imagine you’re hired by a beef company called “American Beef Makers” as a Data Analyst and you’re tasked with determining if annual beef consumption has increased in the United States over the ten-year period from 2011 to 2021. In 2011 the annual consumption of beef per person (per capita) was 57.5 pounds per year. To determine if the mean annual beef consumption has increased over the ten-year period from 2011 to 2021, a random sample of 40 people was taken and their annual beef consumption from 2021 was recorded. The results are shown below, rounded to the nearest pound. 77 50 0 76 69 65 49 62 77 73 57 51 74 67 75 54 56 61 67 62 68 56 61 62 8 79 78 60 89 71 56 63 56 56 20 0 72 37 75 47 Obtain a histogram of the data. Does the data appear to be normally distributed? Obtain a boxplot of the data. Are their any outliers in the data? At the 0.05 level of significance, does the data here provide sufficient evidence to conclude that the mean annual beef consumption has increased over the ten-year period from 2011 to 2021? Use either the critical-value or p-value approach here. Be sure to include the hypothesis test setup below as well. Remove the four potential outliers of 0, 0, 8, and 20, and then obtain a new histogram without the outliers. Does the data appear to be normally distributed now? Assuming that the four potential outliers of 0, 0, 8, and 20 are not recording errors, repeat the hypothesis test from part (c) (again setting up the hypothesis test and using either the critical value or p-value approach), and compare your results with that obtained in (c). Did you make a different conclusion? Imagine you know have to make a recommendation/conclusion to the company that hired you: Assuming that the four potential outlies are not recording errors, and looking at the two results above, would you recommend using the first test with the outliers or the second test with the outliers removed? There is no right or wrong answer here, I am interested in what you think and your reasoning.
imagine you’re hired by a beef company called “American Beef Makers” as a Data Analyst and you’re tasked with determining if annual beef consumption has increased in the United States over the ten-year period from 2011 to 2021. In 2011 the annual consumption of beef per person (per capita) was 57.5 pounds per year.
To determine if the mean annual beef consumption has increased over the ten-year period from 2011 to 2021, a random sample of 40 people was taken and their annual beef consumption from 2021 was recorded. The results are shown below, rounded to the nearest pound.
77 |
50 |
0 |
76 |
69 |
65 |
49 |
62 |
77 |
73 |
57 |
51 |
74 |
67 |
75 |
54 |
56 |
61 |
67 |
62 |
68 |
56 |
61 |
62 |
8 |
79 |
78 |
60 |
89 |
71 |
56 |
63 |
56 |
56 |
20 |
0 |
72 |
37 |
75 |
47 |
- Obtain a histogram of the data. Does the data appear to be
normally distributed ?
- Obtain a boxplot of the data. Are their any outliers in the data?
- At the 0.05 level of significance, does the data here provide sufficient evidence to conclude that the mean annual beef consumption has increased over the ten-year period from 2011 to 2021? Use either the critical-value or p-value approach here. Be sure to include the hypothesis test setup below as well.
- Remove the four potential outliers of 0, 0, 8, and 20, and then obtain a new histogram without the outliers. Does the data appear to be normally distributed now?
- Assuming that the four potential outliers of 0, 0, 8, and 20 are not recording errors, repeat the hypothesis test from part (c) (again setting up the hypothesis test and using either the critical value or p-value approach), and compare your results with that obtained in (c). Did you make a different conclusion?
- Imagine you know have to make a recommendation/conclusion to the company that hired you: Assuming that the four potential outlies are not recording errors, and looking at the two results above, would you recommend using the first test with the outliers or the second test with the outliers removed? There is no right or wrong answer here, I am interested in what you think and your reasoning.
Trending now
This is a popular solution!
Step by step
Solved in 4 steps with 6 images
1)Remove the four potential outliers of 0, 0, 8, and 20, and then obtain a new histogram without the outliers. Does the data appear to be
2)Assuming that the four potential outliers of 0, 0, 8, and 20 are not recording errors, repeat the hypothesis test from part (c) (again setting up the hypothesis test and using either the critical value or p-value approach), and compare your results with that obtained in (c). Did you make a different conclusion?
3)Imagine you know have to make a recommendation/conclusion to the company that hired you: Assuming that the four potential outlies are not recording errors, and looking at the two results above, would you recommend using the first test with the outliers or the second test with the outliers removed? There is no right or wrong answer here, I am interested in what you think and your reasoning.