In: Statistics and Probability
A researcher was interested in the amount of time cats and dogs nap while their owners are away from home on a regular work day. The 30 cats napped an average of 7.0 hours with a standard deviation of 1.5 hours. The 30 dogs napped a mean of 5.0 hours with a standard deviation of 1.5 hours. Assume that the two populations are normally distributed with equal but unknown standard deviations. Test at the 5% significance level if the amount of time cats nap is longer than the amount of time dogs nap. What is the critical value and what is your conclusion?
Below are the null and alternative Hypothesis,
Null Hypothesis, H0: μ1 = μ2
Alternative Hypothesis, Ha: μ1 > μ2
Rejection Region
This is right tailed test, for α = 0.05 and df = n1 + n2 - 2 =
58
Critical value of t is 1.672.
Hence reject H0 if t > 1.672
Pooled Variance
sp = sqrt((((n1 - 1)*s1^2 + (n2 - 1)*s2^2)/(n1 + n2 - 2))*(1/n1 +
1/n2))
sp = sqrt((((30 - 1)*1.5^2 + (30 - 1)*1.5^2)/(30 + 30 - 2))*(1/30 +
1/30))
sp = 0.3873
Test statistic,
t = (x1bar - x2bar)/sp
t = (7 - 5)/0.3873
t = 5.164
P-value Approach
P-value = 0
As P-value < 0.05, reject the null hypothesis.