Sei sulla pagina 1di 11

Math 1040 Project

The overall purpose of this project is to put your understanding of statistics together and
apply it to an actual real life scenario. First we attended lectures and took notes, and as the
semester went on we were assigned project parts which we would apply concepts from class in
order to complete each part of the project. Everyone in the class got a bag of skittles and counted
the number of each skittle and also totaled them up to get the number of skittles in each bag. We
also recorded our own heights and submitted those gathered numbers for our first part of the
project. The second part was descriptive statistics, computing outliers and making graphs. The
third part consisted of correlation and regression, computing the regression equation and
deciphering whether there was a significant linear relationship. Next we did part four,
probability. Where we computed the number of times we picked out a red skittle from the whole
class data. Part five was confidence intervals, which are important in order to determine how
confident you are that the method works. Lastly, part 6 we did hypothesis testing. Making a
null hypothesis and an alternative hypothesis, and collecting evidence to test the statement.

Project Part 2: Descriptive Statistics

Candy Color: is qualitative, because color is a characteristic of the skittles.


Number of candies per bag: is quantitative (discrete) because you can physically count
the number of skittles.
The individuals for candy color are single candies
The individuals for the number of candies per bag the individuals are bags of skittles

Fences: IQR= Q3-Q1 upper fence= Q3+1.5(IQR) lower fence=Q1-1.5(IQR)


IQR= 3.5

upper fence= 61.5+1.5(3.5)= 66.75

lower fence= 58-1.5(3.5)=52.75

Outliers: 50,52
No the bag I purchased is not an outlier, I had 63 skittles. And to be an outlier it had to be
below 52.75 or above 66.75.

For the circle graph you cannot look at it and decipher which way it is skewed
For the bar graph there is no shape since candy color is qualitative
For the dot plot I would say it is skewed left
For the boxplot I would say it is skewed left

Categorical Variables: Graphs

n=total number of candies=3551

Quantitative Variable: Graphs


VV

Numerical Summaries for the Quantitative Variable

Column
Mean
Std. dev. Median Range
total
59.183333 3.1108976
59
14

Min
Max Q3 Q1 IQR Mode n
50
64 61.5 58 3.5
59 60

Project Part 3: Correlation and Regression

I do not believe you can use height to predict the number of candies that will be in a bag a
skittles that you purchase, because there is no correlation between height and number of
candies in a bag

Explanatory Variable: Height

R (correlation coefficient) = 0.17042887 n=60

Response Variable: Number of candies


CV=0.361

There is no significant linear relation between height and number of candies per bag
because CV(0.361) > r(0.170). This is the outcome I expected before I analyzed the data,
because there is no correlation between height and the number of candies you receive in a
bag of skittles.

y= 50.713668 + 0.1287705x; 58.891 candies; it was not appropriate to use this regression
equation because there was no correlation between height and number of candies

0.02905 of variation in number of candies per bag can be explained by the height

It would not be appropriate to predict the number of candies in a bag for Yao Ming,
because his height is way outside the range of collected data that we have for our class.

Correlation coefficient: r = 0.146


Regression equation: y=52.961+0.077x
Critical value: n=6 CV= 0.811
There is not a significant linear relationship between height and the number of candies
per bag because CV (0.811)> r (0.146)

Project Part 4: Probability


Problem 1
a) 16/64 * 16/64 = 0.0625
b) 16/64 * 15/63 = 0.0595
c) 1- 48/64 * 48/64 = 1- 0.5625= 0.4375
Problem 2
a) 710/3551 = 0.1999
b) 2841/3551 = 0.8000
c) 716/3551 + 726/3551 = 0.2016+ 0.2044= 0.4061
d) 698/ 698+710+701= 698/2109= 0.3310
Problem 3
a) Each experiment is performed a fixed number of times, using replacement we determined
the probability of picking out a yellow 10 times
Each trial was independent, we used replacement when we were picking out a yellow
skittle
For each trial there were two disjoint outcomes, you either picked out a yellow or you
didnt
Probability of success was the same for each trial, you had a 0.204 chance of picking out
a yellow for each trial because we used replacement
n= 61

p= 0.204

b) binompdf (10, .204, 4) = 0.0925


c) mean ()= 10(.204) = 2.04

Standard Deviation= 10(.204)(1 .204) =1.274


Problem 4
a) Because 32 is normally distributed, the distribution of the sample mean is normally
distributed
Shape is approximately normal because the sample is larger than 30
Center is = 59.1833
Spread ()=
b) z=

3.1108976

58.559.1833
.549934

32

= 0.5499

= 1.2425

1-0.1075 = 0.8925

Project Part 5: Confidence Intervals


1. Confidence interval: is an interval of numbers based on a point estimate that gives a
range of likely values for an unknown parameter.
The purpose of a confidence interval is how confident you are that the method works.
We are (enter level of confidence) confident that the population proportion is between
(lower bound) and (upper bound).
2. In order to compute a confidence interval for a population proportion we need:

Data comes from Simple random sample or randomized experiment

An approximately normal sampling distribution of : (1 ) 10

Independent trials: 0.05 (sample is smaller than 5% of the population)

In order to compute a confidence interval for a population mean we need:

Data comes from Simple random sample or randomized experiment

Sample size is small relative to the population size 0.05

The data come from a population that is normally distributed OR the sample size
is large 30

(1)

3. /2

TI-83 Stats>tests>1PropZInterval..

(.187,.222)

Inpt: stats
x: 726
n=3551
C-Level: .99
4. With 99% confidence the true proportion of yellow candies is between .187 and .221

5. My bag of candies had a true proportion of .127 which is below the true proportion of
the class
6. 2

TI-83
Stat>tests>TInterval
= 59.183
Sx= 3.11
n= 60
C-Level= .95
(58.38, 59.986)
7. With 95% confidence the true mean of number of candies per bag is between 58.38 and
59.986.
8. No, because my bag contained 63 skittles which did not fall in the mean of the class data

Reflection
This project has taught me how I can apply statistics to my personal life. Not always is it
easy for students to look at math and apply it to their everyday life. Being a student isnt easy,
and Im always questioning myself about why I have to study all these classes that dont even
pertain to my career. And I become frustrated because I dont see how I can apply the education
to my everyday life. But as the semester went on, it came to my attention statistics is used for
almost anything you can think of. From things like agriculture all the way to the nightly news. In
my opinion I think statistics is much more applicable to everyday life than math 1050 or any
other math class I have taken. For instance if I am taking a class in the future and I want to host a
survey with my classmates, I now have the knowledge to be able to perform the correct survey
sampling.
Statistics is a class that takes time and work to study for, but is actually very interesting at
the same time. I definitely learned patience will completing this assignment especially part five
dealing with confidence intervals. But I learned sometimes it is best to take a step back and
breath before coming back to work on the assignment. It was easier for me to complete the parts
of the project I understood, then going back over the parts I was having a hard time with.
I can say I have grown an appreciation for people who spend every day working on real
world situations which require statistics. It takes a lot of time and effort in order to solve each
and every problem. I most definitely dont have the patience to work on numbers all day, and rip
my hair out because my numbers arent turning out like they are supposed to. I am very thankful
for all those people who sit there and process all of our paychecks and taxes, because that is a job
I would not want to get myself into.

Potrebbero piacerti anche