Probability and

Statistics -
Practice Tests
and Solutions
1. Probability
Definition:
Classic Model Relative Frequency of Occurrence

Number of outcomes in which Number of times an event

the event occurs occurred
Total Number of possible Total number of opportunities for
outcomes of an experiment an event to occur

Probability
 Mutually Exclusive Events: When
Rule of Addition two events cannot occur at the
same time P(A ∩ B) = 0
The probability that Event A or Event B
occurs
P(A) P(B)
=
Probability that Event A occurs A B
+
Probability that Event B occurs Independent Events: The
- occurrence of Event A does not
Probability that both Events A and B occur change the probability of Event B
P(A ∩ B) = P(A) P(B|A)
P(A ∪ B) = P(A) + P(B) - P(A ∩ B)

Probability
Venn Diagram
❖ Union: Probability that events A ❖ Intersection: Probability that
or B occur: P(A ∪ B) events A and B occur: P(A ∩ B)

A B A B

Probability
 With repetition Without repetition

❖ Permutation: r 𝑛!
n 𝑛𝑃𝑟 =
𝑛−𝑟 !
Order is important.

MS Excel Formula >> PERMUTATIONA(n,r) PERMUT(n,r)

❖ Combination: (𝑟 + 𝑛 − 1)!
𝑛𝑪 𝑟 =
𝑛!
𝑟! 𝑛 − 1 ! 𝑛 − 𝑟 ! r!
Order is NOT important.

MS Excel Formula >> COMBINA(n,r) COMBIN(n,r)

PERMUTATIONS / COMBINATIONS SUMMARY

Slide 6
Bayes’ Theorem
𝑃 𝐴ȁ𝐵 ⋅ 𝑃 𝐵 𝑃 𝐴ȁ𝐵 ⋅ 𝑃 𝐵
𝑃 BȁA = =
𝑃 𝐴 𝑃 𝐴ȁ𝐵 ⋅ 𝑃 𝐵 + 𝑃 𝐴ȁ𝐵′ ⋅ 𝑃 𝐵′

Probability Slide 7
2. Descriptive
Statistics
 Data
❖ Continuous Data
❖ Measurements: Length, height,
time
Qualitative Data Quantitative Data
❖ Discrete Data
❖ Count: Number of students,
Description Numbers Number of heads

Data
Slide 9
 Population: Sampling
Complete Process Sample: Part
collection to of population
be studied

𝜇 − population mean Inference

Statistic xത - sample mean
Parameter s – sample std. dev.
σ - population std. dev.
Characteristic of Characteristic
a population of a sample

SAMPLING
Slide 10
Mean Standard Deviation
σ𝑥
𝜇=
𝑁
Median 𝜎=
σ 𝑥−𝜇
𝑁
2
𝑠=
σ 𝑥 − 𝑥ҧ
𝑛−1
2

Middle value when put in

ascending or descending order. Variance is the square of the standard
Mode deviation.

Most occurring value

Descriptive Statistics
Slide 11
 Highest Value
Q3 – Third Quartile

Q2 – Median

Q1 – First Quartile
Lowest Value

Box and Whisker Plot

Slide 12
3A Binomial
Distribution
A binomial experiment has the
following properties: P(x) = nCx . px . (1 - p)n - x
❖ The experiment consists of n
repeated trials. • n: number of trials
❖ Each trial can result in just two • x: The number of successes desired
possible outcomes. We call one of
these outcomes a success and the • p: The probability of getting success in
one trial
other, a failure.
❖ The probability of success,
denoted by p, is the same on
every trial.
❖ The trials are independent; that is,
the outcome on one trial does not
affect the outcome on other trials.

BINOMIAL DISTRIBUTION
Slide 14
❖ The mean of the distribution
(μx) is
n.p
❖ The variance (σ2x) is
n.p.(1-p)
❖ The standard deviation (σx) is
𝐧⋅𝐩⋅ 𝟏−𝐩

BINOMIAL DISTRIBUTION
Slide 15
3B Poisson
Distribution
A Poisson experiment has the following μx
properties: P x, μ = e−μ ⋅
x!
❖ The experiment results in outcomes that
can be classified as successes or failures. • e: A constant equal to approximately
❖ The average number of successes (μ) that 2.71828. (Actually, e is the base of the
occurs in a specified region is known. natural logarithm system)
❖ Outcomes are random. Occurrence of one • μ: The mean number of successes that
outcome does not influence the chance of occur in a specified region.
another outcome of interest. • x: The actual number of successes that
❖ The outcomes of interest are rare relative occur in a specified region.
to the possible outcomes. • P(x; μ): The Poisson probability that
❖ Example: Road accidents, que at the exactly x successes occur in a Poisson
counter experiment, when the mean number of
successes is μ.

POISSON DISTRIBUTION
Slide 17
• The Poisson distribution has the following
properties:
• The mean of the distribution is equal to μ .
• The variance is also equal to μ .

BINOMIAL DISTRIBUTION
Slide 18
3C Normal
Distribution
 𝑥−𝜇 2
−
ⅇ 2𝜎2
𝑃 𝑥 =
𝜎 2𝜋

• where x is a normal random

variable,
• μ = mean,
• σ = standard deviation,
• π is approximately 3.14159,
• e is approximately 2.71828.

NORMAL DISTRIBUTION
Slide 20
• About 68% of the area under the
curve falls within 1 standard
deviation of the mean.

• About 95% of the area under the

curve falls within 2 standard
deviations of the mean.

• About 99.7% of the area under the

curve falls within 3 standard
deviations of the mean.

NORMAL DISTRIBUTION
Slide 21
 Z Value / Standard Score

❖ How many standard deviations an

element is from the mean.
❖ z = (x - μ) / σ

❖ z is the z-score,
❖ x is the value of the element,
❖ μ is the population mean,
❖ σ is the standard deviation.

NORMAL DISTRIBUTION
Slide 22
Binomial Distribution approximated
to the Normal Distribution

If np and n(1-p) >=10 then approximate it to

The Normal Distribution
The mean of the distribution (μx) is
n.p
The standard deviation (σx) is
𝐧⋅𝐩⋅ 𝟏−𝐩

NORMAL DISTRIBUTION
Slide 23
3D t-Distribution
 𝑥ҧ − 𝜇
𝑡=
𝑠Τ 𝑛
❖ s is the sample standard deviation
❖ 𝑥ҧ is the sample mean
❖ n is the number of samples
❖ 𝜇 is the population mean

Reference: Wikipedia

t - DISTRIBUTION
Slide 25
4 Hypothesis Testing
Basics
❖ For almost all populations, ❖ If a variable has a mean of µ and
the sampling distribution the variance 𝜎 2 , as the sample
of the mean can be size n increases, the sample
approximated closely by a mean approaches a normal
normal distribution, distribution with mean 𝜇𝑥ҧ and
provided the sample size variance 𝜎𝒙ഥ𝟐
is sufficiently large. 𝟐 𝜎𝒙𝟐
𝜇𝑥ҧ = 𝜇 𝜎𝒙ഥ =
𝒏
The standard deviation of the
𝜎𝑥
sampling distribution of the mean 𝜎𝑥ҧ =
is called the standard error of the
mean. 𝑛

CENTRAL LIMIT THEOREM

Slide 27
❖ Point estimate: ❖ Interval estimate:
❖ Summarize the sample by a single ❖ A range of values within which, we
number that is an estimate of the believe, the true parameter lies with
population parameter. high probability.
❖ The sample mean x̄ is a point estimate of ❖ For example, a < x̄ < b is an interval
the population mean μ. The sample estimate of the population mean μ. It
proportion 𝑝ො is a point estimate of the indicates that the population mean is
population proportion P. greater than a but less than b.

CONFIDENCE INTERVAL
Slide 28
 𝑧𝛼Τ2 ⋅ 𝜎
𝐶𝐼 = 𝑥ҧ ± 𝑝Ƹ 1 − 𝑝Ƹ
𝑛 𝐶𝐼 = 𝑝Ƹ ± 𝑧𝛼Τ2
𝑛
❖ Zα/2 = z table value for confidence
level, Zα/2 = z table value for confidence level
❖ σ = standard deviation pො = sample proportion
❖ n = sample size. n = sample size

CONFIDENCE INTERVAL
Slide 29
 TIPS
❖ Start with the Alternate Hypothesis.
❖ Null Hypothesis: The person is innocent This is what you want to prove.
❖ Alternate Hypothesis: The person is ❖ Null Hypothesis will always have the
guilty. You need to provide proof of this. equal to sign (=, ≥, ≤)and Alternate
❖ In statistical terms you: Hypothesis will never have it.
❖ Reject the Null Hypothesis, or
❖ Fail to reject the Null Hypothesis (not accept H0 Ha
the Null Hypothesis) not equal (≠)
equal (=)

greater than or equal to

less than (<)
(≥)
less than or equal to (≤) more than (>)

NULL AND ALTERNATE HYPOTHESIS

Slide 30
 TIPS
❖ Start with the Alternate Hypothesis. This is
what you want to prove.
❖ Null Hypothesis will always have the equal
to sign (=, ≥, ≤)and Alternate Hypothesis
will never have it.

H0 Ha
not equal (≠)
equal (=)

greater than or equal to

less than (<)
(≥)
less than or equal to (≤) more than (>)

NULL AND ALTERNATE HYPOTHESIS

Slide 31
 Type I error (alpha) Type II error (beta)
Name Producer’s risk/ Consumer’s risk
Significance level
True State of Nature 1 minus error is Confidence level Power of the test
called
H0 Ha
Is true Is true Example of Fire False fire alarm leading Missed fire leading to
Support Alarm to inconvenience disaster
H0 / Correct Type II Error
Conclusion Effects on Unnecessary cost Defects may be produced
Reject
Ha process increase due to frequent
Conclusion
Support Correct
changes
Ha / Type I Error Conclusion
Control method Usually fixed at a pre- Usually controlled to < 10%
(Power)
Reject determined level, 1%, by appropriate sample size
H0
5% or 10%
Simple definition Innocent declared as Guilty declared as innocent
guilty

Hypothesis Testing - Errors Slide 32

 P - Value
❖ p value is the lowest value of alpha for
which the null hypothesis can be rejected.
(Probability that the null hypothesis is
correct)
❖ For example, if p = 0.045 you can reject
the null hypothesis at α = 0.05
❖ p is low the null must go / p is high the
null fly.

P - VALUE
Slide 33
5 Hypothesis Tests
 One Sample z Test

One Sample t Test

One
Sample
One Proportion Test

One Variance Test

Two Sample z Test

Two Sample t Test

Two
Tests
Samples
Paired t Test

Two Proportions Test

Two Variances

More than
ANOVA
2 samples

Hypothesis Tests
Slide 35
 1. State the Alternate Hypothesis.
2. State the Null Hypothesis.
3. Select a probability of error level
(alpha level). Generally 0.05
4. Calculate the test statistic (e.g t
or z score)
5. Critical test statistic
6. Interpret the results.

Hypothesis Testing - Six Steps

Slide 36
 𝑥ҧ − 𝜇 𝑥ҧ − 𝜇
𝑧 = 𝑡 =
𝜎Τ 𝑛 𝑠Τ 𝑛
One Sample z Test One Sample t Test

𝑝ො − 𝑝 2
𝑧= 2
𝑛 − 1 𝑠
𝑝 1−𝑝 χ =
𝜎2
𝑛
One Proportion Test One Variance Test

One Sample Tests – Calculated Values

Slide 37
 𝑧𝑐𝑎𝑙 =
𝑥1ҧ − 𝑥ҧ2 𝑠12
𝐹𝑐𝑎𝑙 = 2
𝜎12 𝜎22 𝑠2
+
𝑛1 𝑛2

Two Sample z Test Two Variance Test

Two Sample Tests – Calculated Values

Slide 38
One Sample t Test
𝑥ҧ − 𝜇 Two Sample t Tests
𝑡𝑐𝑎𝑙 =
𝑠Τ 𝑛 ❖ Is variance for two populations equal?
Yes No
𝑥1ҧ − 𝑥ҧ2 𝑥ҧ1 − 𝑥ҧ2
𝑡𝑐𝑎𝑙 = 𝑡𝑐𝑎𝑙 =
1 1 𝑠12 𝑠22
𝑠𝑝 +
𝑛1 𝑛2 +
𝑛1 𝑛2
2 2
𝑛 − 1 𝑠 + 𝑛 − 1 𝑠
𝑠𝑝2 =
1 1 2 2 2 2
𝑠12 𝑠2
𝑛1 + 𝑛2 − 2 +𝑛
The approximate degrees 𝑛1 2
of freedom are rounded ⅆ𝑓 =
ⅆ𝑓 = 𝑛1 + 𝑛2 − 2 down to the nearest 𝑠12 Τ𝑛1 2 𝑠22 Τ𝑛2 2
integer. +
𝑛1 − 1 𝑛2 − 1

Two Sample t Test Slide 39

Proportions – Sample vs Population
How do we represent sample and population proportions?

𝑝1
μ 𝑥ҧ 𝑝Ƹ1
𝜎 s
𝑝 𝑝Ƹ

One Proportion Test 𝑝2 𝑝Ƹ 2

𝑝Ƹ − 𝑝
𝑧=
𝑝 1−𝑝
𝑛

Two Proportions Test Slide 40

One Proportion Test

𝑧=
𝑝 − 𝑝0 Two Proportions Tests
𝑝0 1 − 𝑝0
𝑛 Test for no difference between proportions
H0: p1 - p2 = 0 Yes No H0: p1 - p2 = d
Ha: p1 - p2 ≠ 0 Pooled Un-pooled Ha: p1 - p2 ≠ d

𝑛1 𝑝Ƹ1 + 𝑛2 𝑝Ƹ 2
𝑝ҧ =
𝑛1 + 𝑛2
𝑝Ƹ1 − 𝑝Ƹ 2 − (p1 − p2)
𝑧𝑐𝑎𝑙 =
𝑝Ƹ1 − 𝑝Ƹ 2 𝑝Ƹ1 1 − 𝑝Ƹ1 𝑝Ƹ 1 − 𝑝Ƹ 2
𝑧𝑐𝑎𝑙 = + 2
𝑛1 𝑛2
1 1
𝑝ҧ 1 − 𝑝ҧ +
𝑛1 𝑛2

Two Proportions Test Slide 41

 Variance Tests

❖ Chi-square test
❖ For testing the population variance against a specified value
❖ testing goodness of fit of some probability distribution
❖ testing for independence of two attributes (Contingency Tables)

❖ F-test
❖ for testing equality of two variances from different populations
❖ for testing equality of several means with technique of ANOVA.

Variance Tests Slide 42

6 ANOVA and other
topics
Degrees of freedom Mean Sum of Square = SS / df
Total df = df factor + df error MSSfactor = SS factor /df factor

Sum of Square MSSerror = SS error /df error

SST = SS factor +SS error
F Value
F = MSSfactor / MSSerror

ANOVA Slide 44
Goodness-of-Fit Test
H0: The data follow a specified
distribution.

Ha: The data do not follow the

specified distribution.

𝑘
O−𝐸 2
χ =෎
2
𝐸
𝑖=1

Goodness of Fit Test Slide 45

Contingency Tables
H0: The two criteria are independent.

HA: Some dependence exists.

𝑘
O−𝐸 2
χ =෎
2
𝐸
𝑖=1

Contingency Tables Slide 46