Scribd
Upload
154 views1 page

Sample Size Calculations Revisited: P r (reject H - H) = α

The document discusses sample size calculations for hypothesis testing. It reviews controlling the probability of a type I error and the power of a test. It shows that to calculate the power and satisfy the requirement, the sample size must be large enough such that the standardized test statistic exceeds the critical value with probability 1-β. An equation is derived relating the necessary sample size to the standard deviation, the difference between the null and alternative hypotheses, and the power.

Uploaded by

Fanny Sylvia C.
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
154 views1 page

Sample Size Calculations Revisited: P r (reject H - H) = α

The document discusses sample size calculations for hypothesis testing. It reviews controlling the probability of a type I error and the power of a test. It shows that to calculate the power and satisfy the requirement, the sample size must be large enough such that the standardized test statistic exceeds the critical value with probability 1-β. An equation is derived relating the necessary sample size to the standard deviation, the difference between the null and alternative hypotheses, and the power.

Uploaded by

Fanny Sylvia C.
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/ 1

Sample Size Calculations Revisited

Recall that for a given hypothesis test we want to control the probability of a type I error at no more
than α. That is we want

P r {reject H0 |H0 } = α (1)


and
P r {reject H0 |Ha } = 1 − β (2)
Recall that we reject H0 when
σ
x̄ > z1−α √ + µ0
n
Then, we require ½ ¾
σ
P r x̄ > z1−α √ + µ0 |µa = 1 − β (3)
n
to satisfy our requirement for power. Now, to calculate this probability we must standardize under Ha .
½ ¾ ( )
σ x̄ − µa z1−α √σn + µ0 − µa
P r x̄ > z1−α √ + µ0 |µa = 1 − β ⇒ P r > =1−β
n √σ √σ
n n

This implies that


z1−α √σn + µ0 − µa
= zβ
√σ
n

Solving for n, we have

You might also like