# Regression Assignment by CMmoo4ez

VIEWS: 0 PAGES: 1

• pg 1
```									                           Graded Regression Assignment
Due Tuesday October 9, 2012

Do “better” movies earn more money at the box office? USA Today (Wloszczyna and DeBarros
February 25, 2004) investigated this by determining a rating score for movies released in 2003
based on a compilation of movie reviews published in 20 major newspapers and magazines for
over 300 movies. The dataset movies1.sas7bdat contains these scores (scores) and how much
money the movie made at the box office (boxoffice), in millions of dollars. A high composite
score indicates that most critics loved the movie, and a low score indicates that most critics
panned the movie.

1. Create a scatterplot using score to predict boxoffice. Characterize the relationship.
2. Determine if score is useful in predicting bo office. Give the parameter estimates (these
are the estimates of the intercept and the slope). Interpret the slope.
3. Show the scatterplot with the regression fit on the line.
4. Give the 95% confidence interval for the slope. Interpret the confidence interval.
5. Predict the box office that has 40 for the score. Predict the box office for a movie that
has 70 on the score.
6. Give the 95% confidence interval for the mean boxoffice when the score is 78.
7. Give the 95% prediction interval for the boxoffice when score is 78.
8. Assess the fit of the model with the coefficient of variation and interpret its meaning.
9. Assess the fit of the model with a residual plot.
10. Make a graph with the 95% confidence bounds for the mean boxoffice for specific scores
and the 95% prediction limits for boxoffice.

The researchers also looked at the data set after removing the six movies that earned more than
\$200 million. The data, without the six movies, is called movies2.sas.

11. Create a scatterplot using score2 to predict box office2. Characterize the relationship.
12. Determine if score2 is useful in predicting box office2. Give the parameter estimates.
13. Show the scatterplot with the regression fit on the line.
14. Assess the fit of the model two ways and report your findings.
15. Make a graph with the 95% confidence bounds for the mean boxoffice for specific scores
and the 95% prediction limits for boxoffice.

Which model fits better?

```
To top