BUSS1020 Final Examination Formula Sheet Sample Covariance Range n ¡ X Range = X largest − X smallest C ov(X , Y ) = X i − X̄ ¢¡ Yi − Ȳ ¢ i =1 n −1 Z-score Empirical Rule X − X̄ Z= S If distribution is bell-shaped, then approximately: • 68% of data is within ±1 standard deviation of the mean. Population Variance N ¡ X σ2 = • 95% of data is within ±2 standard deviation of the mean. ¢2 Xi − µ i =1 N • 99.7% of data is within ±3 standard deviation of the mean. Population Standard Deviation v u N uX¡ ¢2 u Xi − µ u t i =1 σ= N Chebyshev’s Rule Regardless of how the data is distributed, at least: µ ¶ 1 1 − 2 × 100%, k > 1 k Sample Variance n ¡ X S2 = X i − X̄ will fall within k standard deviations of the mean. ¢2 i =1 n −1 Counting Rules • Multiplication rule: (k 1 )(k 2 )...(k n ) • Repetition rule: k n Sample Standard Deviation v uX n ¢2 u ¡ X i − X̄ u t i =1 S= n −1 • Factorial: n! = (n)(n − 1)(n − 2)...(2)(1) • Permutations: nP k = n! (n − k)! • Combinations: nC k = Coefficient of Variation µ ¶ S CV = · 100% X̄ Sample Coefficient of Correlation r= Sample Mean C ov(X , Y ) S X SY General Addition Rule n X X̄ = n! k!(n − k)! Xi i =1 n P (A or B ) = P (A) + P (B ) − P (A and B ) X 1 + X 2 + X 3 + ... + X n = n Page 1 of 5 BUSS1020 Final Examination Conditional Probability P (A|B ) = Binomial Distribution Formula P (A and B ) P (B ) P (X = x|n, π) = nC x πx (1 − π)n−x n! = πx (1 − π)n−x x!(n − x)! Independence A and B are independent if: Mean and Standard deviation: µ = nπ p σ = nπ(1 − π) P (A|B ) = P (A) Poisson Distribution Formula Marginal Probability P (A) = k X P (A|B i )P (B i ) i =1 = P (A|B 1 )P (B 1 ) + P (A|B 2 )P (B 2 ) Mean and Standard deviation: + P (A|B 3 )P (B 3 ) + ... + P (A|B k )P (B k ) µ=λ p σ= λ Bayes Theorem Hypogeometric Distribution Formula P (A|B i )P (B i ) P (B i |A) = P (A) = A P (X = x|n, N , A) = P (A|B i )P (B i ) k X C x · N −AC n−x NC n Mean and Standard deviation: nA µ= N s P (A|B i )P (B i ) i =1 = e −λ λx x! P (X = x|λ) = σ= P (A|B i )P (B i ) P (A|B 1 )P (B 1 ) + ... + P (A|B k )P (B k ) n A(N − A) N − n · N2 N −1 Sum of Two Random Variables: Expected Value Expected Value E (X + Y ) = E (X ) + E (Y ) µ = E (X ) = N X x i P (X = x i ) E (a X + bY ) = E (a X ) + E (bY ) = aE (X ) + bE (Y ) i =1 Variance Sum of Two Random Variables: Variance 2 2 σ = E (X ) − [E (X )] = E [X − E (X )] = N X V ar (X + Y ) = σ2X +Y 2 = σ2X + σ2Y + 2σ X ,Y 2 V ar (a X + bY ) = σ2aX +bY [x i − E (X )]2 P (X = x i ) = σ2aX + σ2bY + 2σaX ,bY i =1 = a 2 σ2X + b 2 σ2Y + 2abσ X ,Y Covariance σX Y = N X £ ¤ [x i − E (X )] y i − E (Y ) P (x i , y i ) i =1 = E (X Y ) − [E (X )][E (Y )] Sum of Two Random Variables: Standard Deviation q σ X +Y = σ2X +Y Page 2 of 5 BUSS1020 Final Examination t-score for Sampling Distribution Z-score Z= X −µ σ t= Assessing Normality IQR ∼ = 1.33S Confidence Interval - µ (σ known) σ X̄ ± Zα/2 p n Uniform Distribution Formula P (X < x) = x −a b−a Confidence Interval - µ (σ unknown) Mean and Standard deviation: a +b µ= s2 (b − a)2 12 σ= Exponential Distribution Formula P (X < x) = 1 − e −λx Mean and Standard deviation: 1 µ= λ 1 σ= λ S X̄ ± t α/2, n−1 p n Confidence Interval - proportions s p(1 − p) p ± Zα/2 n Sample Size for the Mean n= n= X̄ − µ σ p n e2 2 Zα/2 π(1 − π) e2 Pooled Variance - σ1 and σ2 equal Z-score for Sampling Distribution Z= 2 Zα/2 σ2 Sample Size for Proportion Standard Error of the Mean σ σ X̄ = p n X̄ − µ S p n S P2 = (n 1 − 1)S 12 + (n 2 − 1)S 22 (n 1 − 1) + (n 2 − 1) Test Statistic - σ1 and σ2 equal ¢ ¡ ¢ X¯1 − X¯2 − µ1 − µ2 = s µ ¶ , d . f = n1 + n2 − 2 1 1 S P2 + n1 n2 ¡ Standard Error of Population Proportion s σp = π(1 − π) n Z-score for Proportions Z=r t st at p −π π(1 − π) n Confidence Interval - σ1 and σ2 equal s µ ¶ ¡ ¢ 1 1 2 X¯1 − X¯2 ± t α/2, n1 +n2 −2 S P + n1 n2 Page 3 of 5 BUSS1020 Final Examination Test statistic - σ1 and σ2 not equal ¢ ¡ ¢ ¡ X¯1 − X¯2 − µ1 − µ2 t st at = s S 12 S 22 + n1 n2 Sum of Squares = X n1 v = à !2 S 12 n1 n1 − 1 + + S 22 (X − X̄ )(Y − Ȳ ) P P ( X )( Y ) XY − n X¡ SS X X = S 12 !2 n2 à !2 S 22 Slope Coefficients n2 b1 = n2 − 1 SS X Y SS X X P Y b1 X b 0 = Ȳ − b 1 X̄ = − n n P Confidence Interval - σ1 and σ2 not equal s ¡ ¢ S 12 S 22 X¯1 − X¯2 ± t α/2,v + n1 n2 Measures of Variation SST = SSR = Test statistic - Paired Difference t st at = X ¢2 X − X̄ P X 2 ( X )2 = X − n With degree of freedom: à SS X Y = D̄ − µD SD p n SSE = n X i =1 n X i =1 n X (Yi − Ȳ )2 (Yˆi − Ȳ )2 (Yi − Yˆi )2 i =1 Coefficient of Determination Confidence Interval - Paired Difference r2 = SD D̄ ± t α/2,n−1 p n Standard Error of Estimate s s P SSE (Yi − Yˆi )2 SY X = = n −2 n −2 Pooled Proportion Estimate p̄ = SSR SST X1 + X2 n1 + n2 Standard Error of Regression Slope SY X SY X S b1 = p = pP SS X (X i − X̄ )2 Z-score for Two Sample Proportions ¡ ¢ p 1 − p 2 − (π1 − π2 ) Z=s µ ¶ ¡ ¢ 1 1 p̄ 1 − p̄ + n1 n2 Test Statistic - regression slope t st at = Confidence Interval for Two Sample Proportions s ¡ ¢ p 1 (1 − p 1 ) p 2 (1 − p 2 ) p 1 − p 2 ± Zα/2 + n1 n2 b 1 − β1 r −ρ =s S b1 1−r2 n −2 F Test for Overall Significance F st at Page 4 of 5 M SR = = M SE SSR k SSE n −k −1 BUS USS10 S1020 20 Final Examina xamination tion Confidence Interval for the average Y given X 𝑌𝑌� ± 𝑡𝑡𝛼𝛼⁄2 𝑆𝑆𝑆𝑆𝑆𝑆�ℎ 𝑖𝑖 Prediction Interval for an individual Y given X 𝑌𝑌� ± 𝑡𝑡𝛼𝛼⁄2𝑆𝑆𝑆𝑆𝑆𝑆�1 + ℎ 𝑖𝑖 Where ℎ 𝑖𝑖 = (𝑋𝑋𝑖𝑖 − 𝑋𝑋�)2 1 (𝑋𝑋𝑖𝑖 − 𝑋𝑋�)2 + = 𝑛𝑛 𝑆𝑆𝑆𝑆𝑆𝑆 ∑(𝑋𝑋𝑖𝑖 − 𝑋𝑋�)2 Page 5 of 5