Skittles Project

Skittles Project
By: Emma Vance

Introduction:
For this Skittles Project, all of our units learned in Stats 1040 were compiled into a fun-filled
project. We organized data, graphed the data, calculated the confidence intervals, etc. All the
data collected was from a bag of skittles.
Part One: Data Collection

Red: 14
Orange: 20
Yellow: 21
Green: 19
Purple: 15
In part two I took the data from part one and displayed predictions, as well as the qualitative and
quantitative data.
Part Two: Organizing and Displaying Qualitative Data

1. Predictions: What proportion of the Skittles do you expect to see of each color?
Red Orange Yellow Green Purple
Predicted 0.1 0.3 0.3 0.2 0.1

Proportion for
each color
2. Data: Collect data from your own bag and entire class sample.
Red Orange Yellow Green Purple Total Count
Counts for
my bag 14 20 21 19 15 89
Counts for
the entire 302 345 295 284 283 1,509
class sample
Actual
Proportions .157 .225 .236 .213 .169 1.00
for my bag
Actual
Proportions
.200 .229 .279 .188 .267 1.00
for the entire
class sample
(I took a sample of 21 students because 91 just seem unreasonable.)
3. Graphics for Qualitative Data: I used StatCrunch to create a pie chart and a Pareto chart
for the total number of candies of each color in our class data set.
4. Skittles Colors: Paragraph Conclusion

I’m not very surprised at the colors in my bag. When I made the pie chart, I saw that the colors
were pretty much equal. I think that skittle corporate does that on purpose. Obviously, they’re
not going to count each skittle individually and place it in each bag, but they at least get a good
guess on them I’m sure. I was definitely blown away by the class count, mainly because there
were so many students, but I wasn’t surprised when I saw how close the colors came to in
comparison.
Discussion: The skittle project represents a random sampling method. There is never a set
amount of browns, reds, yellows, purples, etc., in a skittles bag. It’s always completely random.
We’re sampling from the population of the skittles bag.
In part three I took all of my data collected from part one and displayed it using quantitative and
qualitative data.
PART 3: Organizing and Displaying Quantitative Data: Total Candies per Bag
1. Summary statistics: Found using the entire class count data.
Mean number of candies per bag 60.675
The standard deviation of the number of candies per

8.891
bag
Min: 47
Q1: 57
5-number summary for the number of candies per
Med: 59
bag
Q3: 60
Max: 95
2. Histogram: “Total candies in each bag”.
3. Boxplot: “Total candies in each bag”

4. Number of Candies: Paragraph from the findings of the variable “Total candies in each bag.”
The shape is more skewed right, which surprises me honestly. I thought that the number of
candies per bag would be more uniform (bell-shaped) just because a corporate company should
make sure that all of there bags are pretty much equal. 55-65 has a lot of recurring, which
means that the Skittles company isn’t doing completely horrible, but then you have those
outliers that are 90 skittles per bag or 40 per bag. They don’t have too much of an impact on the
rest of the summary statistics, it just shows that it’s pretty crazy to have a couple of outliers like
that.
Discussion: Qualitative data is based on a certain characteristic or attribute. Quantitative

provides numerical measures/data. Side-by-side bar graphs make sense for qualitative data
because you can compare certain characteristics side by side. A regular vertical bar graph
makes sense for quantitative data because it’s based on numbers, not attributes. The color of
skittles is obviously a qualitative characteristic because it is not based on numbers, whereas the
total candies in each bag represent the quantitative data.
In part four I took all of my data analysis from part three and calculated the confidence intervals.
Part 4: Confidence Intervals

1. Proportion Yellow Candies: Construct a 99% confidence interval estimate for the population
proportion of yellow candies.
I have a total of 89 skittles in my candy bag. 21 of those skittles are yellow. To find out the
confidence interval for the population proportion, I need to use my calculator. I went into STAT,
TESTS, then the letter A. It looks like this:
X: 21
N: 89
C-Level: .90
Calculate
I then entered 21 into the X box because that is our population proportion.
Then I entered 89 into N because that is our sample size.
Then I entered .99 into the C-Level because that is our confidence interval.
After that, I hit calculate and this is my result:
(.120, .352)
That means that we are 99% confident that the yellow skittles population proportion lies
between .120 and .352
1. Mean Number of Candies: Construct a 95% confidence interval estimate for the population
mean the number of candies per bag.
To find out the confidence interval, I need to use my calculator. To find out the answer on my
calculator I first entered all the DATA to the L1 category to find the Mean and Standard
Deviation. The data was as follows; 14 Red, 20 Orange, 21 Yellow, 19 Green, and 15 Purple.
Then I went to STAT, TESTS, 8 (TInterval), then went to data and saw that the mean (17.8),
sample size (5), and standard deviation (3.114) were already inputted, so I didn’t have to worry
about that. The only thing I had to worry about was the Confidence Interval. I typed in .95 for
the 95% confidence interval. Then I hit calculate. It looks like this:
X: 17.8
Sx: 3.114
N: 5
C-Level: .99
Calculate
I ended up with (13.933, 21.667).
That means that we are 95% confident that the population means will be between 13.933
and 21.667.
Discussion: The purpose of a confidence interval is to see all the ranges of values for our
estimated population parameter instead of a single point or a “point estimate.”Wider or smaller
intervals affect the width of a confidence interval. Increasing the sample size decreases the
width, and decreasing the sample size increases the width of the confidence interval. As one
increases, the other decreases.
Summary: I learned a lot from this Skittles Project. It was fun to see all the data collected and
make sense when I put all the parts together. It was everything we learned in every unit
compiled into one project. It was fun and interesting to see how it all tied together.

Skittles Project

Uploaded by

Copyright:

Available Formats

Skittles Project

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Skittles Project

Uploaded by

Copyright:

Available Formats

Skittles Project

By: Emma Vance

Part One: Data Collection

Part Two: Organizing and Displaying Qualitative Data

Red Orange Yellow Green Purple

Predicted 0.1 0.3 0.3 0.2 0.1

Red Orange Yellow Green Purple Total Count

(I took a sample of 21 students because 91 just seem unreasonable.)

4. Skittles Colors: Paragraph Conclusion

The standard deviation of the number of candies per

2. Histogram: “Total candies in each bag”.

3. Boxplot: “Total candies in each bag”

Discussion: Qualitative data is based on a certain characteristic or attribute. Quantitative

Part 4: Confidence Intervals

I ended up with (13.933, 21.667).

You might also like