Part 1: Short answer questions.
a. The vast majority of hotel guests do not take the time to rate their hotel experience on Tripadvisor.com. What sort of bias do you think this might induce in Tripadvisor's hotel ratings?
A sort of selection bias might induce in Tripadvisor's hotel rating, beause people who have extreme good or bad experiences are more likely to rate the hotel than people who had uneventful stays. If there are more people have good experience to stay, then Tripadvior's rating will be high; if there are more people have bad experience to stay, the rating will be low. Under either of these two situations, we will miss the rating of the uneventful stays.
b. A study finds companies that engage in management practices that are conventionally viewed as risky, such as mandating the use of interdisciplinary teams, tend to perform better than companies that don't. The study concludes that risky practices improve firm performance in that industry. Describe how survivor bias could have been responsible for the findings.
Risky management practices will cause either very positive result or very negative result. If the practices cause negative result, the company is more likely to go out of business. And there is survivor bias when the company is still in business, which instead of going out of business. Because it makes the company with risky practices looks better than they actually should be.
c. A news article writes:
"Air traffic control errors like the one that almost caused two airliners to collide near Chicago this week remain extremely rare and staffing levels are adequate, a federal aviation official said Friday... Evidence points to most of such errors occurring when a controller is handling lower numbers of flights, indicating there is no reason to expect an increased likelihood of errors during a hectic air travel period such as Thanksgiving week. She also cited a 2003 FAA study that found 78 percent of errors happen when air traffic is light or average, with only 22 percent occurring when a controller is handling a higher workload of 11 to 15 flights."
To what extent do the findings mentioned from the 2003 study shed light on the risks associated with overworked air traffic controllers? Explain briefly.
Part II
For this question, use the data file "Pset1_2_USNewsRanking.xls" found on QuestromToolsin the Problem Sets folder. It contains data about US News' 2004 rankings of MBA programs and various variables about each program in the "MBA programs" tab, as well as information about the relationship between SAT and GMAT scores in the "GMAT SAT" tab.
a) Create a histogram of average GMAT scores across all the schools.
PRINT OUT THE HISTOGRAM AND ATTACH TO THIS PROBLEM SET.
The Histogram is attached at the last page.
b) Use pivot tables to find information about MBA programs' outcomes depending on their students' average SAT score. First create a new variable called "SAT category". Make "SAT category" = 1 if SAT is less than 1200, =2 if SAT is 1200 to 1300, and =3 if SAT is 1300 or above. (Hint-You can either sort the data or use IF statements to do this.)
Create a Pivot Table to find the following:
• Average fraction of a school's graduates who are employed at graduation
• Average fraction of a school's graduates who are employed at graduation, conditional on being in SAT Category 1
• Average fraction of a school's graduates who are employed at graduation, conditional on being in SAT Category 2
• Average fraction of a school's graduates who are employed at graduation, conditional on being in SAT Category 3
PRINT OUT THE PIVOT TABLE AND ATTACH TO THIS PROBLEM SET.
d) Create a scatter plot with GMAT Score on the horizontal axis and average salary on the vertical axis. Describe below any relationship you see in the scatter plot.
PRINT OUT THE SCATTER PLOT AND ATTACH TO THIS PROBLEM SET.
e) Create a correlation matrix including the following variables: Average GMAT score, Acceptance Rate, Average Salary, and Employment at graduation. What is the correlation coefficient between GMAT score and acceptance rate? In 1-2 sentences, describe what the correlation coefficient tells us.
PRINT OUT THE CORRELATION TABLE AND ATTACH TO THIS PROBLEM SET
f) A junior statistician examining the correlation table you just made concludes that there is a stronger association between GMAT score and employment than between acceptance rate and employment. He explains that the correlation GMAT score and employment is positive, and the correlation between acceptance rate and employment is negative. What do you think of the statistician's conclusion?
g) Are schools with higher GMAT scores also likely to have higher salaries? How do you know?
Attachment:- Assignment.rar