Notation of the β coefficients

Welcome to the forum for MLwiN users. Feel free to post your question about MLwiN software here. The Centre for Multilevel Modelling take no responsibility for the accuracy of these posts, we are unable to monitor them closely. Do go ahead and post your question and thank you in advance if you find the time to post any answers!

Remember to check out our extensive software FAQs which may answer your question: http://www.bristol.ac.uk/cmm/software/s ... port-faqs/
Post Reply
RasulGro
Posts: 3
Joined: Tue Apr 19, 2016 12:28 pm

Notation of the β coefficients

Post by RasulGro »

Dear MLwiNners,

I have a small question regarding the prefered notation concerning the notation of the estimated β coefficients reported in MLwiN when including the estimates in the result section of an article.
When reporting the specific coefficients in the text, should one use the notation β (as MlWin calculates estimates for the population) or b (as these estimates are based on the sample values)? (e.g. something like β=1.23, p<.05)
What is the most common notation? Does anyone have examples in papers or manuals?
And does this differ from reporting single-level regression results?

Kind regards,
Rasul
ChrisCharlton
Posts: 1351
Joined: Mon Oct 19, 2009 10:34 am

Re: Notation of the β coefficients

Post by ChrisCharlton »

Professor Kelvyn Jones has provided the following response:
The fixed effects, the βs, represent the ‘population’ means and these are similar to the parameters of a single-level regression model. The estimates may be portrayed by a non-Greek B or by placing a hat over the parameter, β̂. There would appear to be no general accepted convention but differences occur by discipline and journal. The best approach is to choose a journal and have a look at previously published papers – the Multilevel Gallery (http://www.bristol.ac.uk/cmm/research/gallery/) may be of help here.
Post Reply