turn on suggestions

Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.

Showing results for

Find a Community

- Home
- /
- Analytics
- /
- Stat Procs
- /
- Multiple Regression Analysis

Topic Options

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

07-13-2016 02:07 PM

Hello I really need some help. Here are my assignment instructions.

Perform a Multiple Regression Analysis paralleling the HBAT analysis performed in the textbook and in class, but now use the HATCO dataset (see HATCO_X1-X14_Tabs data file).

Include the following analyses:

- Consider the overall general Model X9 = X1 X2 X3 X4 X5 X6 X7
- Perform a Correlation Analysis
- Fit and Analyze the best single independent (simple) regression analysis
- Perform a Stepwise Regression Analysis to select the best subset model using Alpha = 0.05
- Perform a Full Model (Confirmatory) Regression Analysis using Alpha = 0.05
- Using the best subset from the Stepwise Regression Analysis now include variable X8 (Firm Size) and analyze its effect and the new resultant model
- Analyze and Discuss the Multiple Regression Analysis Assumptions, e.g., Linearity, Normality, Homoscedasticity, and Independence using Residual and other Graphical/Statistical measures and tests for all Model Analyses
- Similarly Analyze and Discuss any Influential observations with recommendations, as well as the Model’s Multicollinearity.

Here is what I've done so far for my code:

FILENAME REFFILE "/home/tmaciver7840/my_content/HATCO X1-X14.txt" TERMSTR=CR;

PROC IMPORT DATAFILE=REFFILE

DBMS=tab

OUT=WORK.IMPORT;

GETNAMES=YES;

RUN;

PROC CONTENTS DATA=WORK.IMPORT; RUN;

Input ID X1 X2 X3 X4 X5 X6 X7 X8 X9 X10 X11 X12 X13 X14;

Data WORK.IMPORT;

Set WORK.IMPORT (Keep = ID X1 X2 X3 X4 X5 X6 X7 X9);

Label ID = 'ID - Identification Number'

X1 = 'X1'

X2 = 'X2'

X3 = 'X3'

X4 = 'X4'

X5 = 'X5'

X6 = 'X6'

X7 = 'X7'

X8 = 'X8'

X9 = 'X9'

X10 = 'X10'

X11 = 'X11'

X12 = 'X12'

X13 = 'X13'

X14 = 'X14';

Proc Print Data = WORK.IMPORT;

*;

*;

* Correlation Matrix - All Variables;

*;

Proc Corr Data = WORK.IMPORT;

Var X1 X2 X3 X4 X5 X6 X7 X9;

Plot NQQ.*R. NPP.*R.; * NQQ.*R and NPP.*R request specific separate

Normal Quantile and Normal Probability Plots;

*;

How do I perform the rest of the regression analyses? I really appreciate any help! (Attached is the dataset)

Accepted Solutions

Solution

07-14-2016
03:52 PM

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

07-13-2016 02:31 PM

Some of that code is correct and some of its not. I assume you're getting errors?

I would suggest running it piece by piece and including comments on what you expect each section to do.

Then to answer your question start taking a look at either proc REG or GLM.

All Replies

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

07-13-2016 02:22 PM

That's a big assignment! And a lot of questions!

I suggest that you start with your instructor, teaching assistant, and classmates. They can review topics that you covered in class or refer to relevant sections of the textbook, class notes, or lab instructions where these topics are described. Almost surely there is some example that you did in class or in a lab that is similar to the analyses that you are being asked to conduct here.

Solution

07-14-2016
03:52 PM

- Mark as New
- Bookmark
- Subscribe
- Subscribe to RSS Feed
- Highlight
- Email to a Friend
- Report Inappropriate Content

07-13-2016 02:31 PM

Some of that code is correct and some of its not. I assume you're getting errors?

I would suggest running it piece by piece and including comments on what you expect each section to do.

Then to answer your question start taking a look at either proc REG or GLM.