NivaarExam PrepOfficial exam papers ↗

04-BS-2 · December 2017

Question 7 of 8

Nivaar worked solution (AI-drafted; not reviewed by a licensed engineer)

Notes on this paper

National Examinations, December 2017 — 04-BS-2 Probability and Statistics, 2 hours, closed book except one hand-written information sheet and an approved calculator. Eight questions of equal value; the exam instructs "any 5 questions constitute a complete paper," but all 8 are answered here as a full study resource.

Reference texts: Walpole, Myers, Myers & Ye, Probability & Statistics for Engineers and Scientists (9th ed.) — used throughout for distribution theory, estimation, and hypothesis-testing procedures.

Question 7 (20 marks: (a) 10, (b) 10)

Question text not reproduced: the examination questions are © Engineers and Geoscientists BC. Open the official past paper (linked at the top of this page) to read the question, then follow the worked solution below.

Given. Two independent samples of bulb lifetimes: A ($n_A=11$, $\bar{x}_A=11{,}860$, $s_A=370$) and B ($n_B=10$, $\bar{x}_B=11{,}980$, $s_B=250$).

Find. (a) Test $H_0:\sigma_A=\sigma_B$. (b) Test $H_0:\mu_A=\mu_B$, using the F-test result from (a) to choose the correct t-procedure.

Approach. Compare the two variances with an F-test first (assuming both populations are Normal, independent samples) — the outcome decides whether the means are compared with a pooled-variance or a Welch (unequal-variance) t-test.

  1. (a) F-test for equal variances. Put the larger sample variance on top: $$F = \frac{s_A^2}{s_B^2} = \frac{370^2}{250^2} = \frac{136{,}900}{62{,}500} = 2.190.$$ Critical value $F_{0.025,10,9}=3.964$ (df$_A$=10 numerator, df$_B$=9 denominator). Since $2.190 < 3.964$, we fail to reject H₀ — the two population variances are not significantly different, so a pooled-variance t-test is the right procedure for part (b).
  2. (b) Pooled t-test for equal means. Pooled variance: $$s_p^2 = \frac{(n_A-1)s_A^2+(n_B-1)s_B^2}{n_A+n_B-2} = \frac{10(370^2)+9(250^2)}{19} = 101{,}657.9, \qquad s_p = 318.8.$$ $$t = \frac{\bar{x}_A-\bar{x}_B}{s_p\sqrt{1/n_A+1/n_B}} = \frac{11{,}860-11{,}980}{318.8\sqrt{1/11+1/10}} = \frac{-120}{139.3} = \boxed{-0.861}.$$ With df $=19$, $t_{0.025,19}=2.093$, and $|-0.861|<2.093$, we fail to reject H₀ — the mean lifetimes of the two manufacturers' bulbs are not significantly different.
Question 7 — final results
PartQuantityValue
(a)F stat vs F-crit2.190 < 3.964 → fail to reject (pool)
(b)t stat vs t-crit−0.861, |t|<2.093 → fail to reject
Check: assumes both bulb-lifetime populations are Normally distributed and the two samples are independent — the standard assumption for the F-test and two-sample t-test with small samples.