Methodology and the Computational Approach

Now that we understand the experiment and the raw data collected, let's take a look at the methodology, which is our approach to handling the computing and data analysis.  We will look at this at a high level, a general overview. Watch the next video as Ashu talks about the cycle of data analysis.  Using our case study, he will describe in general terms the tasks of: 1) filtering and reducing, 2) sorting and transposing, and 3) calculating the correlation.

Quiz

Question

Identify the correct order of items in the "Cycle" that we talk about in the video

Looks Good! Correct: Explanation: We identify what needs to be done, how can it be done with the software we are using, what kind of format does the data needs to be in, and finally apply the function of the software
Question

True or False - Assume you have to find mean and standard deviation of 7 numbers using Microsoft Excel. The "Cycle" as described in video will include the following in the following order:

Enter Cycle

--- Cycle 1

  1. Identify that we need to find the  mean
  2. Identify the function (formula) in Microsoft Excel that helps us find the mean
  3. Feed the data to Microsoft Excel in the format it requires so that we can apply the function (formula) identified in last step
  4. Apply the function (formula)

--- Cycle 2

  1. Identify that we need to find the  standard deviation
  2. Identify the function (formula) in Microsoft Excel that helps us find the standard deviation
  3. Feed the data to Microsoft Excel in the format it requires so that we can apply the function (formula) identified in last step
  4. Apply the function (formula)

Exit Cycle

Looks Good! Correct: Explanation: We identify what needs to be done, how can it be done with the software we are using, what kind of format does the data needs to be in, and finally apply the function of the software

Now lets simplify the problem to define a computational approach - we will be looking at a smaller subset of data to help us develop the R codes. Looking at just a portion of the data makes it easy to follow the steps as we develop the R codes.

** Note it will be beneficial to print the slides of the following video and follow them along. There are additional slides i.e. slides 4 through 8 which will be useful to understand and visualize the Program Flow. It is highly recommended that you refer to slides 4 through 8 when the speaker is explaining the Program Flow. You may also benefit from occasionally pausing the video while you are referring to the slides 4 through 8.