝑄, 𝑄𝑁, 𝑁𝑄, 𝑁𝑁) . . . .
99 640 No 46
• For three applicants: 100 740 Yes 47

𝑆 = {𝑄𝑄𝑄, 𝑄𝑄𝑁, 𝑄𝑁𝑄, 𝑁𝑄𝑄, 𝑄𝑁𝑁, 𝑁𝑄𝑁, 𝑁𝑁𝑄, 𝑁𝑁𝑁)

3.1 – PROBABILITY: INTRODUCTION

• Law of Large Numbers: If the events are independent, then as the

number of trials increase, the long run relative frequency of any
outcome gets closer and closer to a single value.
3.2 – PROBABILITY RULES

Rule 1: A probability is a number between 0 and 1.

0≤𝑃 𝐴 ≤1

Rule 2: The probability of the set of all possible outcomes must be 1.

𝑆𝑡𝑜𝑐𝑘 𝑖𝑛𝑐𝑟𝑒𝑎𝑠𝑒, 𝑠𝑡𝑜𝑐𝑘 𝑑𝑒𝑐𝑟𝑒𝑎𝑠𝑒, 𝑠𝑡𝑜𝑐𝑘 𝑠𝑎𝑚𝑒 ⇒ 𝑃 𝑆 = 1

Rule 3: The probability of an event occurring is 1 minus the probability

that it does not occur.
𝑃 𝐴 = 1 − 𝑃(𝐴* )
3.2 – PROBABILITY RULES

Rule 4: 𝑃 𝐴 ∩ 𝐵 = 𝑃 𝐴 . 𝑃(𝐵), provided that A and B are independent.

𝐴 = 𝐶𝑢𝑠𝑡 1 𝑞𝑢𝑎𝑙𝑖𝑓𝑖𝑒𝑠 𝐵 = 𝐶𝑢𝑠𝑡 2 𝑞𝑢𝑎𝑙𝑖𝑓𝑖𝑒𝑠 𝑃(𝐴 ∩ 𝐵) = 𝑃 𝐴 . 𝑃(𝐵)

Rule 5: 𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃(𝐵), provided that A and B are disjoint.

A B

Rule 6: 𝑃 𝐴 ∪ 𝐵 = 𝑃 𝐴 + 𝑃 𝐵 − 𝑃 𝐴 ∩ 𝐵 for any two events A and B.

3.3 – CONDITIONAL PROBABILITY

• The event probabilities discussed thus far are often called

unconditional probabilities, as there has been no special conditions
assumed, other those that define the experiment.

• Sometimes, we have added knowledge that might affect the likelihood of

the outcome of an experiment, so we need to alter the probability of an
event of interest.
3.3 – CONDITIONAL PROBABILITY

Example:
The event of observing an even number (event A) on a toss of a fair die is
½.

1/6 1/6 1/6 1/6 1/6 1/6

3.3 – CONDITIONAL PROBABILITY

• Suppose now we have the added (or given) information that on a

particular throw of the die, the result was a number less than or equal to
3 (event B).

• Would the probability of observing an even number on that throw of the

die still be equal to ½?

1/6 1/6 1/6 1/6 1/6 1/6

1/3 1/3 1/3

3.3 – TO FIND THE CONDITIONAL PROBABILITY

• To find the conditional probability that event A occurs given that event B
occurs, divide the probability that both A and B occur by the probability
that B occurs – that is:

P(A|B) = (P(A ∩ B))/(P(B)) or

P(B |A)= (P(A ∩ B))/(P(A))
3.3 – CONDITIONAL PROBABILITY

• Rule 7: General Multiplication Rule

𝑃 𝐴 ∩ 𝐵 = 𝑃 𝐴 . 𝑃 𝐵 𝐴) for any two events A and B

3.3 – CONDITIONAL PROBABILITY

Example:
Would the probability of observing an even number on that throw of the
die still be equal to ½?

1
𝑃(𝐴 ∩ 𝐵) 𝑃(2) 6 1
𝑃 𝐴 𝐵) = = = =
𝑃(𝐵) 𝑃(1) + 𝑃 2 + 𝑃(3) 1 + 1 + 1 3
6 6 6
3.3 – CONDITIONAL PROBABILITY

Example:
To develop programs for business travelers staying at convention hotels, a
major hotel chain commissioned a study of executives who play golf. The
study revealed that 55% of the executives admitted they had cheated at
golf. Also, 20% of the executives admitted that they had cheated at golf
and had lied in business. Given an executive had cheated at golf, what is
the probability that the executive also had lied in business?

𝐿𝑒𝑡 𝐴 = {𝑒𝑥𝑒𝑐𝑢𝑡𝑖𝑣𝑒 𝑤ℎ𝑜 ℎ𝑎𝑑 𝑐ℎ𝑒𝑎𝑡𝑒𝑑 𝑎𝑡 𝑔𝑜𝑙𝑓}

𝐿𝑒𝑡 𝐵 = {𝑒𝑥𝑒𝑐𝑢𝑡𝑖𝑣𝑒 𝑤ℎ𝑜 ℎ𝑎𝑑 𝑙𝑖𝑒𝑑 𝑖𝑛 𝑏𝑢𝑠𝑖𝑛𝑒𝑠𝑠}

𝑃(𝐴 ∩ 𝐵) .2
𝑃 𝐵 𝐴) = = = .365
𝑃(𝐴) .55
3.4 – INDEPENDENT VS. DISJOINT

• Events A and B are independent whenever:

𝑃 𝐵 𝐴) = 𝑃(𝐵)
3.4 – INDEPENDENT VS. DISJOINT

• Example:

Reason for Complaint

Complaint Origin Electrical Mechanical Appearance Totals

During Guarantee Period 18% 13% 32% 63%

After Guarantee Period 12% 22% 3% 37%

Totals 30% 35% 35%

𝑃(𝐴 ∩ 𝐵) .32
𝑃 𝐴𝑝𝑝𝑒𝑎𝑟𝑎𝑛𝑐𝑒 𝐶𝑜𝑚𝑝𝑙𝑎𝑖𝑛𝑡 𝐷𝑢𝑟𝑖𝑛𝑔 𝐺𝑢𝑎𝑟𝑎𝑛𝑡𝑒𝑒) = 𝑃 𝐴 𝐵) = = = .51
𝑃(𝐵) .63
 4

Random Variables and

Probability Models
4.1 – RANDOM VARIABLES

• A random variable is a variable that assumes numerical values

associated with the random outcomes of an experiment, where one (and
only one) numerical value is assigned to each sample point.

• Random variables that can assume a countable number (finite or

infinite) of values are called discrete.

• Random variables that can assume values corresponding to any of the

points contained in one or more intervals (i.e., values that are infinite
and uncountable) are called continuous.
4.1 – RANDOM VARIABLES

• Some examples of discrete random variables include:

• The number of cars in a sample of 100 that has defective parts:
x = 0,1,2,3 …, 100
• The number of correct questions in a sample of 35 to grade:
x = 0,1,2,3,…,35

• Some examples of continuous random variables include:

• The weight of sports players at a training camp: 0 < x < ∞
• The length of time between arrivals at a hospital clinic: 0 ≤ x < ∞
4.2 – DISCRETE PROBABILITY MODELS

• The probability distribution of a discrete random variable is a graph,

table, or formula that specifies the probability associated with each
possible value the random variable can assume.

• Requirements for the Probability Distribution of a Discrete Random

Variable x.
1. p(x) ≥ 0 for all values of x
2. S p(x) = 1

Where the summation of p(x) is over all possible values of x.

4.2 – DISCRETE PROBABILITY MODELS

• Example: Tossing two coins and let x be the number of heads observed.

x P(x) Outcome

0 ¼ TT

1 ½ HT, TH

2 ¼ HH
4.2 – DISCRETE PROBABILITY MODELS

• We can’t predict exactly what will happen in an experiment, but we can

say what we expect to happen.

• Expected is a mathematical term and should not be interpreted as it is

typically used.

• Specifically, a random variable might never be equal to its “expected

value.”

• The expected value is the mean of the probability distribution or a

measure of its central tendency.
4.2 – DISCRETE PROBABILITY MODELS

The mean (expected value) of a discrete random variable x.

𝜇 = 𝐸 𝑥 = g 𝑥. 𝑝(𝑥)

The variance of a discrete random variable x.

𝜎 ! = 𝐸 (𝑥 − 𝜇)! = g(𝑥 − 𝜇).! 𝑝(𝑥)

The standard deviation of a discrete random variable.

𝜎= 𝜎!
4.2 – DISCRETE PROBABILITY MODELS

• You toss 2 coins. You’re interested in the number of tails. What are the
expected value, variance, and standard deviation of this random
variable, number of tails?

x p(x) x.p(x) x–µ (x – µ) 2 (x – µ) 2 p(x)

0 ¼ 0 -1 1 ¼

1 ½ ½ 0 0 0

2 ¼ ½ 1 1 ¼
4.3 – CONTINUOUS DISTRIBUTIONS: INTRODUCTION

• The graphical form of the probability distribution for a continuous

random variable x is a smooth curve.
4.4 – CONTINUOUS DISTRIBUTIONS: NORMAL DISTRIBUTION

• Bell-shaped / Bell curve:

• One of the most commonly observed continuous random variables.
• Probability distribution called a normal distribution .

• Why is the distribution so popular?

• Describes many random processes or continuous phenomena.
• Can be used to approximate discrete probability distributions.
• Basis for classical statistical inference.
4.4 – CONTINUOUS DISTRIBUTIONS: NORMAL DISTRIBUTION

2
æ 1ö æ x- µ ö
1 -ç ÷
è 2ø çè
s ø
÷
f (x) = e
s 2p

Where

µ = Mean of the normal

random variable x

s = Standard deviation

π = 3.1415 . . .

e = 2.71828 . . .
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

• The standard normal distribution is a normal distribution with 𝜇 = 0

and 𝜎 = 1.

• A random variable with a standard normal distribution, denoted by the

symbol z, is called a standard normal random variable.

• ‘Z-tables’ are tables that assist in calculating the area/probabilities found

under a standard normal curve.
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

Examples:

1) Find the probability that the standard normal random z falls between
-1.33 and 1.33.
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

Examples:

2) Find the probability that a standard normal random variable exceeds

1.64; that is, find P(z > 1.64).
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

• To apply the previous table to a normal random variable x with any

mean u and any standard deviation sigma, we must first convert the
value of x to a z-score.
• If x is a normal random variable with mean μ and standard deviation s,
then the random variable z, defined by the formula has a standard
normal distribution. The value z describes the number of standard
deviations between x and µ.

x-µ
z=
s
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

x-µ
z=
s
Normal
Distribution

One table!
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

Example:

Assume that the length of time, x, between charges of a cellular phone is

normally distributed with a mean of 10 hours and a standard deviation of
1.5 hours. Find the probability that the cell phone will last between 8 and
12 hours between charges.
8 − 10 12 − 10
𝑃 8 ≤ 𝑋 ≤ 12 = 𝑃 ≤𝑍≤ = 𝑃 −1.33 ≤ 𝑍 ≤ 1.33 = 2. .4082 = 81.64%
1.5 1.5
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

Example:

Human pregnancies follow approximately a normal distribution with a

mean of 266 days and a standard deviation of 16 days. What percent of
pregnancies will last between 241 days and 286 days?

241 − 266 286 − 266

𝑃 241 < 𝑋 < 286 = 𝑃 <𝑍< = 𝑃 −1.56 < 𝑍 < 1.25 ≈ 83.5%
16 16
4.5 – CONTINUOUS DISTRIBUTIONS: STANDARD NORMAL DISTRIBUTION

Example:

What length cuts off the shortest 2.5% of pregnancies?

𝑥−𝜇
𝑍= ⇒ 𝜎𝑍 + 𝜇 = 16 −1.96 + 266 = 234.44
𝜎
4.6 – SAMPLING DISTRIBUTIONS AND CLT (INTRO)

• A parameter is a numerical descriptive measure of a population.

Because it is based on all the observations in the population, its value is
almost always unknown.

• A sample statistic is a numerical descriptive measure of a sample. It is

calculated from the observations in the sample.
4.6 – SAMPLING DISTRIBUTIONS AND CLT (INTRO)

Population Parameter Sample Statistic

Mean 𝜇 𝑥̅

Variance 𝜎! 𝑠!

Standard Deviation 𝜎 𝑠

Proportion p 𝑝̅

• The sampling distribution of a sample statistic calculated from a

sample of n measurements is the probability distribution of the statistic.
4.6 – SAMPLING DISTRIBUTIONS AND CLT (INTRO)
4.6 – SAMPLING DISTRIBUTIONS AND CLT (INTRO)

Properties of the Sampling Distribution of x-bar

1. Mean of the sampling distribution equals mean of sampled

population, that is, 𝜇n̅ = 𝐸 𝑥̅ = 𝜇

2. Standard deviation of the sampling distribution equals:

𝜎
𝜎n̅ =
𝑛
4.6 – SAMPLING DISTRIBUTIONS AND CLT (INTRO)

Standardizing the Sampling Distribution of x bar

x - µx x-µ
z= =
sx s
n
4.7 – CENTRAL LIMIT THEOREM

• Consider a random sample of n observations selected from a population

(any probability distribution) with mean 𝜇 and standard deviation 𝜎.
Then, when n is sufficiently large, the sampling distribution of 𝑥̅ will be
approximately a normal distribution with mean 𝜇n̅ = 𝜇 and standard
o
deviation 𝜎n̅ = . The larger the sample size, the better will be the
&
normal approximation to the sampling distribution of 𝑥.̅
4.7 – CENTRAL LIMIT THEOREM (SIMULATION EXAMPLE)
4.7 – CENTRAL LIMIT THEOREM

Example:
A manufacturer of automobile batteries claims that the distribution of the
lengths of life of its best battery has a mean of 54 months and a standard
deviation of 6 months. Recently, the manufacturer has received a rash of
complaints from unsatisfied customers whose batteries have died earlier than
expected. Suppose a consumer group decides to check the manufacturer’s claim
by purchasing a sample of 50 of these batteries and subjecting them to tests that
determine battery life.

Assuming that the manufacturer’s claim is true, what is the probability that the
consumer group’s sample has a mean life of 52 or fewer months?

𝑥̅ − 𝜇,̅ 52 − 54
𝑍= = = −2.35
𝜎,̅ 6
50
 5

Estimation with
Confidence Intervals
5.1 – CONFIDENCE INTERVALS: DEFINITIONS

• A point estimator of a population parameter is a rule or formula that

tells us how to use the sample data to calculate a single number that can
be used as an estimate of the target parameter.
• Provides a single value.
• Gives no information about how close the value is to the unknown
population parameter.
5.1 – CONFIDENCE INTERVALS: DEFINITIONS

• An interval estimator (or confidence interval) is a formula that tells us

how to use the sample data to calculate an interval that estimates the
target parameter.
• Provides a range of values.
• Gives information about closeness to unknown population
parameter.
5.1 – CONFIDENCE INTERVALS: DEFINITIONS

A confidence interval provides a range of plausible values for the population parameter.
5.3 – CONFIDENCE INTERVALS: FORMULA

1. A random sample is selected from the target population.

2. The sample size n is large (i.e., n ≥ 30). Due to the Central Limit
Theorem, this condition guarantees that the sampling distribution of x
is approximately normal.

𝜎
𝑥̅ ± 𝑍qp 𝜎n̅ = 𝑥̅ ± 𝑍qp
! ! 𝑛
5.4 – CONFIDENCE INTERVALS: EXAMPLES

Examples:

Consider the large bank that wants to estimate the average amount of
money owed by its delinquent debtors, µ. The bank randomly samples n
= 100 of its delinquent accounts and finds that the sample mean amount
owed is 𝑥̅ = $230. Also, suppose it is known that the standard deviation of
the amount owed for all delinquent accounts is σ = $90.
Find a 90% and 95% confidence interval for the target parameter, µ

𝜎 90
90%: 𝑥̅ ± 𝑍-/! = 230 ± 1.64 = (215.24, 244.76)
𝑛 100

𝜎 90
95%: 𝑥̅ ± 𝑍-/! = 230 ± 1.96 = (212.36, 247.64)
𝑛 100
 6

Test of Hypothesis
6.1 – HYPOTHESIS TESTS: INTRODUCTION

• A statistical hypothesis is a statement about the numerical value of a

population parameter.
• Ho: Null hypothesis -> accept unless data provides convincing
evidence that it is false.
• Ha: Alternate hypothesis -> accepted only if the data provides
convincing evidence of its truth.
6.1 – HYPOTHESIS TESTS: INTRODUCTION

• As with confidence intervals, the methodology for testing hypothesis

varies depending on the target population parameter.

Parameter Key Words or Phrases

µ Mean; average

ρ Proportion; percentage; fraction; rate

6.1 – HYPOTHESIS TESTS: INTRODUCTION

1. Alternate Hypothesis: Opposite of null hypothesis.

2. The hypothesis that will be accepted only if the data provide
convincing evidence of its truth.
3. Designated Ha
4. Stated in one of the following forms:
Ha: µ ¹ (some value)
Ha: µ < (some value)
Ha: µ > (some value)
6.1 – HYPOTHESIS TESTS: INTRODUCTION

• Example
Is the population average of Netflix viewing 3 hours?

𝐻𝑜: 𝜇 = 3
𝐻𝑎: 𝜇 ≠ 3

Is the population average amount spent on amazon purchases greater

than $50?
𝐻𝑜: 𝜇 ≤ 50
𝐻𝑎: 𝜇 > 50
6.2 – HYPOTHESIS TESTS: FORMULA

• Conditions Required for a Valid Large-Sample Hypothesis Test for the

mean

1. A random sample is selected from the target population.

2. The sample size n is large (i.e., n ≥ 30). (Due to the Central Limit
Theorem, this condition guarantees that the test statistic will be
approximately normal regardless of the shape of the underlying
probability distribution of the population.)
6.2 – HYPOTHESIS TESTS: FORMULA

• The test statistic is a sample statistic, computed from information

provided in the sample, that the researcher uses to decide between the
null and alternative hypotheses.

• The test statistic is a z-value that measures the distance between the
value of x-bar and the value of 𝜇 specified in the null hypothesis:

𝑥̅ − 𝜇n̅ 𝑥̅ − 𝜇
𝑍= = 𝜎
𝜎n̅
𝑛
6.2 – HYPOTHESIS TESTS: FORMULA

Example:

You are an analyst at Ford Motor Company. You want to find if the
average miles per gallon of the new Ford Escape is 32mpg. Similar models
have a standard deviation of 3.8mpg.
You take a sample of 60 Escape and compute a sample mean of 30.7mpg.
Is there evidence that MPG is less than 32mpg?
𝑥̅ − 𝜇,̅ 30.7 − 32
𝑍= = = −2.65
𝜎,̅ 3.8
60
𝐻𝑜: 𝜇 ≥ 32
𝐻𝑎: 𝜇 < 32
6.3 – HYPOTHESIS TESTS: TYPE I & II ERRORS

• A Type I error occurs if the researcher rejects the null hypothesis in

favor of the alternative hypothesis when, in fact, H0 is true. The
probability of committing a Type I error is denoted by a.

• A Type II error occurs if the researcher accepts the null hypothesis

when, in fact, H0 is false. The probability of committing a Type II error is
denoted by b.
6.3 – HYPOTHESIS TESTS: TYPE I & II ERRORS

True State of Nature

𝑯𝟎 𝑻𝒓𝒖𝒆 𝑯𝒂 𝑻𝒓𝒖𝒆

Accept 𝑯𝟎 (Assume
Type II
𝑯𝟎 𝑻𝒓𝒖𝒆)

Reject 𝑯𝟎 (Assume Type I

𝑯𝒂 𝑻𝒓𝒖𝒆)
6.4 – HYPOTHESIS TESTS: REJECTION REGIONS

• The rejection region of a statistical test is the set of possible values of

the test statistic for which the researcher will reject H0 in favor of Ha.
6.4 – HYPOTHESIS TESTS: REJECTION REGIONS

Examples:

Key Words or Phrases Defendant Innocent Defendant Guilty

Accept presumption Type II

of innocence

Reject presumption Type I

of innocence
6.5 – HYPOTHESIS TESTS: P-VALUES

• Probability of obtaining a test statistic more extreme (£ or ³) than actual

sample value, given H0 is true .

• Called observed level of significance.

• Smallest value of a for which H0 can be rejected.

• Used to make rejection decision.

• If p-value ³ a, do not reject H0
• If p-value < a, reject H0
6.5 – HYPOTHESIS TESTS: P-VALUES

Example:

𝐴𝑠𝑠𝑢𝑚𝑒 𝛼 = 5%
𝐻𝑜: 𝜇 ≥ ∎
𝐻𝑎: 𝜇 < ∎
𝑥̅ − 𝜇,̅
𝑍= = −1.9
𝜎,̅

Reject Ho as the test statistic falls inside of the rejection region

Or
Reject Ho as p-value < alpha
6.5 – HYPOTHESIS TESTS: P-VALUES

Calculating the p-Value for a Test of Hypothesis

𝐴𝑠𝑠𝑢𝑚𝑒 𝛼 = 5%
𝐻𝑜: 𝜇 ≤ ∎
𝐻𝑎: 𝜇 > ∎
𝑥̅ − 𝜇,̅
𝑍= = 1.5
𝜎,̅

Fail to reject Ho as the test statistic falls outside of the rejection region
Or
Fail to reject Ho as p-value > alpha
6.6 – HYPOTHESIS TESTS: EXAMPLE

𝐴𝑠𝑠𝑢𝑚𝑒 𝛼 = 5%
𝐻𝑜: 𝜇 = ∎
𝐻𝑎: 𝜇 ≠ ∎
𝑥̅ − 𝜇,̅
𝑍= = 1.9
𝜎,̅

Fail to reject Ho as the test statistic falls outside of the rejection region
Or
Fail to reject Ho as p-value > alpha
6.6 – HYPOTHESIS TESTS: EXAMPLE