Download Statistical Formulas Cheat Sheet for Final Exam and more Cheat Sheet Statistics in PDF only on Docsity! Formula Sheet for Final Exam Summary Statistics • Sample mean: x̄ = n∑ i=1 xi n • Sample variance: s2 = ∑n i=1(xi − x̄)2 n− 1 • Sample standard deviation:= √ s2 • Inter-quartile range = q75 − q25, where qx = xth percentile. Probability • Complement: P (Ac) = 1− P (A) • Addition law: P (A or B) = P (A) + P (B)− P (A and B) • Conditional probability: P (A|B) = P (A and B) P (B) • If A and B are mutually exclusive: P (A and B) = 0 • If A and B are independent: P (A and B) = P (A)P (B) • Bayes’ rule: P (A|B) = P (B|A)P (A) P (B) • Partition law: If A1, . . . , An are mutually exclu- sive and ∑n i=1 P (Ai) = 1, then P (B) = n∑ i=1 P (B|Ai)P (Ai) Discrete Distribution • E(X) = ∑ x∈X xP (x) • V (X) = ∑ x∈X (x− µ)2P (x) = ∑ x∈X x2P (x)− µ2 • If X ∼ Bernoulli (p), p(x) = { p if x=1 1− p if x=0 E(X) = p V (X) = p(1− p) • If X ∼ Binomial (n, p), for r = 0, 1, . . . n, P (X = r) = ( n r ) pr(1− p)n−r E(X) = np V (X) = np(1− p)( n r ) = n!r!∗(n−r)! where n! = n(n − 1)(n − 2) · · · 1 and 0! = 1 • If X ∼ Poisson ( λ ), for k = 0, 1, 2, . . . P (X = k) = λk k! e−λ E(X) = λ, V (X) = λ Continuous Distribution • Let F (xo) be the cumulative distribution func- tion of X with density p(x): F (xo) = P (X ≤ xo) = ∫ xo −∞ p(x)dx P (a < X ≤ b) = F (b)− F (a) • If X is Normal with mean µ and variance σ2: X ∼ N (µ, σ2), then X − µ σ = Z ∼ N (0, 1) Expectation and Variance Let X and Y denote two independent random vari- ables and let a and b denote two known constants. • E(aX + b) = aE(X) + b 1 • V (aX + b) = a2V (X) • V (X) = E(X2)− [E(X)]2 • E(X + Y ) = E(X) + E(Y ) • V (X + Y ) = V (X) + V (Y ) Sampling Distribution Let X1, . . . , Xn be an iid sample with E(Xi) = µ and V (Xi) = σ 2. Denote X̄ the sample mean and s2 the sample variance. X̄ ∼ N ( µ, σ2 n ) X̄ − µ σ/ √ n ∼ N(0, 1) X̄ − µ s/ √ n ∼ tn−1 Point Estimation Let X and Y be estimators for θ. • Bias = E(X)− θ • MSE (X) = E[(X − θ)2] = V(X) + [Bias(X)]2 • Efficiency of X compared to Y = MSE(Y ) MSE(X) *MSE = mean squared error Confidence Interval for One Mean • If the population variance σ2 is known: x̄± z(1−C%)/2 × σ√ n . where z(1−C%)/2 is the (1 − C%)/2 quantile of the standard Normal distribution. • If the population variance σ2 is unknown: x̄± t(1−C%)/2, n−1 × s√ n . Confidence Interval for the Difference in Two Means • If σ21 and σ22 are known: (x1 − x2)± z(1−C%)/2 × √ σ21 n1 + σ22 n2 . • If σ21 and σ22 are unknown and equal: (x1 − x2)± t(1−C%)/2, n1+n2−2 × sp √ 1 n1 + 1 n2 . sp = √ (n1 − 1)s21 + (n2 − 1)s22 n1 + n2 − 2 . • If σ21 and σ22 are unknown and unequal: (x1 − x2)± t(1−C%)/2, tWS × √ s21 n1 + s22 n2 tWS = (s21/n1 + s 2 2/n2) 2 (s21/n1) 2/(n1 − 1) + (s22/n2)2/(n2 − 1) . Hypothesis Testing • Type I error (α) = P (reject H0|H0 is true) • Type II error (β) = P (not reject H0|H0 is false) • Power = 1− β • Test statistic for one mean, H0 : µ = µ0:, X̄ − µ0 σX̄ • Test statistic for difference of two sample means, H0 : µ1 − µ2 = d0, (X1 −X2)− d0 σX1−X2 Joint Distribution Let X and Y denote two random variables with joint distribution p(x, y). Let a and b denote two known constants • E[g(X,Y )] = ∑ xy g(x, y)p(x, y) • V [g(X,Y )] = ∑ xy (g(x, y)− E[g(x, y)]) 2 p(x, y) 2