398353_en-US

liliconcom

Bivariate analysis

Hello,

 

I would like confirmation on the bivariate analysis performed by JMP.

When only the X and Y parameters are entered, is the statistical analysis performed subsequently parametric? If so, is it possible to do a non-parametric type analysis? How to proceed?

 

Thanks in advance

 

Married

AnalyticsRe: Bivariate analysis

Fit Y by X can perform four different types of analyses, depending on the modeling types of X and Y. Here are the different types of analyses based on the modeling types that are offered. This comes straight from the Fit Y by X dialog box:

Depending on the type of analysis, if the result is a parametric analysis, then the red triangle options will typically have a nonparametric option.

If you are more specific on what you are looking for, then the community may be able to provide more guidance.

 

Re: Bivariate analysis

Hello Dan,

 

Thank you for your reply. In fact, I expressed myself badly. I know the analysis and the possibilities of the fit Y by X in finction of the type of data. I want to do a bivariate analysis on continuous data but which does not follow a normal law.
When I launch the fit Y by X module I fill in the Y and X fields and I get my analysis. My pproblem is that I can't see if JMP considers my data as parametric or non-parametric. When I click on the red triangle of the bivariate analysis I cannot select the type of my data and I therefore do not know what the statistics obtained are based on.
How to be sure that the analysis is done well considering that the data does not follow a normal law?

I am using JMP16.0.0

 

Thanks for your help

Re: Bivariate analysis

Fit Y by X, more specifically Bivariate, is performing standard least squares regression. Regression does not assume that your data be normally distributed. But it does assume that the residuals (or errors) be normally distributed. This distinction is important because the raw data will have signals in it that could prevent it from being normally distributed. The X or explanatory variable should remove the effect of the signals. What is left (the errors or residuals) need to be normally distributed in order for all of the statistical inferences of the regression to be valid. That is why a regression analysis should always include an examination of the residuals as well. Bivariate will allow you to perform the residual analysis.

 

If the residuals are not normally distributed, there are a few options. One is to transform your response so that the residuals can be normally distributed. The Bivariate report offers several options to transform your response. They can be found under Fit Special from the red pop up menu.

 

Another option is to use Fit Model and specify a Generalized Linear Model. That will allow you to specify the distribution response. A generalized linear model is more than I can get into here, but might be worth you looking into for whatever your problem is.

Re: Bivariate analysis

Thanks Dan,

 

All of this is very helpfull and will allow me to do the job I need to do!

I found and tested all your solutions and both of them give me my answer. I have a preference for the Fit Y by X then residuals analysis after fitting linear regression model!