Adefowope Odueyungbo, Lehana Thabane and Maureen Markle-Reid discuss ways to improve estimates from various linear regression models and derive findings when confidence intervals overlap
In randomised controlled trials, an overlap of confidence intervals is often cited as evidence of ‘no statistically significant difference’ between intervention groups. This paper illustrates the limitations of this strategy and compares different univariate linear regression models with baseline and follow-up response measures. The researchers also demonstrate that using ‘change in response’ or exit score as a function of the baseline response in clinical studies leads to the same results. Further, using a model that includes baseline response as covariate leads to more precise estimates. The implications for future trials are discussed.
Nurse Researcher. 16, 4, 73-83. doi: 10.7748/nr2009.07.16.4.73.c7163
or
Alternatively, you can purchase access to this article for the next seven days. Buy now
Are you a student? Our student subscription has content especially for you.
Find out more