Page 1 of 9

Chapter 3 Descriptive Statistics x−μ

z=
σ
Population Mean
∑ x x1 + x 2 + x3 + ⋯+ x N Coefficient of Variation
μ=¿ =
N N s
CV = (100) for sample
x
Sample Mean
∑ x x1 + x 2 + x3 + ⋯+ x n σ
x= = CV = (100) for population
n n μ
Interquartile Range
Q3 – Q1

Sum of Deviations from the Arithmetic Mean is

Always Zero
∑(x – μ ) = 0

Mean Absolute Deviation

∑|x−μ|
MAD =
N
Population Variance
2
2 ∑(x−μ)
σ =
N

Population Standard Deviation

√
2
σ = √ σ 2 = ∑ (x−μ)
N

Empirical Rule*
Distance from the Mean Values within the Distance
μ ±1 σ 68%
μ ±2 σ 95%
μ ±3 σ 99.7%

*Based on the assumption that the data are

approximately normally distributed.

Sample Variance
2
2 ∑( x−x )
s =
n−1
Sample Standard Deviation

√
2
s =√ s 2= ∑ (x−x)
n−1

s= √ s2

z Score
 Page 2 of 9

Chapter 4 Probability P ( X ∩Y )
P ( X |Y )= =P ( X ) ∙ P ¿ ¿
P (Y )
Range of Possible Probabilities
Bayes’ Rule
0 ≤ P( E )≤ 1
P ( X 1 ¿ ∙ P ( Y |X 1 )
Probability by Relative Frequency of Occurrence
P ( X 1|Y )=
P ( X 1 ¿ ∙ P ( Y | X 1) + …+ P ( X n ¿ ∙ P (Y | X n )
Number of ×an Event Occurred
Occur ¿Independent Events X, Y
Total Number of Opportunities for the Event ¿ If X and Y are independent events, the following must be
true:
Marginal Probability P ( X|Y )=P ( X )∧P ( Y | X )=P ( Y )
P(X)
P ( X ∩Y )=P ( X ) ∙ P ( Y )
Union Probability
P ( X ∪Y )
Joint Probability
P ( X ∩Y )
Conditional Probability
P ( X∨Y )
Mutually Exclusive Events X and Y
P ( X ∩Y )=0
Independent Events X and Y
P ( X |Y )=P ( X )∧P ( Y | X )=P(Y )
Probability of the Complement of A
P ( A ' )=1−P( A )

General Law of Addition

P ( X ∪ Y )=P ( X ) + P ( Y )−P( X ∩Y )
where X, Y, are events and ( X ∩Y ) is the intersection of
X and Y.

Special Law of Addition

If X, Y are mutually exclusive,
P ( X ∪ Y )=P ( X ) + P ( Y )
General Law of Multiplication
P ( X ∩Y )=P ( X ) ∙ P ( Y | X ) =P (Y ) ∙ P( X|Y )
Special Law of Multiplication
If X, Y are independent,
P ( X ∩Y )=P ( X ) ∙ P ( Y )
Law of Conditional Probability
 Page 3 of 9

Chapter 5 Discrete Distributions

Mean or Expected Value of a Discrete Distribution
μ= E ( x )=∑ [ x ∙ P ( x ) ]
where
E(x) = long-run average Mean and Standard Deviation of a Uniform
x = an outcome Distribution
P(x) = probability of that outcome a+ b
μ=
Variance of a Discrete Distribution 2
2
σ =∑ ¿
where b−a
x = an outcome
σ=
P(x) = probability of a given outcome
√ 12
μ= mean Probabilities in a Uniform Distribution
Standard Deviation of a Discrete Distribution x 2−x 1
P ( x) =
σ =√ ∑ ¿ ¿ b−a
where
Assumptions of the Binomial Distribution a ≤ x1 ≤ x 2 ≤ b
- The experiment involves n identical trials.
- Each trial has only two possible outcomes denoted as
z formula
success or failure.
- Each trial is independent of the previous trials. x−μ
z= ,σ ≠0
- The terms p and q remain constant throughout the σ
experiment, where the term p is the probability of
getting a success on any one trial and the term q = 1 – Exponential Probability Density Function
p is the probability of getting a failure on any one
trial.
f ( x )= λ e−λ x
where
x≥0
Mean and Standard Deviation of a Binomial λ> 0
Distribution and e = 2.718281…
μ=¿ n ∙p
Probabilities of the Right Tail of the Exponential
Distribution
σ = √n ∙ p ∙ q − λ x0
P ( x ≥ x 0 )=e
Poisson Formula where
x
λ e −λ x0 ≥ 0
P ( x) =
x!
where
x = 0, 1, 2, 3, …
λ = long-run average
e = 2.718281…

Mean and Standard Deviation of a Poisson

Distribution
μ= λ

σ =√λ
Chapter 6 Continuous Distributions
Probability Density Function of a Uniform
Distribution
 Page 4 of 9

Chapter 7 Sampling & Sampling ^p − p

z=

√
Distributions p∙q
n
where
Central Limit Theorem
If samples of size n are drawn randomly from a ^p = sample proportion
population that has a mean of μ and a standard n = sample size
p = population proportion
deviation of σ , the sample means, x , are approximately q=1–p
normally distributed for sufficiently large samples (n ≥
30*) regardless of the shape of the population
distribution. If the population is normally distributed,
the sample means are normally distributed for any
sample size.

From mathematical expectation, it can be shown that

the mean of the sample means is the population mean:
μ x =μ
and the standard deviation of the sample means (called
the standard error of the mean) is the standard
deviation of the population divided by the square root
of the sample size:
σ
σ x=
√n
z Formula for Sample Means
x−μ
z=
σ
√n

Sample Proportion
x
^p=
n
where
x = number of items in a sample that have the
characteristic
n = number of items in the sample

z Formula for Sample Proportions for n ∙ p> 5 and

n ∙ q>5
 Page 5 of 9

Chapter 8 Statistical Inference:

Estimation for Single Populations Confidence Level z α / 2Value
90% 1.645
100(1 – a)% Confidence Interval to Estimate μ: σ 95% 1.96
Known (8.1) 98% 2.33
99% 2.575

where
 = the area under the normal curve outside the
confidence interval area
 = the area in one end (tail) of the distribution
outside the confidence interval

Confidence Interval to Estimate μ : Population

Standard Deviation Unknown and the Population
Normally Distributed (8.3)

Confidence Interval to Estimate p (8.4)

^p−z α /2
√ p^ ⋅q^
n √
≤ p≤ ^p + z α /2
p^ ⋅q^
n
where
^p = sample proportion
q^ = 1− ^p
p = population proportion
n = sample size

Sample Size When Estimating μ (8.7)

( )
2 2 2
z α /2 σ zα / 2 σ
n= 2
=
E E
where
E = error of estimation i.e. the difference between
x̄ and μ
If σ is unknown, it is acceptable to use
σ=1/4 (range)

Sample Size When Estimating p (8.8)

2
z α / 2 p⋅q
n= 2
E
where
p = population proportion
q= 1 – p
E = error of estimation i.e. the difference between
^p and p
n = sample size

z Values for Some of the More Common Levels of

Confidence
 Page 6 of 9

Chapter 9 Statistical Inference: Chapter 10 Statistical Inference: About

Hypothesis Testing for Single Two Populations
Populations
z Formula for the Difference in Two Sample Means
z Test for a Single Mean (9.1) (Independent Samples and Population Variances
x−μ Known) (10.1)
z= ( x̄ 1− x̄ 2 )−( m1 −m 2 )
σ z=

√
2 2
s 1 s2
√n n1 n2
+

where
t Test for a Single Mean (9.3) μ1 = mean of population 1
x−μ μ2 = mean of population 2
t=
s n1 = size of sample 1
√n n2 = size of sample 2
df = n – 1
Confidence Interval to Estimate μ1 − μ 2 (10.2)

√ √
z Test of a Population Proportion (9.4) 2 2 2 2
^p − p σ1 σ2 σ1 σ2
z= ( x̄1 − x̄ 2 )−z α / 2 + ≤μ1 −μ2 ≤( x̄ 1 − x̄ 2 )+ z α /2 +

√
n 1 n2 n 1 n2
p∙q
t Formula to Test the Difference in Means Assuming
n 2 2
where σ 1 and σ 2 are Equal (10.3)
^p = sample proportion
p = population proportion ( x̄ − x̄ )−( μ1 −μ2 )
q=1–p t= 1 2
sp
1 1
+
n1 n2
df=n1 +n 2−2
√
where
t Formula to Test the Difference in Means (10.4)
( x̄ 1 − x̄2 )−(m1−m2 )
t=

√
s 21 s 22
+
n1 n2

( )
2
s21 s22
+
n 1 n2
df=

() ()
2 2
s21 s 22
n1 n2
+
n1 −1 n2 −1

Confidence Interval to Estimate μ1 − μ2 Assuming

the Population Variances are Unknown and Equal
(10.5)

( x̄1 − x̄ 2 )−t
√ s21 (n1 −1)+s 22 ( n2−1 ) 1 1
n1 +n2 −2 √
+ ≤μ 1−μ 2≤
n1 n 2

√ √
2 2
s ( n −1 )+s 2 (n2 −1) 1 1
( x̄1 − x̄ 2 )+t 1 1 +
n1 +n2−2 n 1 n2
df=n1 +n2 −2
 Page 7 of 9

Chapter 10 Statistical Inference: About

Two Populations (cont.)
t Test for the Difference in Two Related Samples
(the differences are normally distributed in the
population) (10.6)
d̄−D
t= Confidence Interval to Estimate p1 - p2 (10.12)

(√ ) √
sd ^p 1 ⋅ q^ 1 ^p 2 ⋅ q^ 2
n ( ^p1− ^p2 ) −z n1
+
n2
≤ p 1− p2
, df = n – 1

Confidence Interval Formula for Estimating the

Difference in Related Samples (the differences are
√^p ⋅ q^ ^p ⋅ q^
≤( ^p1− ^p 2)+ z 1 1 + 2 2
n1 n2
normally distributed in the population) (10.9)
sd sd Chapter 11 Analysis of Variance and
d̄−t α / 2 ≤D≤ d̄+t α / 2 Design of Experiments
√n √n , df = n – 1
Formulas for Computing a one-way ANOVA
z Formula for the Difference in Two Population C
Proportions (10.10)
( ^p1 − p^ 2 )−( p1 − p2 )
∑ (
SSC= n j x̄ j− x̄  2 , df C =C−1
)
j=1
z=

√
nj C
p1⋅q 1 p2⋅q2
+ SSE=∑ ∑ ( x ij − x̄ j )  , df E =N −C
2
n1 n2
where i=1 j=1
n
^p1 = proportion from sample 1 j C
SST=∑ ∑ ( xij − x̄ )  , df T =N−1
2
^p2 = proportion from sample 2
i=1 j=1
n1 = size of sample 1
n2 = size of sample 2 SSC SSE MSC
MSC= , MSE= , F=
p1 = proportion from population 1 df C df E MSE
p2 = proportion from population 2
q 1 = 1− p1
q 2 = 1− p2

z Formula to Test the Difference in Population

Proportions (10.11)
( ^p1 − p^ 2 )−( p1 − p2 )
z=

√ (
( p̄⋅q̄ )
1 1
+
n1 n 2 )
x 1+ x 2 n1 ^p1 +n 2 p^ 2
p̄= =
n 1 +n2 n1 + n2
and
where
q̄=1− p̄
 Page 8 of 9

Chapter 12 Correlation and Simple 2 b 21 SS xx

Regression r=
SS yy
(12.1) Pearson product-moment correlation
coefficient t test of slope

r=
∑ ( x− x̄ )( y− ȳ )
√ ∑ ( x− x̄ )2 ∑ ( y− ȳ )2
Equation of the simple regression line

Sum of squares
(12.6) Confidence interval to estimate E(yx) for a
given value of x

(12.7) Prediction interval to estimate y for a given

value of x

(12.2) Slope of the regression line

b 1=
∑ ( x− x ) ( y− y )
∑ ( x −x )2
(12.3) Alternative formula for slope

(12.4) y intercept of the regression line

b 0= ȳ−b1 x̄

Sum of squares of error

SSE=∑¿
Standard error of the estimate

(12.5) Coefficient of determination

2 SSE
r =1−
SS yy

Computational formula for r2

 Page 9 of 9

Chapter 13 Multiple Regression

Analysis
The F Value
MS reg SS reg /df reg SSR/ k
F= = =
MS err SS err /df err SSE/ ( N−k−1 )
Sum of squares of error

SSE=∑ ( y− ^y )
2

Standard error of the estimate

s e=
√ SSE
n−k−1
Coefficient of multiple determination
SSR SSE
R2 = =1−
SS yy SS yy
Adjusted R2
SSE/ ( n−k−1 )
AdjustedR 2 =1−
SS yy / ( n−1 )

Chapter 16 Analysis of Categorical

Data
2
χ Goodness-of-Fit Test (16.1)
2
(f o−f e )
χ 2=∑ , df = k – 1 - c
fe
2
χ Test of Independence (16.2)
2
(f o−f e )
χ =∑ ∑
2
, df = (r – 1)(c - 1)
fe