You are on page 1of 12

PROBABILITY AND STATISTICS

PROJECT
Caroline Kelley &
James Hull
INTRODUCTION
➤ To find out the country’s most popular vacation destination
and snapscores, I gathered data from all across the country.
My population is United States Citizens and my sample is my
friends and family. I gathered my data by sending out a google
form on my Facebook page, as well as asking my friends at
school my questions and writing down my results on pen and
paper. The Google form asked 2 questions: their favorite State
to visit and their snapscore, if they had one. While the data I
accumulated was representative of my friends and family, as a
vast majority of them answered, it is not representative if the
United States population. There are over 350 million people
currently living in the United States, and I had 100 responses.
QUALITATIVE DATA
➤ To gather this information, I
asked, “what is your favorite
State to visit?” I wasn't
surprised by the most
common ones, but I was
surprised by a few. I then used
this data in a Pareto and a pie
chart. The Pareto chart was
easier to read than the pie
chart, as the pie chart repeated
colors sometimes.
Analysis

From my data, I can determine that 25% of my sample enjoyed


visiting Florida the most (25 votes). The next most common state
was North Carolina with 12% (12 votes). Most states that were
voted on only had 1 vote. This made up 12% of my responses.
Washington was more popular than I thought. I suspected it
wouldn't be voted, but it got 2 votes! I was also a little surprised at
how popular North Carolina was. It got 12 votes. I suspected that
it would be less popular because it's just one state over, but I was
proven wrong! I can see the popularity of each state easily in both
my Pareto chart and my pie graph, however the pie chart is not
labeled by state. (When I put the legend on display, it covered up
some of the pie chart.)
REFLECTION
➤ Gathering this data was fairly
easy. All I had to do was ask
people a question and they
would give me the name of a
state. I did have some
instances where people on the
google form would put “South
Florida” or “Disney” as a
state, so I had to adjust that
and group their responses in
with the people who voted
Florida.
QUANTITATIVE DATA
➤ To gather information about
Snapscores, I asked, “what is
your Snapscore”? Surprisingly,
everyone we asked had a
Snapchat! I divided my data
into 11 classes and ended up
with a class width of 76,460. I
got exactly 100 responses.
HISTOGRAM
➤ The snapscores of United
States Citizens range from
360-764,959. The distribution
of snapscores is skewed to the
right. The most common
snapscores are between
359.5-76,819.5, accumulating
nearly half of the responses.
The rest of the classes
accumulated much smaller
portions of the total.
OGIVE
➤ The distribution of snapscores
among United States Citizens
is skewed to the right. Most
DISCLAIMER: the ogive
snapscores were between
displays 76,819.5 as the 359.5 and 76,819.5, where the
lowest lower bound no
matter how many times I increase is steepest. The least
tried to change it to 359.5.
Numbers was not amount of snapscores were
cooperating!
between 535,579.5-612,039.5,
where the increase is flattest.
The ogive remains relatively
flat from 459,119.5-764,959.5
because nit a lot of people had
snapscores that big.
FREQUENCY POLYGON
➤ The distribution of snapscores
among United States Citizens is
skewed to the right. This is
evident because there is a large
spike on the left side compared to
the right side, where the spikes are
much lower. Most citizens have
snapscores around the midpoint if
38,389.5, where the spike of the
frequency polygon is highest at a
frequency of 48. The next highest
is 172,509.5, with 15 snapscores.
There is a large variety in
responses, and you can tell from
the increases and decreases of the
frequency polygon.
REFLECTION
➤ Gathering the data for the
quantitative data wasn't hard,
but the hard part was
compiling it all into the
frequency distribution. I had
to go back and make sure that
I had all of my counts right, or
else it would be off. Creating
the frequency distribution was
also a little difficult because of
the large class width (76,460).
COMPARISON
➤ These two types of salta are very
different in how they are
presented. The qualitative data
displays are much easier to
understand, as with the
quantitative displays, you have to
know what ogives, histograms,
and frequency polygons are to
dissect the display and read the
data. The questions also produced
varying responses. My quantitative
question accumulated almost half
of the data into one of the classes
in the frequency distribution,
while my qualitative question
produced more varied results.
FINAL REFLECTION
➤ I think we did this project well. We were efficient in gathering our data
and putting it onto the displays. I worked with James, who was very
helpful in gathering data. I created the google form and put the
presentation together, while he went around and asked his friends on
pen and paper. If we were to do this again, I would make sure we had a
more concise population instead of something as broad at the
population if the United States. By doing this project I learned that
making data displays is much more time consuming than I originally
anticipated. We demonstrated personal responsibility by using our class
time to work on the project, growth mindset by going up and asking
people questions on ILT (which is always awkward), collaboration and
relationships by working together to complete the project, excellence by
completing the project in its entirety, and citizenship by reaching out to
several different types of people (age, gender, race, status etc).

You might also like