• Home
  • La Trobe University
  • Data-Based Critical Thinking
  • Understanding Correlation and Causation in Data Analysis

Understanding Correlation and Causation in Data Analysis

STA1DCT Assignment 4 Due Thursday the 4th of May 2017 at 3pm. You must submit your assignment electronically and as a single file via the LMS page for this subject. Where appropriate, your solutions must include your workings. In submitting your work, you are consenting that it may be copied and transmitted by the University for the detection of plagiarism. Please start with the following statement of originality, which must be included near the top of your submitted assignment: "This is my own work. I have not copied any of it from anyone else." IMPORTANT NOTE 1: The total possible marks for this assignment is 50. There are 40 marks associated with accuracy (i.e. correctness of your answers; the breakdown of these marks is indicated on this question sheet), a further five marks for completeness (you will only get the full five marks for completeness if you make a serious attempt to answer every question) and a further five marks for your written communication (e.g. clarity, spelling, grammar, correct use of notations etc.) STA1DCT: 40 + 5 + 5 = 50 marks. IMPORTANT NOTE 2: When you are asked to calculate an answer by hand, you may still use your calculator for basic calculations (e.g. multiplication, division, taking a square-root etc.) Your workings should show that you now how a formulae or process works. 1. Consider a study in which researchers collect data comparing the number of hospital emergency departments within a region in 2016 (let X denote this variable) with the total number of people who presented to (attended) the emergency department within that region during 2016 (let Y denote this variable). For example, in one region considered there were 27 emergency departments in 2016 and a total of 3,007 people who presented to these emergency departments. When comparing the data collected for many different regions of varying population sizes, it is noted that the two variables (X and Y) have a strong positive correlation. Upon reading this, a journalist in an opinion column who thinks that we spend too much on health care is quoted as saying "The data shows us that we need to reduce the number of emergency departments. Building more emergency departments only encourages more people to present to an emergency department which is clearly a waste of money." Clearly the journalist's claim is illogical since it fails to take into account other reasons for this correlation. Explain why it is not surprising that this correlation was observed and why then it is not an increase in the number of emergency departments that causes there to be more presentations. Note: there is one obvious explanation for this and you should be able to explain this clearly in just two of three sentences. If you do not identify the obvious explanation you can still receive marks based on your explanation of another reason if that reason appears plausible. Please make sure that your explanation is free of spelling and grammatical errors. One mark will be deducted