Question about p-value in the linear regression
Hi friends,
I am learning python machine learning course and this question comes from the lesson:' How to interpret the Regression Table.
This is the question: 'What is the predicted GPA of students with an SAT score of 1850? (Unlike in the lectures, this time assume that any coefficient with a p-value greater than 0.05 is not significantly different from 0)?
in the lesson, GPA= 0,0017*SAT+0.275
I don't really understand what to do with p-value 0.05. Please give me a support of explaination. Thank you.
:)
1 answers ( 0 marked as helpful)
Hi Tran,
Now the p-value of the intercept doesn't always matter. It is not essential as it is causal relationship of the Xs we are interested in.
Often the case really is: we don't really care about the intercept b0.
The reason is that if you are looking for the relationship between the independent variables and the dependent variable, the value of the intercept (b0) doesn't matter.
Alternatively, if you are looking to make predictions using the regression model, the intercept (also called 'bias') is used to correct the predictions by a certain constant (b0). In that case, you'd want to know b0 (but will also want it to be significant).
In this exercise we are suggesting that the intercept may not matter in some situations.
Best,
The 365 Team