LOGIN

International Epidemiology Databases to Evaluate AIDS

Home >> Publications >> Assessing and interpreting the association between continuous covariates and outcomes in observational studies of HIV using splines

Publication

Author(s):

Shepherd BE1, Rebeiro PF; Caribbean, Central, South America network for HIV epidemiology (CCASAnet).

Pub Title:

Assessing and interpreting the association between continuous covariates and outcomes in observational studies of HIV using splines

Pub Date:

Oct 27 2016

Journal:

Title: 
J Acquir Immune Defic Syndr.

PubMed: 27798430
Pub PDF:

The HIV epidemiology literature is replete with studies that categorize continuous predictors, such as age and CD4+ cell count. It is well known that such an approach is sub-optimal, but it persists in part because results are easy to interpret after categorization. Splines may be used to incorporate continuous predictors with smoothed curves into regression models without categorization or linearity assumptions. Properly presenting and interpreting results from analyses with splines is critical for their widespread use. With data from 13,706 antiretroviral initiators in Latin America, we demonstrate how to interpret results from a Cox regression model using restricted cubic splines.

The following websites provide guidelines and policies when citing from PubMed®: http://www.ncbi.nlm.nih.gov/books/NBK7243/
http://www.nlm.nih.gov/bsd/policy/cit_format.html

Citation:

J Acquir Immune Defic Syndr. 2016 Oct 27. [Epub ahead of print] Assessing and interpreting the association between continuous covariates and outcomes in observational studies of HIV using splines. Shepherd BE1, Rebeiro PF; Caribbean, Central, South America network for HIV epidemiology (CCASAnet).