Central Limit Theorem

1) What is the average delay in departures from Oregon Airports?

Hint 1: You’ll want to take the average of “DepDelay”.

2) We have a pretty cool data set here, and can see all departures by major carriers in the given timeframe. What if instead we just measured a few flights? Measure 3 different “random” sets of data. For ease, pick 3 random flights and calculate the average of your 3 flights. What is the average departure delay of your 3 flights?

Hint 2: There are many different ways to randomly select rows in Excel. You may find the following method useful for this course:

Step 1: Create a new column in the first column (Column A). Name this column as Index

Step 2: In cell A2, type = rand() to randomly generate a decimal number between 0 and 1.

Step 3: For all the remaining cells in Column A, also fill in =rand().

Step 4: Sort the entire spreadsheet according to the values in Column A. Highlight Column A, click Data > Sort > Expand the selection. If you do not choose “Expand the selection”, you are only sorting Column A, not the entire spreadsheet. Make sure sort by Column A is selected on the next screen.

Step 5: The first 3 rows in this sorted spreadsheet would be a sample of 3 randomly selected flights.

3) Those probably weren’t that close to the true average (although you might have gotten lucky). What if you do the same thing, but average 30 flights? What is the average departure delay of these 30 flights?

4)Do you see evidence of the Central Limit Theorem at play? Was the average of a larger sample closer to the truth? Do you think all your classmates will find the same thing? Why or why not?