Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 1 down vote favorite

Effects of growth hormone (GH) replacement with recombinant human GH on bone and mineral metabolism were studied in 36 GH-deficient children. Several outcomes, including serum ionized calcium levels, were assessed at pretherapy (zero months) and 1, 3, 6, 9 and 12 months after the beginning of therapy. Simple linear regression was used to determine if changes in ionized calcium levels could be predicted from length of therapy. Each patient’s ionized calcium level was employed in the analysis.

Is the use of simple linear regression appropriate?

a. Yes

b. No

c. The investigators should have used logistic regression instead

share|improve this question
2  
Why do you think that the researchers should have used logistic regression? The response variable is clearly continous (although maybe with some censoring). Please elaborate, if we are to help you in providing a good answer to this question. – abaumann Oct 29 '12 at 19:45
Hi.. that's all what is given :S..so u think the answer is a. Yes? – Francois Oct 29 '12 at 19:49
I would say b because simple linear regression assumes independence of the residuals, which probably isn't the case with repeated measurements on individuals. – Max Oct 29 '12 at 20:08
Hi Max..can you please explain why you choose b and nt a?.. thanks – Francois Oct 29 '12 at 20:23
1  
@Francois I think Max is right. I will also go with (b). As these are repeated measurements of your variables, so you should adopt models for longitudinal data. You should take into account the possible correlation in these repeated measurements. The responses closer in time are likely to be highly correlated. There are many other practical issues involved with it, I would suggest that you follow this useful book for theories-amazon.com/Applied-Longitudinal-Analysis-Probability-Statistics/… – Blain Waan Oct 29 '12 at 20:23
show 1 more comment

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.