Scribd
Upload
42 views3 pages

Handout 14 Hypothesis Tests Regarding A Population Proportion

The document describes a hypothesis test regarding the probability of heads for a coin. A student proposes rejecting the null hypothesis if the number of heads in 64 tosses is 40 or more. This results in a Type I error probability of 0.0228 and Type II error probability of 0.0951. To reduce these to below 0.05 and 0.02 respectively, the test should be to reject the null if the number of heads in 78 tosses is 46 or more.

Uploaded by

ahmed22gouda22
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
42 views3 pages

Handout 14 Hypothesis Tests Regarding A Population Proportion

The document describes a hypothesis test regarding the probability of heads for a coin. A student proposes rejecting the null hypothesis if the number of heads in 64 tosses is 40 or more. This results in a Type I error probability of 0.0228 and Type II error probability of 0.0951. To reduce these to below 0.05 and 0.02 respectively, the test should be to reject the null if the number of heads in 78 tosses is 46 or more.

Uploaded by

ahmed22gouda22
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Handout 14 Hypothesis Tests Regarding a Population Proportion

Example : Gambling with Dr. K. ( Never a good idea ...) From conversations with my former students, it is known that I use two different kinds of coin when I gamble with my students : one coin is fair, the other is loaded to come up heads 70% of the time. The two kinds of coin look, feel, smell and sound the same. And, of course, Im not going to tell you which coin Im using ! I will allow you 64 practice tosses on which to base your decision about p, the probability the coin I give you comes up heads. In technical terms this sample is your basis for testing the pair of hypotheses : H0 : p = 0.5 versus H1 : p = 0.7 (A) One of your fellow students proposes that the null hypothesis be rejected if the number of tosses which come up heads is 40 or more, and otherwise one accepts the null hypothesis that the coin is fair. Find the probability of an error of Type I ; find the probability of an error of Type II. Solution : In terms of the sample proportion, the proposed test is to reject the null hypothesis if the sample proportion of heads is at least 40/64 = 0.625, and reject the null hypothesis otherwise. If p = 0.5 , P( Type I error ) = The key to our computations is to recall that, as a consequence of the Central Limit Theorem, for large n, is approximately a .

standard normal random variable. Thus P( Type I error ) =

. P( Z $ 2 ) = 1 - P ( Z # 2 ) = 1 - 0.9772 = 0.0228.
And if p = 0.7 , P ( Type II error ) =

. P ( Z # -1.31 ) = 0.0951.
(B) Suppose that one wishes to have a test so that the probability of a Type I error is no more than 0.05, and the probability of a Type II error is no more than 0.02. Find such a test. Solution : A reasonable test is to reject the null hypothesis if , and accept the

null hypothesis otherwise. Specifying a test comes down to specifying the critical value, c , and the sample size, n. Calculating as before, P( Type I error ) =

. From the specification on Type I error,

one must have

; so , in terms of n, the

critical value is :

Now consider the Type II error : P ( Type II error ) =

Now substitute

for c to obtain :

. Since we want to commit a Type II error with probability no more than 0.02, set , and solve for n to find

n = 78 .

Then the critical value c is

Just so you understand what this means : the test weve found consists in flipping the coin 78 times ; if there are at least 0.5931( 78 ) . 46 tosses that turn up heads , then one rejects the null hypothesis ; if there are fewer than 46 tosses that come up heads one accepts the null hypothesis ( i.e. the hypothesis that the coin youve got is fair. )

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy