Sie sind auf Seite 1von 4

BreAnna Spackman

Skittles Project
In this experiment we except to see that in an original 2.17 ounce bag of skittles there will be
more red candies verses all the other colors within that bag. This project will display the different
statistical graphs and calculations that prove this theory.
The pie charts do not reflect the difference between total candies verses a single bag. Its hard
to decipher what color portion is bigger. However, the pareto charts help us see the differences better
between the number of candies in each bag and as a total for the class. It also displays the percentages
of colors of candies.

Total Colors of Candies

Total Colors of Candies


350
300
250
200
150
100
50
0

Red Candies
19%

Orange Candies

24%

Yellow Candies

20%

18%

Green Candies

19%

Purple Candies

Red Candies
19%
20%

23%

Orange Candies
Yellow Candies
Green Candies

18%

Purple Candies

Total Colors
of Candies
Cumlative
Percent

Own Skittles Bag

Own Skittles Bag


20%

100.0
80.0
60.0
40.0
20.0
0.0

15
10
5
0

100.0
80.0
60.0
40.0
20.0
0.0

Candies in bag
Cumlative
Percent

This chart shows that this is not a normal distribution but that it is skewed to the right.
According to the 5-number summary this boxplot represents the overall data very well. As a whole my
individual Skittles bag does reflect back to the class and keeping it within the quartiles.

Mean
Standard
Error
Median
Mode
Standard
Deviation
Sample
Variance
Kurtosis
Skewness
Range
Minimum
Maximum
Sum
Count
Q1
Q3
IQR
Lower
Upper
Outliers

Total Candies
59.85714286
0.680635957
60
60
3.119065794
9.728571429
3.989077178
-1.864110213
13
51
64
1257
21
59
61.5
2.5
55.25
65.25
51, 52

5-Number Summary
Min

51

Q1

59

Q2 (Median)

60

Q3

61.5

Max

64

Frequency

Total Candies
15
10
5
0

Frequency
Bin Range

Quantitative Data is measurable or quantifiable, such as length, weight, etc. Categorical data
(also referred to as frequency or qualitative data) is things that are grouped according to some common
property(ies) and the number of members of the group are recorded (e.g., males/females, vehicle type).
Bar graphs and pie charts are best used with categorical data to help us see what percentage of the
whole each category constitutes. Pie charts require all categories to be included in a graph. Each graph
always represents the whole. Stemplots are used with quantitative data to display shapes of
distributions, to organize numbers and make them more comprehensible. It is a descriptive technique
which gives a good overall impression of the data. When calculating out categorical data its best to use
nominal or ordinal levels of measurements. Quantitative data is found by using interval or ratio levels of
measurement because there is meaningful numbers whereas, nominal and ordinal have no meaning
within the numbers.

Confidence interval is a range of values (instead of a single value) used to estimate the true
value of a population parameter. It gives us a better sense of how good an estimate is.
99% CI of proportion:
.1993*0.8007/1257=0.0290
0.1993-0.0290=0.1702, 0.1993+0.290=0.2283
0.1702<p<0.2283
99% of the time, the proportion of yellow candies in a bag is less than 1/5 of the bag of candies because
our proportion is less than 20% (0.290).
95% CI of mean:2.086*3.119/
=1.420
59.857-1.420=58.44, 59.857+1.420=61.27
58.44<x<61.27
95% of the time, it is not likely to have less than 58 and less than 61 candies per bag.
98% CI of standard deviation:
=2.28
=4.85
2.28<s<4.85
The confidence levels do not overlap, so it appears that there is not a dramatic difference.
A hypothesis is a claim or statement about a property of a population and a hypothesis tests is used for
testing a claim about a property of a population.
0.05 SL of 20%: z= 0.2339-0.2/
*0.8/1257= 2.839
P=.007, 0.2105<p<0.2573
0.2 is not in the confidence level because it is greater than therefore we reject the hypothesis.
0.01 SL of 55: t=59.857-55/3.119/
=7.14
57.92<x<61.79 p=0
The fifty-five skittles per bag is less than the mean number, so we fail to reject the hypothesis.
The conditions of interval estimates are the sample has to be a simple random sample and the
conditions for the distribution are satisfied. There also has to be at least 5 successes and 5 failures of
attempts. Hypothesis conditions are that the sample results could easily occur by chance and not likely
to occur by chance. Our data shows, that these requirements were met. Errors that can occur would
include: the mistake of rejecting the null hypothesis when its actually true and failing to reject the null
hypothesis when its not true. Using the wrong sample size for finding the interval estimates could be an
error. These methods could be improved by making sure we have the correct sample size and results.
Also makings sure the hypothesis testing is correct of what you reject or fail to reject. My conclusion of
the results shows that most bags did have more red candies than any other color.

Critical thinking is the mode of thinking about any subject, content, or problem, in which
the thinker improves the quality of his or her thinking by skilfully analysing, assessing, and
reconstructing it. It is self-directed, self-disciplined, self-monitored, and self-corrective thinking.
Everybody can benefit from having good problem solving skills as we all encounter problems on
a daily basis; some of these problems are obviously more severe or complex than others. It
would be wonderful to have the ability to solve all problems efficiently and in a timely fashion
without difficulty, but unfortunately there is no one way in which all problems can be solved.
Being part of the medical field we use problem solving skills daily, many of what Ive
learned from previous education and experience. This class has helped me develop some new
skills as well as strengthen old ones. Four basic steps to solving a problem include: Defining the
problem, second generating alternatives, third evaluating and selecting alternatives and last
implementing solutions. This math class has helped me to break problems into steps to adjust
for easier understanding and solving the problem.
The project has also had a benefit on improving and using my problem solving and
critical thinking skills. It has broken down different techniques and equations learned in order
to come up with a conclusion about our hypothesis. Doing this project helped me realized all
the calculations that go into statistical work for our everyday use. Critical thinking wise it has
made me analyse the question at all angles on what its really asking and interpreting it into my
own words. I hope to remember these skills that I have learned throughout the class as it
comes to an end but I continue on my way.

Das könnte Ihnen auch gefallen