EconHM17 - Q uestion #1 T his question is related to slide...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon
Question #1 This question is related to slide 42 (page 75) of your course packet. It will help you identify some of the linear regression assumption violations. Based on the excel file provided here , answer the following questions. 1. To get a feel of the data, create 4 different charts (scatter plots) for the four data sets you were given in the excel file. Put the X variable on the x-axis (independent variable), and the Y variable on the y- axis (dependent variable). Given the above four graphs, match them with the graphs (data sets) you have created. 1. Data set 1 in the file corresponds to the above graph B
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2. Data set 2 in the file corresponds to the above graph C 3. Data set 3 in the file corresponds to the above graph D 4. Data set 4 in the file corresponds to the above graph A 2. Now that you have successfully matched graphs and data files, look at the graphs and try identifying potential problems. 1. In data set 1 the potential problem could be everything seems ok 2. In data set 2 the potential problem could be non-linearity of data 3. In data set 3 the potential problem could be an outlier 4. In data set 4 the potential problem could be an outlier Now run four different regressions for the four data sets you are given. Before you jump into running regressions, do the following: in the regression window, you should see Residuals and there should be four boxes. Make sure you check all four of them before you click ok. You should notice that you will be given addition output besides the usual regression output. This will be very useful when analyzing potential regression assumption violations. Since the assumption were made on the error term, it is only natural that we analyze the error term when trying to identify assumption violations.
Background image of page 2
3. When you look at the four data sets, you notice that they are different. When you look at the four regression equations, you can say that they are almost the same . The natural question is: "How can that be?" The answer is that we have some assumption violations in our data sets. Look at the residual plots that were given to you when you ran regressions. Based on those plots, answer the following questions? 4. Which residual plot(s) indicate presence of an outlier? plots 3 and 4 5. If we removed the outlier from data set 4, what would you say about the relationship between the remaining X and Y values? c) the slope of the regression line would be undefined Question #2 It has been computed that the 95% confidence interval is [144.4, 154.2] for the average exam score when a student spent 10 hours on average per week studying for the class. The 99% prediction interval for a student who spent 10 hours on average per week studying for the class will be wider narrower
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
of the same width cannot be determined based on the provided information.
Background image of page 4
Image of page 5
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/11/2010 for the course ECON 203 taught by Professor Petry during the Spring '09 term at University of Illinois, Urbana Champaign.

Page1 / 14

EconHM17 - Q uestion #1 T his question is related to slide...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online