IMPORTANT FORMULAS Chapter 5: Discrete Probability Distributions

Mean 
of a discrete random variable: Mean of a binomial random variable:
μ X = [x · P(x)] μ X = np
Chapter 3: Numerical Summaries of Data
Variance
 of a discrete random variable: Variance of a binomial random variable:
Sample σ X2 = [(x − μ X )2 · P(x)] = [x 2 · P(x)] − μ2X σ X2 = np(1 − p)
 mean: Coefficient of variation:
x σ
x̄ = CV = Standard
n μ  deviation of a discrete random variable: Standard
 deviation of a binomial random variable:
Population σ X = σ X2 σ X = np(1 − p)
 mean: z-score:
x x −μ
μ= z=
N σ
Chapter 6: The Normal Distribution
Range: Interquartile range:
Range = largest value − smallest value IQR = Q 3 − Q 1 = third quartile − first quartile
z-score: z-score for a sample mean:
Population x −μ x̄ − μ
 variance: Lower outlier boundary:
z= z=
(x − μ)2 σ σx̄
σ2 = Q 1 − 1.5 IQR
N
Convert z-score to raw score: Standard
 deviation of the sample proportion:
Sample
 variance: Upper outlier boundary:
x = μ + zσ p(1 − p)
2 (x − x̄)2 σ p̂ =
s = Q 3 + 1.5 IQR n
n−1
Standard deviation of the sample mean: z-score for a sample proportion:
σ p̂ − p
σx̄ = √ z=
n
Chapter 4: Probability σ p̂

General Addition Rule: General Method for Computing Conditional Chapter 7: Confidence Intervals
P(A or B) = P(A) + P(B) − P(A and B) Probability:
P(A and B)
P(B | A) = Confidence interval for a mean, standard deviation Confidence interval for a proportion:
P(A) known:  
σ σ p̂(1 − p̂) p̂(1 − p̂)
Multiplication Rule for Independent Events: General Multiplication Rule: x̄ − z α/2 √ < μ < x̄ + z α/2 √ p̂ − z α/2 < p < p̂ + z α/2
P(A and B) = P(A)P(B) P(A and B) = P(A)P(B | A) = P(B)P(A | B) n n n n

Sample size to construct an interval for μ with margin Sample size to construct an interval for p with
Addition Rule for Mutually Exclusive Events: Permutation of r items chosen from n: of error m: margin of error m:
n!  z · σ 2  z 2
P(A or B) = P(A) + P(B) n Pr = α/2 α/2
(n − r )! n= n = p̂(1 − p̂) if a value for p̂ is available
m m
Rule of Complements: Combination of r items chosen from n: z 2
α/2
n! Confidence interval for a mean, standard deviation n = 0.25 if no value for p̂ is available
P(Ac ) = 1 − P(A) n Cr = m
r !(n − r )! unknown:
s s
x̄ − tα/2 √ < μ < x̄ + tα/2 √
n n
 Chapter 8: Hypothesis Testing Chapter 11: Correlation and Regression
Test statistic for a mean, standard deviation known: Test statistic for a proportion: Correlation coefficient: Standard error for b1 :
x̄ − μ0 p̂ − p0
  
z= √ z=  1  x − x̄ y − ȳ se
σ/ n r= sb = 
p0 (1 − p0 ) n−1 sx sy (x − x̄)2
n
Test statistic for a mean, standard deviation unknown: Equation of least-squares regression line: Confidence interval for slope:
x̄ − μ0 ŷ = b0 + b1 x b1 − tα/2 · sb < β1 < b1 + tα/2 · sb
t= √
s/ n
Slope of least-squares regression line: Test statistic for slope b1 :
sy b1
Chapter 9: Inferences on Two Samples b1 = r
sx
t=
sb

Test statistic for the difference between two means, Confidence interval for the difference between y-intercept of least-squares regression line: Confidence interval for the mean response:

independent samples: two proportions: b0 = ȳ − b1 x̄
 1 (x ∗ − x̄)2
(x̄1 − x̄2 ) − (μ1 − μ2 ) p̂1 (1 − p̂1 ) p̂2 (1 − p̂2 ) ŷ ± tα/2 · se +
t=  p̂1 − p̂2 − z α/2 + < p1 − p 2 Residual standard deviation: n (x − x̄)2
n1 n2 
s12 s2 (y − ŷ)2
+ 2  se =
n1 n2 Prediction interval
 for an individual response:
p̂1 (1 − p̂1 ) p̂2 (1 − p̂2 ) n−2
< p̂1 − p̂2 + z α/2 + 1 (x ∗ − x̄)2
n1 n2 ŷ ± tα/2 · se 1+ +
n (x − x̄)2
Confidence interval for the difference between Test statistic for the difference between two means,
two means, independent samples: matched pairs:

s12 s2 d¯ − μ0
x̄1 − x̄2 − tα/2 + 2 < μ1 − μ2 t= √
n1 n2 sd/ n

s12 s2 Confidence interval for the difference between two
< x̄ 1 − x̄2 + tα/2 + 2
n1 n2 means, matched pairs:
sd sd
d¯ − tα/2 √ < μd < d¯ + tα/2 √
Test statistic for the difference between n n
two proportions:
p̂1 − p̂2
z=   
1 1
p̂(1 − p̂) +
n1 n2
x1 + x2
where p̂ is the pooled proportion p̂ =
n1 + n2

Chapter 10: Tests with Qualitative Data