This website uses Cookies. Click Accept to agree to our website's cookie use as described in our Privacy Policy. Click Preferences to customize your cookie settings.
Accept
Reject
Preferences
cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Submit your abstract to the call for content for Discovery Summit Americas by April 23. Selected abstracts will be presented at Discovery Summit, Oct. 21- 24.
Discovery is online this week, April 16 and 18. Join us for these exciting interactive sessions.
Choose Language Hide Translation Bar
Soniayoung
Soniayoung
Level I

How to do Weighted Least Squares for simple regression

Apr 4, 2020 06:27 AM (1835 views)

Hi, I'm new to JMP and I need some advice on how to run a WLS for a simple regression.

Other discussions say that I use Analyze > Fit Y by X > select another numerical column with the appropriate weights and click "Weight".

But what exactly do I put in the weight tab? Do I put the saved residuals or the x variable itself?

 

Sorry if this question is very elementary -- I'm having hard time navigating this software and my statistics class. Thank you! 

0 Kudos
1 REPLY 1
Mark_Bailey
Staff Mark_Bailey
Staff

Re: How to do Weighted Least Squares for simple regression

Apr 4, 2020 06:35 AM (1832 views)  |  Posted in reply to message from Soniayoung 04-04-2020

I suggest that you spend time with Help > Tutorials and the Help > JMP Documentation Library > Discovering JMP guide.

 

JMP uses the paradigm of 'analysis roles.' For example, the Y role is the dependent variable and X is the independent variable. The Weight role is used when a variable in your data table contains weights. So for every observation (row), you have a value for the dependent variable, the independent variable, and the weight.

 

There are many weighting schemes. For example, if the assumption of constant variance by linear regression is violated, then the reciprocal variance is a useful weight. Observations that exhibit greater variation are weighted less than observations with less variation.

0 Kudos