9709/72

Mathematics 9709/72February/March 2016

Cambridge A-Level · Probability & Statistics 2 · worked solutions for every part, with the mark scheme

7
questions
50
marks
75
minutes

Topics Linear Combinations of Random Variables · Hypothesis Tests · Sampling and Estimation · The Poisson Distribution · Continuous Random Variables

Q15MLinear Combinations of Random VariablesFree sample

A fair six-sided die is thrown 20 times and the number of sixes, XX, is recorded. Another fair six-sided die is thrown 20 times and the number of odd-numbered scores, YY, is recorded. Find the mean and standard deviation of X+YX + Y.

DifficultyMedium
Worked solution

Approach

Since XX counts sixes in 20 throws of a fair die, XX is binomial with n=20n=20 and p=16p=\frac{1}{6}. Since YY counts odd-numbered scores, YY is binomial with n=20n=20 and p=12p=\frac{1}{2}. The two dice are thrown independently, so XX and YY are independent. Use the binomial mean and variance formulae, then combine using E(X+Y)=E(X)+E(Y)E(X+Y)=E(X)+E(Y) and Var(X+Y)=Var(X)+Var(Y)\mathrm{Var}(X+Y)=\mathrm{Var}(X)+\mathrm{Var}(Y).

Working

For XX:

E(X)=20×16=103E(X)=20\times\frac{1}{6}=\frac{10}{3} Var(X)=20×16×56=259\mathrm{Var}(X)=20\times\frac{1}{6}\times\frac{5}{6}=\frac{25}{9}

For YY:

E(Y)=20×12=10E(Y)=20\times\frac{1}{2}=10 Var(Y)=20×12×12=5\mathrm{Var}(Y)=20\times\frac{1}{2}\times\frac{1}{2}=5

Combine:

E(X+Y)=E(X)+E(Y)=103+10=403E(X+Y)=E(X)+E(Y)=\frac{10}{3}+10=\frac{40}{3} Var(X+Y)=Var(X)+Var(Y)=259+5=709\mathrm{Var}(X+Y)=\mathrm{Var}(X)+\mathrm{Var}(Y)=\frac{25}{9}+5=\frac{70}{9} sd(X+Y)=709=7032.79\mathrm{sd}(X+Y)=\sqrt{\frac{70}{9}}=\frac{\sqrt{70}}{3}\approx 2.79

Answer

E(X+Y)=40313.3,sd(X+Y)=7032.79E(X+Y)=\frac{40}{3}\approx 13.3,\quad \mathrm{sd}(X+Y)=\frac{\sqrt{70}}{3}\approx 2.79
Final answer

E(X+Y) = 40/3 ≈ 13.3; sd(X+Y) = √70/3 ≈ 2.79

Detailed explanation

Walkthrough

First identify what each variable represents. XX is the number of sixes in 20 throws, so each throw has probability p=16p=\frac{1}{6} of success. YY is the number of odd-numbered scores; on a die, 1, 3 and 5 are odd, so p=12p=\frac{1}{2}. Both are binomial counts because each throw is independent and has a fixed number of trials.

For a binomial distribution, the mean is npnp and the variance is np(1p)np(1-p). Apply this to XX and YY separately. Then, because the two dice are thrown independently, XX and YY are independent random variables. For independent variables, expectations add and variances add. This is why we add the two variances before taking the square root to find the standard deviation.

Key Takeaways

  • A count of successes in a fixed number of independent trials is binomial.
  • For XBin(n,p)X \sim \mathrm{Bin}(n,p), E(X)=npE(X)=np and Var(X)=np(1p)\mathrm{Var}(X)=np(1-p).
  • For independent random variables, E(X+Y)=E(X)+E(Y)E(X+Y)=E(X)+E(Y) and Var(X+Y)=Var(X)+Var(Y)\mathrm{Var}(X+Y)=\mathrm{Var}(X)+\mathrm{Var}(Y).
  • Standard deviation is the positive square root of variance.

Common Mistakes

  • Using p=16p=\frac{1}{6} for YY as well; odd-numbered scores have probability 12\frac{1}{2}.
  • Adding standard deviations instead of variances. You must add variances first, then square root.
  • Forgetting that the variance addition rule requires independence. Here the dice are separate, so independence is valid.
  • Giving the variance instead of the standard deviation as the final answer.

Things to Be Careful About

  • Keep exact fractions throughout and only round at the end.
  • Check the probability for YY: odd scores are 1, 3, 5, so p=36=12p=\frac{3}{6}=\frac{1}{2}.
  • The final standard deviation can be written as 703\frac{\sqrt{70}}{3}, 709\sqrt{\frac{70}{9}}, or 2.792.79 to 3 significant figures.
  • The mark scheme accepts equivalent forms such as 2×53\sqrt{2}\times\frac{5}{3} for the standard deviation.
Techniques used
recognise X and Y as binomial random variablesuse binomial mean and variance formulaeadd expectations of independent variablesadd variances of independent variablestake the square root of the variance for the standard deviation

The rest of this paper

6 more questions
  • Q2Hypothesis Tests5M
  • Q3Hypothesis Tests5M
  • Q4Linear Combinations of Random Variables5M
  • Q5Sampling and Estimation8M
  • Q6The Poisson Distribution · Linear Combinations of Random Variables11M
  • Q7Continuous Random Variables11M
Loading the full paper…