Z z α 3 reject h if z z α 2 note n ˆ π and n 1 ˆ

Info icon This preview shows pages 8–11. Sign up to view the full content.

View Full Document Right Arrow Icon
z 0 < - z α 3. reject H 0 if | z 0 | > z α/ 2 Note: n ˆ π and n (1 - ˆ π ) must be greater than or equal to 5 for both populatons in order for the normal approximation (and hence for this test) to hold. That is, the above test is valid when x 1 5, n 1 - x 1 5, x 2 5, and n 2 - x 2 5. / £ ¡ ¢ EXAMPLE 10.4 In a recent survey of county high school students ( n 1 = 100 males and n 2 = 100 females), 58 of the males and 46 of the females sampled said they consume alcohol on a regular basis. Use the sample data to conduct a test H 0 : π 1 - π 2 = 0 against the one-sided alternative H a : π 1 - π 2 > 0, that a higher proportion of males than females consume alcohol on a regular basis. Use α = . 05. SOLUTION The four parts of the statistical test are shown here: H 0 : π 1 - π 2 = 0 H a : π 1 - π 2 > 0 8
Image of page 8

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
T.S.: z 0 = ˆ π 1 - ˆ π 2 r b π (1 - b π ) 1 n 1 + 1 n 2 · R.R.: For α = . 05, reject H 0 if z > 1 . 645. From the sample data we find ˆ π 1 = 58 100 = . 58 , ˆ π 2 = 46 100 = . 46 , and ˆ π = 58 + 46 100 + 100 = . 52 , Note also that n ˆ π and n (1 - ˆ π ) are 5 or more for both samples, validating the normal approximations to the binomial. Substituting into the test statistic, we obtain z = . 58 - . 46 q . 52( . 48) ( 1 100 + 1 100 ) = . 12 . 071 = 1 . 69 . Conclusion: Since z = 1 . 69 exceeds 1.645, we reject H 0 : π 1 - π 2 = 0; we have shown that a higher proportion of high school males than females in the county studies consumes alcohol on a regular basis. 10.4 The Multinomial Experiment and Chi-Square Goodness- of-fit Test ¤ § ¥ ƒ The Multinomial Experiment 1. The experiment consists of n identical trials. 2. Each trial results in one of k outcomes. 3. The probability that a single trial will result in outcome i is π i , i = 1 , 2 , . . . , k, and remains constant from trial to trial. (Note: i π i = 1. ) 4. The trials are independent. 5. We are interested in n i , the number of trials resulting in outcome i . (Note: i n i = n .) The probability distribution for the number of observations resulting in each of the k outcomes, called the multinomial distribution , is given by the for- mula P ( n 1 , n 2 , . . . , n k ) = n ! n 1 ! n 2 ! . . . n k ! π n 1 1 π n 2 2 · · · π n k k 9
Image of page 9
Recall from Chapter 4, where we discussed the binomial probability distri- bution, that n ! = n ( n - 1) · · · 1 and 0! = 1 . We can use the formula for the multinomial distribution to compute the probability of particular events. Note, when k = 2, the multinomial experiment reduces to the binomial experiment. Equivalently, the multinomial distribution reduces to the binomial distribution. / £ ¡ ¢ EXAMPLE 10.5 (only required for AMS graduate students) Previous experience with the breeding of a particular herd of cattle suggests that the probability of obtaining one healthy calf from a mating is . 83. Similarly, the probabilities of obtaining zero or two healthy calves are, respectively, .15 and .02. If a farmer breeds three dams from the herd, find the probability of obtaining exactly three healthy calves.
Image of page 10

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 11
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern