Edexcel IAL Mathematics S3.3.1 standard error and unbiased estimationPractise estimating sample means, unbiased variances and standard errors, then comparing unbiased estimators by variance.SyllabusFirst assessment 2019CourseMathematics YMA01LevelA2
Exam pointscalculate x̄ and s² from totals or coded data, using n - 1 for the unbiased varianceestimate the standard error from a combined sample variance and sample sizeshow an estimator is unbiased with E(U)=µ, then choose the smaller-variance estimator
S3.3.1 - Concepts of standard error, question 1[Maximum number: 8]A random sample of two observations X1X_{1}X1 and X2X_{2}X2 is taken from a population with unknown mean μ\muμ and unknown variance σ2\sigma^{2}σ2Question (a)(a)Explain what you understand by an unbiased estimator for μ\muμTwo estimators for μ\muμ are U1U_{1}U1 and U2U_{2}U2 whereU1=3X1−2X2 and U2=X1+3X24U_{1}=3 X_{1}-2 X_{2} \quad \text { and } \quad U_{2}=\frac{X_{1}+3 X_{2}}{4}U1=3X1−2X2 and U2=4X1+3X2[ 1 ]Show AnswerMark as masteredAn estimator for μ\muμ is unbiased if its expected value is equal to μ\muμB1(1)Question (b)(b)Show that both U1U_{1}U1 and U2U_{2}U2 are unbiased estimators for μ\muμThe most efficient estimator among a group of unbiased estimators is the one with the smallest variance.[ 3 ]Show AnswerMark as masteredE(U1)=3E(X1)−2E(X2)\mathrm{E}\left(U_{1}\right)=3 \mathrm{E}\left(X_{1}\right)-2 \mathrm{E}\left(X_{2}\right)E(U1)=3E(X1)−2E(X2) or E(U2)=14(E(X1)+3E(X2))\mathrm{E}\left(U_{2}\right)=\frac{1}{4}\left(\mathrm{E}\left(X_{1}\right)+3 \mathrm{E}\left(X_{2}\right)\right)E(U2)=41(E(X1)+3E(X2))M1E(U1)=3μ−2μ=μ\mathrm{E}\left(U_{1}\right)=3 \mu-2 \mu=\muE(U1)=3μ−2μ=μ (therefore unbiased)A1csoE(U2)=14(μ+3μ)=μ\mathrm{E}\left(U_{2}\right)=\frac{1}{4}(\mu+3 \mu)=\muE(U2)=41(μ+3μ)=μ (therefore unbiased)A1csoQuestion (c)(c)By finding the variance of U1U_{1}U1 and the variance of U2U_{2}U2 state, giving a reason, the most efficient estimator for μ\muμ from these two estimators.[ 4 ]Show AnswerMark as masteredVar(U1)=9Var(X1)+4Var(X2)=13σ2\operatorname{Var}(U_1)=9\operatorname{Var}(X_1)+4\operatorname{Var}(X_2)=13\sigma^2Var(U1)=9Var(X1)+4Var(X2)=13σ2Var(U2)=116Var(X1)+916Var(X2)=58σ2\operatorname{Var}(U_2)=\frac{1}{16}\operatorname{Var}(X_1)+\frac{9}{16}\operatorname{Var}(X_2)=\frac{5}{8}\sigma^2Var(U2)=161Var(X1)+169Var(X2)=85σ2As Var(U1)>Var(U2)\operatorname{Var}(U_1)>\operatorname{Var}(U_2)Var(U1)>Var(U2), U2U_2U2 is the most efficient estimator for μ\muμ.M1 for use of a2Var(X1)+b2Var(X2)a^2\operatorname{Var}(X_1)+b^2\operatorname{Var}(X_2)a2Var(X1)+b2Var(X2).A1 for 13σ213\sigma^213σ2, A1 for 5σ2/85\sigma^2/85σ2/8, A1 for U2U_2U2 with a correct reason.Add to Test
Question (a)(a)Explain what you understand by an unbiased estimator for μ\muμTwo estimators for μ\muμ are U1U_{1}U1 and U2U_{2}U2 whereU1=3X1−2X2 and U2=X1+3X24U_{1}=3 X_{1}-2 X_{2} \quad \text { and } \quad U_{2}=\frac{X_{1}+3 X_{2}}{4}U1=3X1−2X2 and U2=4X1+3X2[ 1 ]Show AnswerMark as masteredAn estimator for μ\muμ is unbiased if its expected value is equal to μ\muμB1(1)
Question (b)(b)Show that both U1U_{1}U1 and U2U_{2}U2 are unbiased estimators for μ\muμThe most efficient estimator among a group of unbiased estimators is the one with the smallest variance.[ 3 ]Show AnswerMark as masteredE(U1)=3E(X1)−2E(X2)\mathrm{E}\left(U_{1}\right)=3 \mathrm{E}\left(X_{1}\right)-2 \mathrm{E}\left(X_{2}\right)E(U1)=3E(X1)−2E(X2) or E(U2)=14(E(X1)+3E(X2))\mathrm{E}\left(U_{2}\right)=\frac{1}{4}\left(\mathrm{E}\left(X_{1}\right)+3 \mathrm{E}\left(X_{2}\right)\right)E(U2)=41(E(X1)+3E(X2))M1E(U1)=3μ−2μ=μ\mathrm{E}\left(U_{1}\right)=3 \mu-2 \mu=\muE(U1)=3μ−2μ=μ (therefore unbiased)A1csoE(U2)=14(μ+3μ)=μ\mathrm{E}\left(U_{2}\right)=\frac{1}{4}(\mu+3 \mu)=\muE(U2)=41(μ+3μ)=μ (therefore unbiased)A1cso
Question (c)(c)By finding the variance of U1U_{1}U1 and the variance of U2U_{2}U2 state, giving a reason, the most efficient estimator for μ\muμ from these two estimators.[ 4 ]Show AnswerMark as masteredVar(U1)=9Var(X1)+4Var(X2)=13σ2\operatorname{Var}(U_1)=9\operatorname{Var}(X_1)+4\operatorname{Var}(X_2)=13\sigma^2Var(U1)=9Var(X1)+4Var(X2)=13σ2Var(U2)=116Var(X1)+916Var(X2)=58σ2\operatorname{Var}(U_2)=\frac{1}{16}\operatorname{Var}(X_1)+\frac{9}{16}\operatorname{Var}(X_2)=\frac{5}{8}\sigma^2Var(U2)=161Var(X1)+169Var(X2)=85σ2As Var(U1)>Var(U2)\operatorname{Var}(U_1)>\operatorname{Var}(U_2)Var(U1)>Var(U2), U2U_2U2 is the most efficient estimator for μ\muμ.M1 for use of a2Var(X1)+b2Var(X2)a^2\operatorname{Var}(X_1)+b^2\operatorname{Var}(X_2)a2Var(X1)+b2Var(X2).A1 for 13σ213\sigma^213σ2, A1 for 5σ2/85\sigma^2/85σ2/8, A1 for U2U_2U2 with a correct reason.