In: Statistics and Probability
Are yields for organic farming different from conventional
farming yields? Independent random samples from method A (organic
farming) and method B (conventional farming) gave the following
information about yield of lima beans (in tons/acre). (Reference:
Agricultural Statistics, United States Department of
Agriculture.)
Method A | 1.16 | 1.45 | 1.17 | 1.54 | 1.91 | 1.26 | 1.20 | 1.95 | 1.64 | 1.44 | 1.81 | |
Method B | 1.15 | 2.17 | 2.10 | 1.78 | 1.90 | 2.06 | 1.14 | 2.08 | 1.41 | 2.03 | 1.30 | 1.42 |
Use a 1% level of significance to test the hypothesis that there is
no difference between the yield distributions.
(a) What is the level of significance?
State the null and alternate hypotheses.
Ho: Distributions are the same. H1: Distributions are different.
Ho: Distributions are the same. H1: Distributions are the same.
Ho: Distributions are different. H1: Distributions are different.
Ho: Distributions are different. H1: Distributions are the same.
(b) Compute the sample test statistic. (Use 2 decimal places.)
What sampling distribution will you use?
normal
Student's t
chi-square
uniform
What conditions are necessary to use this distributions?
Both sample sizes must be less than 10.
Both sample sizes must be greater than 10.
At least one sample size must be less than 10.
At least one sample size must be greater than 10.
(c) Find the P-value of the sample test statistic. (Use 4
decimal places.)
(d) Conclude the test?
At the ? = 0.01 level, we reject the null hypothesis and conclude the data are not statistically significant.
At the ? = 0.01 level, we reject the null hypothesis and conclude the data are statistically significant.
At the ? = 0.01 level, we fail to reject the null hypothesis and conclude the data are not statistically significant.
At the ? = 0.01 level, we fail to reject the null hypothesis and conclude the data are statistically significant.
(e) Interpret your conclusion in the context of the
application.
Reject the null hypothesis, there is sufficient evidence that the yield distributions are different.
Fail to reject the null hypothesis, there is sufficient evidence that the yield distributions are different.
Fail to reject the null hypothesis, there is insufficient evidence that the yield distributions are different.
Reject the null hypothesis, there is insufficient evidence that the yield distributions are different.
a)
The null and alternate hypotheses are:
H0: Distributions are the same. H1: Distributions are different.
b)Test statistic
First,We will arrange the two methods jointly in ascending order and rank the two groups separately .
Then,we will add up the rank of the group with the smaller sample size,in this case,it is method A.
The sum of the ranks is denoted by R:
R=114
Let n1 be the size of the smaller sample size,i.e., n1=11 and
n2 be the size of the larger sample size,i.e., n2=12
Then,
Test statistic is
Test statistic is z=-1.11
Method A | Rank | Method B | Rank |
1.16 | 3 | 1.14 | 1 |
1.17 | 4 | 1.15 | 2 |
1.2 | 5 | 1.3 | 7 |
1.26 | 6 | 1.41 | 8 |
1.44 | 10 | 1.42 | 9 |
1.45 | 11 | 1.78 | 14 |
1.54 | 12 | 1.9 | 16 |
1.64 | 13 | 2.03 | 19 |
1.81 | 15 | 2.06 | 20 |
1.91 | 17 | 2.08 | 21 |
1.95 | 18 | 2.1 | 22 |
2.17 | 23 | ||
Sum | 114 | 162 |
We will use Normal distribution
Both sample sizes must be greater than 10.
c) we can find the exact p-value in excel by using the condition
p-value=2*(1-NORM.S.DIST(1.11,TRUE))
p-value=0.2670
Note :we are multiplying by 2 as it is a two-tailed test.
If p-value is greater than alpha vlaue,then we do not reject H0.
Here our p-value=0.2670>=0.01,hence we do not reject H0.
d) At the = 0.01 level, we fail to reject the null hypothesis and conclude the data are not statistically significant.
e)Fail to reject the null hypothesis, there is insufficient evidence that the yield distributions are different.