Discrete Distrubutions

DistributionFormulaMean μVariance σ2Moment Generating Function
Bernoulli Distributionp if k = 1, 1 - p if k = 0, else 0pp(1 - p)1 - p + pet
Binomial Distribution
f(k;n,p)  =  n! * pk(1 - p)n - k
  k!(n - k)!

npnp(1 - p)(1 - p + pet)n
Negative Binomial Distribution
f(n;k,p)  =  (n - 1)! * pk(1 - p)n - k
  (k - 1)!(n - k)!

k
p

k(1 - p)
p2

(1 - p)r
(1 - pet)r

Geometric DistributionP(x = n) = p * (1 - p)(n - 1)
1
p

1 - p
p2

pet
1 - (1 - p)et

Poisson Distribution
P(k; λ)  =  λk
  eλk!

λλeλ(et - 1)
Hypergeometric Distribution
P(x;n,N,k)  =  (kCx) * (N - kCn - x)
  NCn

nk
N

nk(N - k)(N - n)
N2(N - 1)

N/A
Multinomial Distribution
ƒ(x0!·x1!·x2...·n;x;n,θ012,...,θn)  =  n!(θ0 · θ1 · θ2 · ... · θn)
  x0 · x1 · x2 · ... · xn

npinpi(1 - pi)(Σpieti)n
Uniform Distribution
P(k; λ)  =  λk
  eλk!

½a + b
(b - a)2
12

etb - eta
t(b - a)


Test Statistic Decision Tree:

TypeKeywordsSample SizeUse Test
Z-scoreMean, AverageGreater than 30 or population σ is known
z  =  X - μ
  σ/√n

t-scoreMean, Average30 or less: population σ is not known
t  =  x - μ
  s/√n

proportion-scoreProportion (Test p), Fraction, Percentage, Rate, Probabilitymore than 30
z  =  p^ - p0
  p0q0/n

Variance σ2Variance, Variability, SpreadN/A
χ2  =  (n - 1)s2
  σ2

Equal Variances σ12 = σ22Equal Variances, Ratio or Difference in VariancesN/A
F  =   σ12
   σ22


Confidence Interval Decision Tree

TypeKeywordsSample SizeUse Test
Test the MeanConfidence Interval, Mean, AverageGreater than 30X - zscoreα/2 * s/√n < μ < X + zscoreα/2 * s/√n
Test the MeanConfidence Interval, Mean, Average30 or lessX - tscoreα * s/√n < μ < X + tscoreα * s/√n
Test the VarianceConfidence Interval, VarianceGreater than 30(n - 1)s22α/2 < σ2 < (n - 1)s221 - α/2
Test the Standard DeviationConfidence Interval, Standard DeviationGreater than 30Square Root((n - 1)s22α/2) < σ2 < Square Root((n - 1)s221 - α/2)
Test the ProportionConfidence Interval, Proportion, percentage, rate, PopulationGreater than 30(n - 1)s22α/2 < σ2 < (n - 1)s221 - α/2
Test the Difference of MeansConfidence Interval, Difference of MeansGreater than 30(x1 - x2) - zscoreα x √a < μ1 - μ2 < (x1 - x2) - zscoreα x √a
Test the Difference of MeansConfidence Interval, Difference of Means30 or less(x1 - x2) - tscoreα x √a < μ1 - μ2 < (x1 - x2) - tscoreα x √a
p^ Confidence IntervalConfidence Interval (test p), criteria,characteristic, proportion30 or lessp^ - zα/2σ√p(1 - p)/n < p < p^ + zα/2p(1 - p)/n

Sample Size Decision Tree:

TypeKeywordsUse Test
Sample Size for μSample Size, average, mean
n  =  Z-scoreα/22 x σ2
  SE2

Proportion Sample SizeSample Size, Proportion, Population, Percentage, Rate
n  =  Z-score2 x p x (1 - p)
  SE2

μ1 - μ2 Sample SizeSample Size, Difference of Means, μ1 - μ2
n  =  Z-score212 + σ22)
  ME2

p1 - p2 Sample SizeSample Size, Difference of p, p1 - p2
n  =  Z-score2(p1q1 + p2q2)
  ME2

Hypothesis Testing Decision Tree

p-value Significance Test (observed level of significance):

Find your z-score, then find the probability in the z-table associated with that score, and if α > probability (p-value), reject H0

Hypothesis Testing Errors:

Type I error - Reject null hypothesis H0 when H0 is TRUE: Probability = α
Type II error - Accept null hypothesis H0 when H0 is FALSE: Probability = β
Power of the Test = Probability you Reject null hypothesis H0 when H0 is FALSE: --> 1 - β
Note: It is a bigger mistake to make a Type II error than a Type I error

Finite Population Correction Factor:

If n/N > 0.05, then you multiply your confidence interval by the following factor
N - n
N

Regression Testing and Correlation Coefficients:

Cov(X,Y)  =  Σ(Xi - X)(Yi - Y)
  n

Correlation Coefficient (r)  =  Cov(X,Y)
  sxsy

β  =  Σ(Xi - X)(Yi - Y)
  Σ(Xi - X)2

Least Squares Regression Line ← α = Y - βX
y^ = α + βx where α is the y-intercept for the line that contains the points in X & Y and β is the is the slope of the line that the set of points lies on.
α & β are designed such that they produce the smallest possible SSE defined below
Sum of Squares about the Mean (SSM) = (yi - y)2
Square of the Residual Difference (SSE) (yi - y^i)2
SSE represents the difference between the straight line that we create and the plotted points from our data
Coefficient of Determination (r2)  =  SSM - SSE
  SSM

Large Sample Condition Requirement:

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.)





Subscribe for get Daily New Courses

There are many variations of passages of Lorem Ipsum available, but the majority have suffered alteration in some form, by injected.