Page 1 of 1
Choose confidence interval in linear regression
Posted: Thu Sep 06, 2012 9:44 am
by jnkfoune
Hello,
I wanted to know if it is possible to choose the confidence interval (guessing that it is by default 95%) as it is possible on excel!
I would like to get a 90% confidence
Thank you for your help!
Re: Choose confidence interval in linear regression
Posted: Thu Sep 06, 2012 10:30 am
by EViews Gareth
When you look at the confidence interval for an equation, the first thing it asks you is what confidence levels you wish to see.
Re: Choose confidence interval in linear regression
Posted: Thu Sep 06, 2012 6:53 pm
by jnkfoune
But the thing that mess me up is that building a linear regression on excel you can choose a confidence interval in the parameters and it actually give different outputs when confidence is either 95% or 90%. I wanted to know if there is a way to do the same on Eviews.
Even if, according to me, all the coefficients, standard errors, t-statistics, p-values, etc., everything should be exactly the same. The only difference should be the interpretation. If I am using a 95% confidence interval, then I reject if the p-value is less than 0.05. If you are using a 90% confidence interval, then I reject if the p-value is less than 0.10. But that's it - the p-value should be exactly the same, regardless of the confidence level - the only difference is how I interpret the p-value.
Do you have any explication on this?
Re: Choose confidence interval in linear regression
Posted: Thu Sep 06, 2012 6:58 pm
by jnkfoune
Sorry, my mistake. Outputs are exactly the same, I did a mistake in my calculations.
Im ok now