Regression Analysis (Linear) of Exam Score/Study Time
Regression Analysis (Linear) of Exam Score/Study Time
*Create a report (suggested length of 3 written pages or 800 words) by doing the following:
A. Summarize the real-world business situation you identified in task 1.
B. Report the data you collected, relevant to the business situation, by doing the following:
1. Describe the relevant data you collected. (Time studied by candidate and exam score achieved)
2. Create an appropriate graphical display (e.g., bar chart, scatter plot, line chart, or histogram) of the data you collected.
Note: This display should be a summary or representation of your data, not raw data.
C. Report how you analyzed the data using an analysis technique from the given list by doing the following:
1. Describe an appropriate analysis technique that you used to analyze the data. (Regression Analysis, Linear)
2. Include the output and any calculations of the analysis you performed.
Note: The output should include the output from the software you used to perform the analysis.
3. Justify why you chose this analysis technique.
D. Summarize the implications of your data analysis by doing the following:
1. Discuss the results of your data analysis.
2. Discuss the limitation(s) of your data analysis.
3. Recommend a course of action based on your results.
Note: Your recommendation should focus on the results of your analytic technique output from part C2.
Data Driven Decision Making Template
| Student name: | |
| ID number: | #000328804 |
| Date: | April 10th, 2020 |
| PROMPT | RESPONSE |
| B.Describe a real-world business situation that could be addressed by collecting and analyzing a set of data. |
The real-world business situation that could be addressed by collecting and analyzing a set of data is that of: The California Water Environment Association is interested in discovering if the hours studied in preparation for their exams directly correlates to candidate exam scores candidates achieve. This information will allow them the opportunity to better offer study time recommendations to their candidates and allow them to trend study time/pass score data. |
| B1.Summarize one question or decision relevant to the real-world business situation you will answer by collecting and analyzing a set of data. |
The question I will answer by collecting and analyzing a set of data is do candidate study times directly correlate to candidate exam scores. Meaning if a candidate studies more, does that go to say they will have a higher score and ultimately pass an exam. |
| B2.Explain why the situation or question would benefit from a data analysis. |
The situation would benefit from data analysis because the overall preparation for its exams is important to both CWEA and Customers. The overwhelming majority of other credentialing systems look at this data very often. It has been noted that customers have complained about feeling they studied enough but ultimately didn’t pass the exam. CWEA’s exam system is vulnerable because it very rarely looks at this. Identifying the amount of time studied in order to pass an exam would greatly benefit CWEA and its customers. |
| B3.Identify data you will need to collect that is relevant to the situation or question. Note: A sample size of 30 or more is suggested to provide a statistically reliable finding. |
The data I will need to collect is the total number of tests per day for each day in the month, and the scores for the tests taken, whether they are pass or fail. I will also look at the time studied. This data is logged by CWEA in two ways. First, all test scores are listed on a master data sheet that is auto-generated by CWEA’s computer exam system. Secondly, at the beginning of each exam, candidates are asked a series of survey questions, one of those questions is how did you prepare for the exam and how long total did you study. This will clearly identify the scores and the amount of time studied. Additionally, as a Executive Committee Chairman, I have full access to view this information. |
| B4.Describe the data gathering methodology you will use to collect data. |
Statistical Methods, Exam Score Reports, and Surveys will be used to compile the number of exams taken for each day of the month. This data is collected routinely as part of the day-to-day operations of the agency. This administrative data is readily available and is collected over time, thus providing a sufficient amount of data for a reliable analysis. Additionally, a closer look at the data will need to be done to identify any pattern that shows a correlation between score and study time. |
| B5.Identify the appropriate data analysis technique you will use to analyze this data (e.g., linear programming, crossover analysis, t-test, regression). |
The appropriate data analysis technique I plan to use is Regression Analysis. More precisely, Linear Regression. I will be using method because it will allow me to use the time studied, or the independent variable, as a tool to predict the exam score, or the dependent variable. I feel this is appropriate because I can use the data obtained for time studied as a predictor and see if I can make a prediction about exam score. This method is most appropriate for my situation. |
| B5a.Explain why the data analysis technique you chose is an appropriate technique to analyze the data collected. |
Because I am looking at the data on the exams as hours studied and an actual exam numeric score, this method is more appropriate than say Logistic Regression. In Logistic Regression it would be appropriate if it was pass or fail data. Because I am using the predictor data, independent variable, study time and comparing to a possible prediction, dependent variable, of exam score, Linear Regression is most appropriate. |
| C.Sources Used (if applicable) |
N/A |
Leave a Reply
Want to join the discussion?Feel free to contribute!