Academic Integrity: tutoring, explanations, and feedback — we don’t complete graded work or submit on a student’s behalf.

please show all the work. 19. Consider the following EXCEL residual analysis out

ID: 3313181 • Letter: P

Question

please show all the work.

19. Consider the following EXCEL residual analysis output. Observation 2 4 6 Standard Residuals 0.047721046 0.220440988 3.275870148 Residuals 0.708648472 3.273506837 18.94642956 14.43972152 1.680952477 26.05083942 14.40739508 30.86739819 10.00072574 6.832802462 6.171396375 11.86712473 22.68023363 16.67850869 12.43439955 0.233862597 15.93088427 9.29422972 12.36605323 1.828199338 Predicted Score (y) 57.29135153 50.72649316 73.94642956 59.56027848 87.68095248 71.94916058 81.59260492 39.13260181 50.00072574 73.83280246 47.17139637 52.86712473 69.68023363 61.67850869 0.972384247 0.1131969 1.754287701 0.970207354 1.978639238 0.673458151 -0.460127258 0.415587559 0.799143191 1.527307979 1.123146252 0.837344004 2.015748524 1.07280053 0.625882054 0.8327415 0.12311264 9 79.56560045 49.7661374 82.06911573 51.29422972 76.36605323 71.82819934 20 a. Comment on the presence of any outliers aua b. Comment on the dispersion of the standard residuals, using the "+2 rule c. Does this support any doubt regarding the underlying assumption of the normal distribution of the error terms? the aun d. What does this indicate regarding the appropriateness of the associated simple linear regression model?

Explanation / Answer

b) A general rule of thumb for figuring out what the standardized residual means, is:

If your residuals are +/-3, then it means that something extremely unusual is happening. If you get +/-4, it’s something from the Twilight Zone! This makes sense if you think about the 68 95 99.7 rule: if your data is normally distributed, 95% of your data should be within 2 standard deviations from the mean. If you have something greater than that, then you’re looking at an outlier.

So, Majority of standardized reiduals lie between - 2 and +2

So, a large dispersion is not there.

d) Model is appropriate as the dispersion is very less and asuumption is satisfied. Points will fall in straight line in normal probability plot.