# excel data analytics engagement project

1. Export the SAS cars data to Excel (In your SASHELP library in SAS Studio, right click on CARS, select export, and export as an Excel or csv file). Select a folder within your SAS files area and export to that folder. Find the file you exported and download it to your computer.
2. Open the file within Excel. If you cannot export as an Excel file, ensure that you export as a csv – you will still be able to open the csv file from Excel.
3. On a separate workbook page, recreate the scatter plot that you made in SAS comparing engine size to highway mpg. You should have one graph with two sets of dots.
4. For each car type in the scatterplot, right click on any dot and select add trendline. Use linear option, display equation on chart and display R-squared value on chart.
5. Add any chart elements you feel will make the scatterplots easier to read and understand. I strongly recommend that each plot has a title, axis labels, and a legend at the minimum.
6. Using Data > Data Analytics in Excel, do a linear regression for each type of car. Put this output on the same page as your scatter plot. NOTE: If your regression coefficients do not match the trendline equation for each car type, double check your work!
7. Use Excel to calculate the correlation coefficient using the =CORREL command for each car type. Additionally, calculate the coefficient of determination for each car type as well. Put these values near your regression output. Do these values match what you found in your regression output?
8. If the engine size was 8L, what do you predict the MPG would be for each type of car? Show your work in the file.
9. Explain what your results mean in a textbox near your plots. Pay attention to the regression equation, regression output, correlation, and the R-squared value. Do the equations do a good job explaining MPG? Why or why not? What changes might you make to improve the model? Show me that you understand regression analysis. Do not be too brief!
10. Save the Excel file, name it, and upload it here. NOTE: You must use Excel 2016 to upload your file as the only file type accepted is *.xlsx.Excel Data Analytics Project Rubric
Excel Data Analytics Project Rubric
Criteria Ratings Pts
This criterion is linked to a Learning Outcome
Raw Data & Filters

 10.0 pts Excellent Raw data shown on separate page. Clear how data was filtered to do graphs and regressions. 9.0 pts Average Raw data included but not clear how it was filtered to do graphs and regressions. 0.0 pts Poor File only shows filtered data without no indication of how it was obtained or project plagiarized.
10.0 pts
This criterion is linked to a Learning Outcome
Graphs

 35.0 to >28.0 pts Excellent Graph had title, axis labels, legend, and two sets of filtered data included each with a trendline, regression equation, and R2. Only minor errors, if any, present. 28.0 to >21.0 pts Above Avg Graphs set up properly for two sets of data but missing at least one element or has one substantial error. 21.0 to >14.0 pts Average Graphs missing several required elements and/or have 1-2 significant errors. 14.0 to >7.0 pts Below Avg Graph has numerous missing elements or multiple significant errors. 7.0 to >0 pts Poor Graph missing most required elements or serious errors made, not done, or plagiarized.
35.0 pts
This criterion is linked to a Learning Outcome
Regressions

 20.0 pts Excellent Summary output for both types of cars done. No errors and results clear. 15.0 pts Above Avg Two sets of regressions done but with some minor errors. 10.0 pts Average Only one regression done or one significant error made. 5.0 pts Below Avg One regression done with several major errors present. 0.0 pts Poor Regressions not done or project plagiarized.
20.0 pts
This criterion is linked to a Learning Outcome
Calculations

 15.0 pts Excellent Forecast, correlation coefficient, and coefficient of determination all done and correct. 12.0 pts Above Avg All calculations done but with minor errors. 9.0 pts Average One calculation missing or substantive error present. 5.0 pts Below Avg Two calculations missing or other major errors present. 0.0 pts Poor Calculations not done, answers provided without formulas shown, or project plagiarized.
15.0 pts
This criterion is linked to a Learning Outcome
Explanations

 20.0 pts Excellent Substantive answers for all four questions asked. 15.0 pts Above Avg All questions answered but one lacking substance. 10.0 pts Average Answers missing for one question or answers not sufficiently substantive for two questions. 5.0 pts Below Avg Multiple questions unanswered or answers not substantive. 0.0 pts Poor No explanation provided or answers plagiarized.
20.0 pts
Total Points:
100.0