ImmersionGroup1

Back to Activity1

Begin by examining the data set. Recognize how the data is recorded and how you may be able to use the given data to explore potential relationships between categories.
=__Scatterplot Questions__= ==1. Create a scatterplot using average MPG and another category that you feel may influence fuel efficiency. Answer the following questions.== Answer: We picked MPG and weight with the assumption that the more a vehicle weighs, the less MPG you will get.
 * === Identify the category you chose and why you thought there might be a relationship BEFORE creating the scatterplot? ===

Answer: The weight is our x-axis because that is your independent variable (what you control) and the MPG are our y values because we determined that the MPG depends on how much the car weighs.
 * === Create the scatterplot. Which category is your x-axis and which is your y-axis? Why did you create your scatterplot in that order? ===

Answer: Yes there is a relationship because there is a correlation in our data on our graph.
 * === Do you believe there is a relationship between the two categories? Why or why not? ===

Answer: Our correlation was negative proving that as the weight of the vehicle increased, the MPG decreased.
 * === If there appears to be a relationship, does it have a positive or negative slope? What does this mean about the relationship between the two categories? ===

=__Regression Questions__=

(What is Regression?)
==Create the linear regession equation in Excel, which Excel calls the trend line. Click the boxes to create both the equation and the r 2 value on the graph. Answer the following questions.== Answer: y = -0.007x + 49.32...in words this means that for every pound of weight, the MPG decrease 0.007. The 49.32 is the y-intercept which is the MPG if your car doesn't weigh anything...which doesn't make sense (not realistic).
 * === What is your regression equation? Explain what the equation means in words. ===

Answer: 0.704 It is a pretty good correlation and close to 1, but there are outliers from the trend line.
 * === What is your r 2 value? Is this a strong correlation? Why or Why not? If you are not sure, try searching the internet for supporting documents. Provide URL's for where you find your information ===

Answer: No, we still feel that the more a car weighs, the less MPG you will get.
 * === Based on all the information you have, has your belief about the relationship of the two categories changes? Why or why not? ===

=__**Analysis**__= ==Right click on the regression equation and select "Format Trendline". Explore the different variations of regression equations.== Answer: Checking all of the r2 values with the different types of equations
 * === How would you determine which equation had the best relationship? ===

Answer: No, the Power Regression trend line was the best because it's r2 value was closer to 1.
 * === Was the "Linear" option the optimal option? If so, why? If not, what was the better equation and why? ===

>

=//**Attach your Scatter Plots and Regression Information. Make sure your X and Y axis are correctly labeled. You may use Screen Shots to do so.**//= = =