project 9 - Fa09

project 9 - Fa09 - 6. Assumption 4 is checked by plotting...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
2 November 2009 BUAD 310 Minitab Project 9 1. Assumption 2 should be questioned most because the data is taken sequentially. 2. To check assumption 1, you need to plot x vs. y to see if there is a linear relationship. The relationship is not linear and the plots fan out therefore assumption one is not likely to be valid. APPL 40 30 20 10 0 -10 -20 -30 250 200 150 100 50 0 -50 -100 3. Since the Pvalue > 10% you do not reject the null hypothesis therefore lag-1 is not significant in the population. 4. The Durbin-Watson statistic = 1.63383 which is between the range of (1,3) so assumption 2 holds. 5. To check assumption 3 the residuals are plotted against the fit. The assumption does not hold in this example because the graph is fanning and not uniform indicating the variances are unequal. FITS1 RESI1 80 70 60 50 40 30 20 10 0 150 100 50 0 -50 -100 Scatterplot of RESI 1 vs FI TS1
Background image of page 1

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

View Full DocumentRight Arrow Icon
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: 6. Assumption 4 is checked by plotting the residuals in a histogram. The histogram is unimodal so the assumption holds. RESI1 Frequency 140 20-100 7 6 5 4 3 2 1 Histogram of RESI 1 7. It is clear that the first three assumptions do not hold up to testing so the answers in project 8 would be invalidated. 8. The leverage points are equal to Hi > 2p/n. With 2 parameters the leverage point is 4/18 or .2222. There is one leverage point in the 13 th year when the S&P experienced a 23% decline. There are no outliers 9. The leverage points represent the year that has an extremely good or bad performance in S&P500 returns. 10. When the leverage point is removed from the data the new regression analysis shows a change in the regression line. S&P APPL 40 30 20 10-10-20 250 200 150 100 50-50-100 Scatterplot of APPL vs S&P...
View Full Document

This note was uploaded on 02/23/2010 for the course BUAD 310 at USC.

Page1 / 2

project 9 - Fa09 - 6. Assumption 4 is checked by plotting...

This preview shows document pages 1 - 2. Sign up to view the full document.

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