BUS  MGT 2320 Autumn 2017 Technology Assignment

BUS  MGT 2320 Autumn 2017 Technology Assignment

 

 

BUS  MGT 2320 Autumn 2017 Technology Assignment

 

Instructions:1. This assignment is individual work (NO collaboration).  You may not consult with any persons other than the BUSMGT 2320 instructors and TAs.  2. For each requirement you will see a prompt for the result needed, such as [Insert the scatter plot here.]   Replace the prompt with the required information or
graphic.3. Formatting and presentation account for 10% of your grade. Follow these formatting guidelines, as well as good sense:a. Sign the honor pledge.  Failure to do so will result in a score of 0.b. Include the page numbers as initiated.c. In order to reduce the number of pages required, re-size graphs where appropriate (be sure to lock the aspect ratio).  Make them as small as possible and have
the details still be readable. No graph should take up all or even most of the space on a page.d. Print your document.  Assemble all pages in correct order.e. Staple all pages together in the upper left-hand corner.4. Have your assignment ready to submit on Thursday, 9/14, at the start of your scheduled lecture.  You may not submit your assignment any other way (e-mail, for
example) without prior permission from your instructor.  If permission is not granted, the assignment will receive a grade of 0.
As a member of the Ohio State University, I will not participate in or tolerate academic dishonesty.  By signing below, I attest that I have completed this assignment
without collaboration with or assistance from any other persons.  I understand that any violation of this statement by handing in any portion of another individual’s
or group’s work as my own will result in a suspected case of academic misconduct.
Signature: ______________________________ Date: _______________

Learning Objectives:1. Introduce and promote familiarity with the statistical computing program StatCrunch.2. Introduce (or review, in some cases) use of statistical functions in Excel and the Add-In, Data Analysis.3. Review data summarization.4. Review calculation with the Normal probability distribution.5. Review lines of best fit.
Accessing StatCrunch:• Enter MyStatLab via Carmen and go to the MyStatLab course home.• Carefully read the menu items on the left-hand side of your screen to find StatCrunch.  Launch StatCrunch. You should see the following image on your screen. • Click on StatCrunch website.• Select “Open StatCrunch” or an appropriate menu item under “My Data” • You should now see a spreadsheet in your window.  This is called a StatCrunch Data Table. • Each column has a generic label called “var#.”  When you paste your data into the spreadsheet, your variable names will be copied over these “var#” labels. • Above the spreadsheet is a set of blue buttons identifying menus of functions/operations/procedures.  By clicking on any of them you will get a drop down menu
from which you can refine your request.• For example, under the StatCrunch button you see an option for a New Data Table.  By clicking on it, you launch a fresh spreadsheet.• In the lower right-hand corner of the screen you will see a notification that help is available. • Let’s see how the help works.  Click on the Learn about StatCrunch sessions! Prompt.• In the Search prompt, type box plot.  Select the second option: Creating boxplots with a group by column. Watch the video (2 minutes and 40 seconds).• You can search for any procedure you need to use and in most cases find a brief video explaining what all of the prompts in the dialogue box require.  In a few
cases you will only find printed instructions with screenshots.  We cannot create any better instructions than are already available.  Use them.• To Copy and Paste graphs, click on the blue Options button in the upper left-hand corner of the graph window.  Select Copy from the menu.  Follow the “Tip”
instructions that appear in the yellow box below the graph window.You should be well-versed in using Excel, including how to manage Add-Ins.  The Data Analysis Add-In will appear on the right-hand side of the Ribbon at the top of the
Excel workbook when you click on Data.  If it is not enabled, do so.
Part 1 – One-variable Data SummarizationIn this part, you will be generating summary information about repair costs for different types of machines used by a furniture manufacturer.  The data for this
investigation is in the worksheet titled “RepairCosts” in the Excel File, Technology Assignment Data, that is posted on Carmen > Modules > Cases > Technology
Assignment.  Copy the data and column labels and paste into a StatCrunch Data Table by clicking on var1 and then Paste. Var1 and var2 should now be replaced with
Repair Cost ($) and Machine Type.  The data should be in the rows 1 – 60 below.Part 1 Requirements using StatCrunch :1. Obtain a single object that displays a histogram of repair cost for each of the 3 machine types.  a. Group by Machine Typeb. Graph the Relative Frequenciesc. Put values above the bar. d. Overlay a Normal distribution (select Display options > Normal). e. Mark the Mean and Median (check both Markers).f. Use the “multiple graphs” optioni. Use the same X axis and Y axisii. Change the “Columns per page” from 1 to 3[Paste one image of your 3 histograms here.]2. Obtain one graph that shows the box plots of repair costs by machine type (Group by) including the following features:a. Fences. b. Vertical alignment.c. Mark the Mean and Median.d. Percent dividersi. Once you have the graph, adjust the percent dividers to show the percent of the machines with repair cost of no more than $375.[Paste your graph of the box plots of Repair Costs by Machine Type here.]3. Identify the outlier in RepairCost for the Lathes and the outlier in RepairCost for the Stamps.The outlier in Repair Costs for the Lathes has the value [Type your answer here] and occurs in row [Type your answer here].The outlier in Repair Costs for the Stamps has the value [Type your answer here] and occurs in row [Type your answer here].4. Remove each of the outliers.  While the row is highlighted in pink, go to the blue Edit button.  Select Rows > Delete.  Repeat requirement 1 using the data
after the outliers are removed. [Paste one image of your 3 histograms here.]Part 2 – More One-variable Data Summarization
In this part, you will be investigating the time required to complete different tasks in a team building obstacle course.  The tasks are identified as A, B, and C.
Random samples of 200 recent times required to complete each task have been collected. The data can be found in the Excel worksheet titled “TaskTimes” in the Excel
file, Technology Assignment Data, that is posted on Carmen > Modules > Cases > Technology Assignment.  The samples are labeled TimeA, TimeB, and TimeC, and the times
are all in minutes.
Part 2 Requirements:1. Use StatCrunch to obtain a basic histogram with a Normal overlay (no other bells and whistles required) for each sample. Obtain a Q-Q Normal plot for each
sample.  Don’t forget the “Learn about StatCrunch session” help if you need it.[Paste one image of the 3 histograms here.]  [Paste one image of the 3 QQ Plots here.]2. Characterize the shape of the distribution of each sample of times as either symmetric, skewed to the right, or skewed to the left.  Describe the appearance of
the Q-Q Normal plot in each case.
Choose the one best answer for Distribution Shape and for Q-Q Plot Appearance for each of TimeA, TimeB, and TimeC.  Delete all but the answer you choose, or
alternatively, underline the answer you choose (one selection per column = 6 selections).
Times A Times B Times CDistribution Shape Q-Q Plot Appearance Distribution Shape Q-Q Plot Appearance Distribution Shape Q-Q Plot Appearancea. symmetric a. linear a. symmetric a. linear a. symmetric a. linearb. skewed right b. mound or hump b. skewed right b. mound or hump b. skewed right b. mound or humpc. skewed left c. bowl or “U” c. skewed left c. bowl or “U” c. skewed left c. bowl or “U” d. “S” d. “S” d. “S”
3. Obtain the 5-number summary statistics, the average, the standard deviation and the sample size for each set of times.  Do not include any other statistics.
Use StatCrunch > Stat > Summary Stats > Columns or use Excel > Data > Data Analysis > Descriptive Statistics.  Once you have the results format any numbers that are
not integer values to have 2 decimal places.
[Paste your results here.]  4. The time required to complete the task for each of the three processes can be modeled well by one, and only one, of three theoretical distributions described
on page 6.  The examples given there were not generated from the assignment data.  Each of your data sets will display a shape consistent with one of these theoretical
distributions, but will not have the same parameters as shown in the example.  Identify which distribution best models each of the three tasks, and use the sample
statistics obtained in Requirement 3 to provide estimates of the parameter(s). You are estimating the parameters, so use appropriate rounding for the approximate
values.  For example, if my sample average is 33.57, I might give the approximate value of the population mean as 34.
The Uniform distribution best models [Type your selection of Times (A, B, or C) here.] and has a min of approximately [Type the value here.] and a max of approximately
[Type the value here.].
The Normal distribution best models [Type your selection of Times (A, B, or C) here.] and has a mean of approximately [Type the value here.] and a standard deviation
of approximately [Type the value here.].
The Exponential distribution best models [Type your selection of Times (A, B, or C) here.] and has a mean of approximately [Type the value here.].
5. Using the models defined in requirement 4, determine the amount of time that should be allowed in order that 95% of the time the task can be completed in that
amount of time or less.  That is, determine the 95th percentile for time in each of the 3 tasks as calculated from the “model.”  In StatCrunch, select the blue Stat
button > Calculators > select your distribution.
[Paste your image of the “distribution name” Calculator for TimeA here.]
[Paste your image of the “distribution name” Calculator for TimeB next to the image for TimeA.]
[Paste your image of the “distribution name” Calculator for TimeC here.]
Clarifying comment:  The image is the complete result, graph and probability calculation below the graph.
6. Use the NORM.DIST and NORM.INV functions in Excel to find the 95th percentile for the time required to complete the task that you modeled with the Normal
distribution and to find the probability that the task modeled with the Normal distribution will be completed in less than 12 minutes. If you need help, see the videos
for the Normal distribution on Carmen.
95th Percentile: [Copy the Excel formula and paste it here.] [Copy the result and paste it here.]P(Time < 12) [Copy the Excel formula and paste it here.] [Copy the result and paste it here.]
7. Use StatCrunch to determine a 95% confidence interval estimate of the population mean time to complete each of the 3 tasks based on the sample data.  Stat >
choose Z Stats or T Stats as applies > One Sample > With Data.  You can select all 3 times at once.
[Paste your results here.]
8. In a sentence or two explain why all three confidence intervals are probably reliable in spite of the fact that the times for all three tasks are not Normal.
[Type 1 – 2 sentences here.]Example Distributions for Modeling Data:

Part 3 – Check out Some of the Resources Available in MyStatLab and Review of Scatter Plots, Correlation, and Lines of Best Fit (Regression)
Theme parks are big business. In the United States alone, there are nearly 500 theme and amusement parks that generate over $10 billion a year in revenue.  Although
theme parks have started to diversify to include water parks and zoos, rides are still the main attraction at most parks, and at the center of the rides is the roller
coaster.  Engineers and designers compete to make them bigger and faster.  In this part you will use some data collected from some of the fastest roller coasters in
the world today to review how we can use Statistics to describe relationships.  The top Speed (Y) of the roller coaster is measured in mph and the Length (X) of the
track for the roller coaster is measured in feet.
Part 3 Requirements:1. Go to your Course Home in MyStatLab and select “Tools for Success” in the menu. One of “tools” is StatCrunch. Make a list below of the other tools at your
disposal:
2. Click on StatCrunch.  Select Chapter 18 and then Coasters CE18. You should now see a StatCrunch data table containing the roller coaster data.  What is the
name of the first roller coaster in the data list and its associated them park?
Roller Coaster: Theme Park:
3. Obtain a scatter plot of Speed (Y) against Length (X).  Overlay the line of best fit (polynomial of order 1) on the scatter plot. You can use Excel if you
choose, but in StatCrunch select Graph > Scatter Plot.
[Paste your scatter plot here.]
4. Identify the equation of best fit by hovering your cursor over the line you had overlaid on your graph.
[Type the equation here.]
5. Obtain the correlation between Length and Speed. Again, you may use Excel if you choose, but in StatCrunch select Stat > Summary Stats > Correlation.
[Paste the correlation results here.]
6. Does the type of roller coaster offer additional insight?  Obtain a scatter plot of Speed (Y) against Length (X) grouped by Type, with a line of best fit
(polynomial of order 1) for each type overlaid on the graph.
[Paste your scatter plot for here. If you cannot print the graph in color, use highlighters or colored markers/pens to link the line with the legend.  That is, Steel
is blue in the legend, make the line for Steel blue.]
7. Identify the equation of best fit for each type of roller coaster.
[Type the equation for Steel roller coasters here.][Type the equation for Wooden roller coasters here.]
8. Obtain the correlation between Length and Speed for each type of roller coaster.
[Paste the correlation results here.]
9. What additional insight about speed is gained when we differentiate the Type of roller coaster?
[Type 1 – 2 sentences here.]