A Second Project, Part 1: Getting Started.

• For this project we will perform a data analysis of a set of student grades in an introductory level college class.
  • This data has had all personal identifying information removed.
    • Names and IDs have been removed
    • Order has been randomized.
    • This is definitely an ethical issue.
• The data contains
  • A homework average (as a percent) for each student.
  • A project average (as a percent) for each student.
  • A Test average (as a percent) for each student.
  • A final percent for each student.
  • A letter grade for each student.
• A question:
  • Students often claim that test scores are the reason for failure in a class. Is this true? Is the test score the most important indicator of student performance in a class?
  • Note, this really depends on the weights of various components of the class.
• Download this workbook.
• A prelim nary step
  • The data custodian or person responsible for the data has already randomized this data.
  • But let's see how this could have been accomplished.
  • We will do this by
    1. Inserting a new column
    2. Placing a random value in this column for each
    3. Sorting based on the new column.
    4. Removing the new column.
  • Add a column to the right of column A
    • Right click in the column A heading
    • Select Insert
    • 
  • Insert random values into this column
    • There are a number of random functions
    • =rand generates a random number between 0 and 1
    • =randbetween(low, high) generates an integer between low and high.
    • In this case, use rand()
    • Put =rand() in cell A2
    • Copy this down
    • 
    • 
    • Note, your values will be different than mine, why?
  • Make a more permanent copy of the values
    • Every time you change something on the worksheet, the values change
    • This can be distracting.
    • So make a copy of the column, BUT
      • Only copy the values, not the equations.
    • To do this
      • Insert a new blank column between A and B
      • Copy column A
      • Paste in column B, but with select the Values paste option.
      • 
      • Delete column A.
    • By the way, I used this to copy computed values as well.
      • The homework average was a computation, the individual homework scores are not in this worksheet.
      • The same is true for the other averages.
  • Sort the data on the new column A.
    • Your results will be different than mine.
    • 
  • Delete column A.
• We just picked up two techniques
  • Copying data values only
  • Randomizing data.
• Before we start working, let's
  • Make a copy of the raw data
  • We will preserve the "original" data
  • We will work on the copy.
• Start by naming the current worksheet "Raw Data"
• Make a copy of the raw data
  • Right click on the Raw Data worksheet tab.
  • Select Move or Copy
  • 
  • This brings up a dialog box
    • You can move or copy to other open or new workbooks
    • You can place it in the workbook where you want it
    • Make sure in this case you select Create a copy
    • 
  • Rename the new sheet to be Sorted Data
• Finally, go to the Sorted Data sheet and sort the data by final grade descending.
• 
• Save the worksheet someplace you can recover it for the next set of notes.