Knowledge Innovation Excellence LILONGWE UNIVERSITY OF AGRICULTURE AND NATURAL RESOURCES CITY-CAMPUS TO : DR. HENRY KAMKWAMBA FROM : FELIX MOYO ID NUMBER : 200200102 PROGRAME : BABM DEPARTMENT : APPLIED ECONOMICS DEPARTMENT TITLE : ACONOMETRICS 1 ASSIGNMENT COURSE : ACONOMETRICS 1 COURSE CODE : AAE 313 DUE DATE 26th September, 2022. : QEUSTION 1 I. When ππ΄π = 800, the expected GPA will be; E[GPA|SAT = 800] = .70 + .002×800 = 2.3 When SAT= 1400, the expected GPA will be; E[GPA|SAT = 1,400] = .70 + .002×1,400 = 3.5 ο This shows that the SAT score is correlated to GPA score. The higher the SAT score, the higher is the GPA. II. If the average ππ΄π in the university is 1100, then the average πΊππ΄ is; Using Law of iterated expectations; EGPA = E(E[GPA|SAT]) = E(.70 + .002 SAT) = .70 + .002 ESAT = .70 + .002×1,100. = 2.9 III. If the SAT score is 1100, then the student will have the same GPA like the average GPA because they are both related to E[πΊππ΄|ππ΄π] = 0.70 + 0.002ππ΄π. QUESTION 2 I. Proof LHS = ∑ππ=1 xi - ∑ππ=1 xΜ π = ∑π=1 xi - n xΜ π = ∑π=1 xi – n( π = ∑π=1 xi - 1 ∑ππ=1 xi) π ∑ππ=1 xi =0 II. ∑ππ=1(xi - xΜ )2= ∑ππ=1 xi (xi - xΜ ) Proof LHS ∑ππ=1[(xi - xΜ ) (xi - xΜ )] =∑ππ=1( xi2 - xΜ xi - xΜ xi + xΜ 2) =∑ππ=1( xi2 - 2 xΜ xi + xΜ 2) =∑π Μ ∑ππ=1 xi + ∑ππ=1 π₯Μ 2 π=1 π₯π2 – 2x =∑ππ=1 π₯π2 -2n xΜ 2 +nxΜ 2 =∑ππ=1 π₯π2 - n xΜ 2 =∑ππ=1 π₯π2 - n xΜ xΜ 1 =∑ππ=1 π₯π2 - xΜ [n( ∑ππ=1 xi)] π π π =∑π=1 π₯π2 - xΜ ∑π=1 xi π =∑π=1( xi2 - xΜ xi) = ∑ππ=1[ xi(xi - xΜ )] Proved III. ∑ππ=1( xi - xΜ ) (Yi - πΜ )= ∑ππ=1 xi(Yi - πΜ )= ∑ππ=1 Yi(xi - xΜ ) Proof LHS = ∑ππ=1( ππππ − ππ πΜ − xΜ Yi + xΜ πΜ ) =∑ππ=1( ππππ - ππ ∑ππ=1 π¦π - Yi ∑ππ=1 ππ + xΜ πΜ ) =∑ππ=1 ππππ - ∑ππ=1 ππ ∑ππ=1 ππ - ∑ππ=1 ππ ∑ππ=1 ππ +∑ππ=1 xΜ πΜ =∑ππ=1 ππππ - 2∑ππ=1 ππ ∑ππ=1 ππ + ∑ππ=1 ππ ∑ππ=1 ππ =∑ππ=1 ππππ - ∑ππ=1 ππ ∑ππ=1 ππ Taking ∑ππ=1 ππ=πΜ =∑ππ=1 ππππ - πΜ ∑ππ=1 ππ =∑ππ=1 ππ (Yi - πΜ ) π Taking ∑π=1 ππ = x Μ π =∑π=1 ππ (xi - xΜ ) QUESTION 3 I. E[(π − E[π])] = 0 Proof LHS E(X) = µ Therefore; E(X - µ) =E(X) - µ =µ =0 II. -µ Var(π) = E[π(π − E[π])] Proof RHS =E[X(X - µ)] =E [(X2 – X. E(π)] = E (π)].E(X) - E(π)]. E(π)] = µ. µ - µ. µ= µ2- µ2 =0 Var(x) = 0 III. Cov(π, π) = E[π(π − E[π])] = E[(π − E[π])π] Proof E[X(Y – E(Y)] = E[XY – X.E(Y)] =E(XY) – E(X).E(Y) But, E(XY)= E(X)E(Y) Therefore, E(X)E(Y) – E(X)E(Y)= 0 E[(X –E(X)Y)= E(YX – YE(X) = E(YX) – E(Y)E(X) =E(Y)E(X) – E(Y)E(X) =0