converting standard error (regression coefficient) to standard deviation.

[imiyakawa]

Hi guys,

I have a regression output where I'm given the standard error of both the intercept and the gradient (X co-efficient).

I'm required to transform this into the standard deviation, and I've searched all over the internet but find absolutely nothing!

Any help is much appreciated.

[Dragan]

Hi guys,

I have a regression output where I'm given the standard error of both the intercept and the gradient (X co-efficient).

I'm required to transform this into the standard deviation, and I've searched all over the internet but find absolutely nothing!

Any help is much appreciated.

Who is requiring you to do this?

[imiyakawa]

My assignment due today.

This isn't a big secret or anything. My lecturer told me that it was something like
a = b/(N-some small number)^0.5

Where a and b is STDEV and STDError (forgot which way was which).

He even thought it was a mistake on the question sheet, and they may actually want just STDError.

[Dragan]

My assignment due today.

This isn't a big secret or anything. My lecturer told me that it was something like
a = b/(N-some small number)^0.5

Where a and b is STDEV and STDError (forgot which way was which).

He even thought it was a mistake on the question sheet, and they may actually want just STDError.

Well, of course it is a mistake.

Let me explain. The standard error is nothing but the standard deviation of the sampling distribution of an estimator (e.g. a slope coefficent or intercept).

Your instructor's intuition was right --- the question is simply asking for the standard error.

Don't waste anymore time Googling.

[imiyakawa]

Well, of course it is a mistake.

Let me explain. The standard error is nothing but the standard deviation of the sampling distribution of an estimator (e.g. a slope coefficent or intercept).

Your instructor's intuition was right --- the question is simply asking for the standard error.

Don't waste anymore time Googling.

Wow thanks so much.

Just to make 100% sure. STDEV(Beta) is absolute nonsense -- it HAS to be STDERROR(Beta).

Thanks!

What to make of this wiki entry:

i'm guessing the standard error of the mean has nothign to do with the standard error of a regression estimate (slope or intercept).

[Dragan]

Wow thanks so much.

Just to make 100% sure. STDEV(Beta) is absolute nonsense -- it HAS to be STDERROR(Beta).

Thanks!

What to make of this wiki entry:

i'm guessing the standard error of the mean has nothign to do with the standard error of a regression estimate (slope or intercept).

Right, the standard error of a sample mean has nothing to do with the standard errors of a regression line's estimates (slope or intercept)...they are completely different computations.