Your data analysis solution
Name is required.
Email address is required.
Invalid email address
Answer is required.
Exceeding max length of 5KB

Tipe I and Tipe III Sum - Regression

By Ruymán | Feb 20, 2018 01:52PM CET

Hi, I would like to know if the tables of Regression lineal ''Type I and Type III Sum'' gives information for the significance of the introduced variables. In the tutorial, it talks about the Type III, but doesn't talk of Type I. With my data, I have significance values in Type I and no with Type III and vice versa, so I would like to use the significance information if it takes to me good results.

Thank you and regards!




By Efthalia | Feb 20, 2018 10:55PM CET | XLSTAT Agent

Hello Ruyman,

Yes, both tables provide information on the significance of the variables but they test different things.

Type I, also called sequential sum of squares, tests whether a variable has a significant effect after all previous variables in the table are already taken into account in the model. Type I sum of squares depends on the order of the variables selection.

The Type III analysis tells whether a variable has a significant effect when all the other variables (and not just the previous ones) are already included in the model.

If you have interactions in our model, I suggest you looking at Type III.


Post Your Public Answer

Contact Us

Email Sales

Contact our technical support team:
seconds ago
a minute ago
minutes ago
an hour ago
hours ago
a day ago
days ago
Invalid characters found