Question

Problem 6 (39 points) Color blindness is a condition much more prevalent among males than females. But is color blindness uniformly spread among males? Let P? - proportion of color-blind people in the Caucasian American male population P? - proportion of color-blind people in the Asian American male population In a random sample of 810 Caucasian American males, 65 are diagnosed with color blindness, In a random sample of 792 Asian American males, 43 are diagnosed with color blindness. Do the sample results show good evidence that the true population proportion of color-blind Caucasian American males is greater than the population proportion among Asian American males? 1. The null hypothesis is: H?: P? - P? = 0. What is the alternative hypothesis? H?: 2. Calculate the individual sample proportions and the sample statistic to three decimal places $\hat{p}_1$ $\hat{p}_2$ $\hat{p}_1 - \hat{p}_2$ 3. Here is plot of a randomization distribution from 3000 randomization samples. Is it appropriate to use this distribution for p-value estimation? Why or why not? samples = 3000 mean = -0.00048 std. error = 0.012 Left Tail Two Tail Right Tail 250 200 150 100 50 0 -0.04 -0.03 -0.02 -0.01 0.00 0.01 0.02 0.03 0.04 null = 0 0.022 0.026 4. What is the p-value for the test according to the above plot? p-value = 5. Fill in the blanks in the following interpretation of the p-value. Assuming that there is no difference a difference of 0.026 (choose one) in the proportions of color-blind Caucasian American and Asian American males, the chance of observing a statistic as extreme as ours is equal to

Problem 6 (39 points)
Color blindness is a condition much more prevalent among males than females.
But is color blindness uniformly spread among males? Let
P? - proportion of color-blind people in the Caucasian American male population
P? - proportion of color-blind people in the Asian American male population
In a random sample of 810 Caucasian American males, 65 are diagnosed with color blindness,
In a random sample of 792 Asian American males, 43 are diagnosed with color blindness.
Do the sample results show good evidence that the true population proportion of color-blind
Caucasian American males is greater than the population proportion among Asian American males?
1. The null hypothesis is: H?: P? - P? = 0. What is the alternative hypothesis?
H?:
2. Calculate the individual sample proportions and the sample statistic to three decimal places
$\hat{p}_1$
$\hat{p}_2$
$\hat{p}_1 - \hat{p}_2$
3. Here is plot of a randomization distribution from 3000 randomization samples.
Is it appropriate to use this distribution for p-value estimation? Why or why not?
samples = 3000
mean = -0.00048
std. error = 0.012
Left Tail Two Tail Right Tail
250
200
150
100
50
0
-0.04 -0.03 -0.02 -0.01 0.00 0.01 0.02 0.03 0.04
null = 0
0.022
0.026
4. What is the p-value for the test according to the above plot?
p-value =
5. Fill in the blanks in the following interpretation of the p-value.
Assuming that there is no difference a difference of 0.026 (choose one)
in the proportions of color-blind Caucasian American and Asian American males,
the chance of observing a statistic as extreme as ours is equal to

Added by Jason B.

Question

Please give Ace some feedback