Select Page

You would need Statcrunch through MyStatLab or can log in to mine
lab_4_probabilities.doc

lab_3_association__1_.doc

Don't use plagiarized sources. Get Your Custom Essay on
Statistics- I need help completing a few lab assignments on Probability, Regression, and Association
Just from \$10/Page

Unformatted Attachment Preview

Lab 4 – Probabilities
be able to answer the questions for you, but it can help, especially if you sort the data. To sort data, click
on Data/Sort, then choose all columns, then under Sort criteria select the column you want to sort on. Do
NOT try to sort on two different columns at the same time because the rest of the data will no longer match
up. Instead, look at the two columns in the data table to answer the question.
1. What proportion of students in this class are shorter than 66 inches?
What proportion are taller than 66 inches?
How did you find the
What proportion are exactly 66
inches tall?
2. What is the z-score for someone in this class who is 66 inches tall?
How did you find the
3. According to the z-table, in what percentile is a person who is 66 inches tall?
Why do you think they do/don’t match?
Thinking back to Labs 1 and 2 where you looked at a histogram of our class heights, would you say
that our class is normally distributed?
5. What proportion of students in this class have a GPA above 3.5?
6. What is the probability that a randomly selected student in this class has a GPA above 3.5?
7. What is the probability that a randomly selected student in this class is computer savvy? (i.e. Rated
themselves as 7 or higher)
8. What is the probability that a randomly selected student in this class has a GPA above 3.5 and is
computer savvy?
How did you find this answer?
Note: You cannot simply multiply
9. Is the probability that a student in this class has a GPA above 3.5 and is computer savvy (your
answer to question #8) equal to the probability that a student in this class has a GPA above 3.5
(your answer to question #6) times the probability that a student in this class is computer savvy?
Why or why not?
10. What is the probability that a randomly selected student in this class does not smoke?
11. What is the probability that a randomly selected student in this class has brown eyes?
12. What is the probability that a randomly selected student in this class does not smoke or has brown
eyes?
13. Is the probability that a student in this class does not smoke or has brown eyes equal to the
probability that a student does not smoke plus the probability that a student has brown eyes minus
the probability that a student does not smoke and has brown eyes?
14. What is the probability that a randomly selected student in this class is female?
15. What is the probability that a randomly selected student in this class is a female basketball fan?
16. What is the probability that a randomly selected student in this class is a basketball fan given that
she is female?
17. Given that a student is female, what is the probability that she has blue eyes?
18. Given that a student has blue eyes, what is the probability that she is female?
19. What is the probability that a randomly selected student in this class is shorter than you?
20. What is the probability that a randomly selected student in this class is shorter than you given that
she is female?
Bonus Question: What is the probability that a randomly selected sample of 3 students from this class
are all shorter than you?
Lab 3 – Association
Part I – Categorical Variables
Have Statcrunch give you a Contingency Table for Eye Color and Favorite Sport from our class data by
clicking on Stats/Tables/Contingency/With Data. After you’ve selected the variables, you will see a
number of checkboxes on Statcrunch– choose the first four checkboxes – Row percent, Column percent,
Percent of total, and Expected count – so that they appear in your report. Finally, click on “Calculate” and
use the table Statcrunch produces to answer the following questions:
Between eye color and favorite sport:
1. What percent of blue-eyed students like basketball?
Note: You are not being asked what
percent of all students like basketball, so you will use either row percent or column percent in
answering the question, depending on the order in which you chose the variables. Which
percent did you use?
2. How many students like basketball?
How many brown-eyed students like basketball?
How many brown-eyed students are expected to like basketball?
How many
Are the expected counts for basketball the same for all
eye colors?
Are the expected counts for eye color the same for all sports?
3. What percent of brown-eyed students like baseball?
What percent of baseball fans have
brown eyes?
What percent of the entire class likes baseball?
What percent of the
entire class has brown eyes?
4. Does there appear to be an association between eye color and favorite sport? Give a reason for
Keep your contingency table open and have Statcrunch create a side-by-side bar graph for you.
After clicking on Graphs/Bar Plot/With Data, select either favorite sport or eye color from the
list, and then Group By the other variable. (Note: Since there are fewer eye colors than sports,
grouping by favorite sport will produce fewer charts.) At the bottom of the window under “For
Multiple Graphs” you can tell Statcrunch how many rows or columns per page you want. There
should be 5 different eye colors, so type in 5 to get them all on one page. Finally, click on Create
Graph, and then compare the bar graphs to the numbers in your contingency table.
Recall from the lesson video that we really can’t determine if there is an association between two
categorical variables unless there are at least 5 observations in each cell of the contingency table.
Do we meet this condition for eye color and favorite sport?
Can you tell from the bar graph if there is an association between the variables?
Why or
why not?
Because there are not enough students in our class to be able to draw any valid conclusions about the
association between any two categorical variables, we will now look at an example that will enable us to do
so:
An unusually severe increase in gasoline prices may have motivated full-sized pickup truck
buyers to purchase a highly fuel-efficient vehicle. Purchase behavior was collected in one area
for one year and reported below.
Low Fuel Prices
High Fuel Prices
Number of Highly
Fuel Efficient Trucks
Purchased
392
442
Number of Ordinary
Cars and Regular
Trucks Purchased
36,929
42,255
Total
Total
a. Complete the row and column totals in the table above. What is the independent
variable? Explain why.
b. Create a relative frequency table below by typing in the proportion of vehicles in each
category using the column numbers from the table above.
Low Fuel Prices
High Fuel Prices
Proportion of
Highly Fuel Efficient
Trucks Purchased
Proportion of
Ordinary Cars and
Regular Trucks
Purchased
c. Is there an association between fuel prices and the number of highly fuel-efficient trucks
purchased?
Give a reason for your answer based on the results in the table.
Now have Statcrunch give you a Contingency Table for Gender and Exercise using the same process
you used above for Eye Color and Favorite Sport. Complete the numbers table below based on the
data provided in the Contingency Table:
Males
Number who
exercise regularly
or everyday
Number who
exercise rarely or
never
Females
Total
Total
Now convert the numbers table into a percentage table as you did for the fuel price vs type of vehicle
example:
Males
Females
Proportion who
exercise regularly
or everyday
Proportion who
exercise rarely or
never
Is there an association between gender and exercise? Be sure to give a reason for your answer based
on the percentages in the table above.
Part II – Quantitative Variables
Now have Statcrunch run a regression analysis on the following pairs of quantitative variables. Click on
Stat/Regression/Simple Linear. Since we are only looking at correlation in this section, it doesn’t really
matter for now which variable is the explanatory (X) and which is the response (Y). Click on Calculate,
then use the results to complete the following chart:
Here’s a helpful hint to save you time when completing this chart: Find the correlation coefficient for the
whole class and put it in the chart, then click on the Options button in the top left corner of the Regression
Results window and choose EDIT. You will be taken back one step to a screen where you can now Group
By Gender. You can now get the correlation coefficient for each gender to complete that line in the chart.
Between the Variables:
Coefficient of Correlation
Whole class
by Gender
M
F
Height and Shoe Size
GPA and Fastest You’ve Ever Driven
GPA and Computer Savvy
Using your answers in the chart above, does there appear to be a correlation between:
Height and Shoe Size? Give a reason based on the correlation coefficient.
GPA and Fastest You’ve Ever Driven? Give a reason.
GPA and Computer Savvy? Give a reason.
Part III – Correlation and You
Now let’s see how you correlate with the rest of the class:
1. Redo the regression for height and shoe size making height the explanatory variable (x) and shoe size
the response variable (y).
Copy the regression equation which Statcrunch gives you here:
2. What is the slope of this regression line?
(Hint: Recall from high school Algebra that, given an
equation in the form y=mx+b, the slope is the number in front of x. The slope is important because it tells
us how the response variable changes for each unit change in the explanatory variable.)
3. Now plug your own height into the regression equation and calculate (by hand) the shoe size this
regression line predicts for you. (Show your work!):
4. Now take your actual shoe size and subtract the predicted value which you just calculated:
This last number represents your RESIDUAL for shoe size using the regression equation.
5. Now find your residual for Fastest You’ve Ever Driven based on GPA. Show your work by completing
the following steps:
1. Get the regression equation from Statcrunch. Make GPA the explanatory variable (x) and Fastest
Driven the response variable (y):
2. Calculate your predicted driving speed by plugging your GPA into the above equation. (Again,