Question

1. Environmentalists are concerned that Chinook Salmon are becoming infertile due to the increase of toxic chemicals in the Pacific Ocean. Past studies have estimated that the proportion of Chinook that are infertile is 6%. You randomly and independently collect a sample of 240 Chinook and find that 10% of them are infertile. Is this statistically significant evidence that the past studies are underestimating salmon infertility?

Answer this question by

a. Thinking of this problem as a hypothesis test and finding a p-value.

b. State your conclusion about the null hypothesis by comparing the p-value to alpha.

Use  α = .1.

2. True or False

a. Suppose that (-0.47, -0.39) is a confidence interval for the difference of proportions (p₁ - p₂)_. This indicates that p₁ is greater than p₂

b. If two variables are strongly correlated (r > 0.9 or r < -0.9), we can say that the explanatory variable is causing the response variable.

c. If two variables are negatively correlated this means that when one increases the other tends to increase.

d. If p-value < ? then I reject the null hypothesis. This means I'm 100% sure that the null is false and I reject the null hypothesis.

e. All confidence intervals for a population proportion contain p.

f. The “Line of Best Fit” is the line that minimizes the sum of the squared distances between the points and the line.

g. Suppose variables x and y are correlated. It's possible that the x variable is causing the values we are observing in the y variable.

Answer 1

Que.1

Hypothesis:

Test statistic,

P-value = P(z > 2.609) = 1 - p(z < 2.609) = 1-0.9955 = 0.0045

b.

Since p-value is less than = 0.1, we reject null hypothesis and conclude that proportion of Chinook that are infertile is greater than 6%.

There is statistically significant evidence that the past studies are underestimating salmon infertility.