Call me, maybe? Defective Phones Question #3 Intent of Question The primary goals of this question were to assess a student's ability to (1) recognize binomial distribution scenarios and calculate relevant binomial probabilities; (2) calculate an expected value based on the binomial distribution; (3) perform a conditional probability calculation from a discrete random variable; and (4) perform a probability calculation involving independent events using the multiplication rule. Scoring: This question is scored in three sections. Section 1 consists of parts (a) and (b), section 2 consists of part (c), and section 3 consists of part (d). Each of the three sections is scored as essentially correct (E), partially correct (P), or incorrect (I). Question #3 A smartphone manufacturer is concerned about the proportion of defectives produced at a certain plant which produces many smartphones every day. Historically, approximately 15% of phones produced at this plant have been defective. As part of their quality assurance testing, 4 smartphones are selected at random from a day's production. Part (a) Let X represent the number of defective phones in the sample of 4 phones. Complete the table below for the probability distribution of X, assuming the historic defective rate holds. x 0 1 0.522 0.368 2 3 4 P(x) 0.001 Part (a) solution The random variable X has binomial distribution with n = 4 and p = 0.15. The probability that exactly 2 of the 4 selected phones are defective is: 𝑃 𝑋=2 = 4 2 0.152 .852 ≈ 0.098 The probability that exactly 3 of the 4 selected phones are defective is: 𝑃 𝑋=3 = 4 3 0.153 .851 ≈ 0.011 The completed probability distribution of X is displayed below. x 0 1 2 3 4 0.522 0.368 0.098 0.011 0.001 P(x) Section 1 - continued Part (b) Part (b) solution What is the expected number of defective phones in this sample? The expected number of defective phones in this sample is: 𝐸 𝑋 = 𝜇 = 𝑛𝑝 = 4 0.15 = 0.60 phones. Section 1 is scored as follows: Essentially correct (E) if both probabilities are filled in correctly in the table in part (a) with supporting work AND the expected value is calculated correctly in part (b) with supporting work. Partially correct (P) if both probabilities are filled in correctly in the table in part (a) with supporting work AND the expected value is not calculated correctly in part (b) OR the probabilities in part (a) AND the expected value in part (b) are both calculated using incorrect (but reasonable) values for the binomial parameters n and p OR the response does not recognize this as a binomial setting and so the probabilities in part (a) are not calculated correctly AND the expected value in part (b) is calculated correctly using the formula for the mean of a discrete random variable and the incorrect probabilities given in part (a) OR the correct answers are given in both part (a) and part (b) but sufficient supporting work is not given in part (a) or part (b) or both. Section 1 scoring continued Incorrect (I) if the response does not meet the criteria for E or P, including if a correct answer is given in only one of parts (a) and (b) and sufficient supporting work for the correct answer is not given. Notes: The calculator commands, binompdf(4, 0.15, 2) and binompdf(4, 0.15, 3), are not considered sufficient supporting work in part (a), unless somewhere in the response for parts (a) and (b) the value 0.15 is labeled as p and the value 4 is labeled as n. Section 2 Part (c) Part c What is the probability that all four phones were defective given that at least two defectives were found in the sample? Part c- solution The probability that all four phones were defective given that at least two were defective is: 𝑃 𝑋=4𝑋≥2 𝑃(𝑋 = 4 and 𝑋 ≥ 2) = 𝑃(𝑋 ≥ 2) 𝑃(𝑋 = 4) = 𝑃(𝑋 ≥ 2) 0.001 = 0.098 + 0.011 + 0.001 ≈ 0.009 Section 2 scoring Essentially correct (E) if the probability is computed correctly, with work shown that includes correct numerical values for both the numerator and denominator. Partially correct (P) if the response includes a numerator and denominator in calculating the conditional probability, with one (numerator or denominator) correct in numerical value and the other incorrect; OR if the correct answer is given, but no work is shown. Incorrect (I) if the response does not meet the criteria for E or P. Section 3 Part (d) Suppose that each day the phones are produced independently of all other days' phones. If a sample of size 4 is taken every weekday (5 total samples), what is the probability that there are no defective phones found in any of the 5 samples taken? Part (d) solution Because the phones are produced independently across days, the probability that none of the five days' samples contains a defective phone is 0.522 5 ≈ 0.039. Section 3 scoring Essentially correct (E) if the response correctly calculates the probability AND shows sufficient work. Partially correct (P) if the response reports the correct probability but shows no work or does not show sufficient work OR if the response uses the multiplication rule involving five events but does so incorrectly and/or with an incorrect probability of no defectives in a given day. Incorrect (I) if the response does not meet the criteria for E or P. Scoring 4 Complete Response All three sections essentially correct 3 Substantial Response Two sections essentially correct and one section partially correct 2 Developing Response Two sections essentially correct and one section incorrect OR One section essentially correct and one or two sections partially correct OR Three sections partially correct 1 Minimal Response One section essentially correct and two sections incorrect OR Two sections partially correct and one section incorrect