In: Statistics and Probability
Background
You will need to purchase a regular-sized bag of milk chocolate M&M’s for this project.
Let’s work to answer a very important question, vexing humankind for decades: Are the colors evenly distributed in a bag of M&M's???? Is the company reporting accurate color percentages for their product? This activity will guide you through constructing a confidence interval for the proportion of M&M's in a particular color.
M&M says:
On average, our mix of colors for M&M'S CHOCOLATE CANDIES is:
M&M'S MILK CHOCOLATE: 24% cyan blue, 20% orange, 16% green, 14% bright yellow, 13% red, 13% brown.
Each large production batch is blended to those ratios and mixed thoroughly. However, since the individual packages are filled by weight on high-speed equipment, and not by count, it is possible to have an unusual color distribution.
Part 1: Confidence Interval for Single Bag (20 points)
Milk Chocolate M&M’s come in 6 colors; blue, orange, green, yellow, red, and brown.
Color of choice:
Number of M&M's in your color:
Total number of M&M's:
Proportion of M&M's in your color:
Color of choice: Green
Number of M&M's in your color:
Total number of M&M's:100
Proportion of M&M's in your color: 0.12
Color | Observed | Expected |
Cyan blue | 24 | 24 |
Orange | 15 | 20 |
Green | 12 | 16 |
Bright yellow | 14 | 14 |
Red | 19 | 13 |
Brown | 16 | 13 |
(a)
n = 100
p = 0.12
% = 95
Standard Error, SE = √{p(1 - p)/n} = √(0.12(1 - 0.12))/100 = 0.032496154
z- score = 1.959963985
Width of the confidence interval = z * SE = 1.95996398454005 * 0.0324961536185438 = 0.06369129
Lower Limit of the confidence interval = P - width = 0.12 - 0.0636912907284269 = 0.05630871
Upper Limit of the confidence interval = P + width = 0.12 + 0.0636912907284269 = 0.18369129
The confidence interval is [0.0563, 0.1837]
(b)
If samples of size 100 are repeatedly drawn from the population and the confidence intervals constructed such intervals will contain the true proportion 95% of the time.
(c) Margin of error = 0.0637
(d) Conditions to be met are
(i) Conditions of the central limit theorem must be met in order to use the normal model
(ii) The data must be sampled randomly
(iii) The sample values must be independent of each other.
(iv) The sample size must be sufficiently large
All these conditions are met in the present case
(e) Yes, the above confidence interval contains 0.12
(f) If we had a larger sample, the width of the confidence interval would be reduced. For example, if we had a sample size of 200 instead of 100, the margin of error would become 0.045, and confidence interval would become [0.075, 0.165]