Skip to main content
. Author manuscript; available in PMC: 2018 Aug 1.
Published in final edited form as: Prev Med. 2017 Jun 1;101:91–95. doi: 10.1016/j.ypmed.2017.05.031

Table 2.

Odds Ratios Associated with Survey Period in Continuous and Discrete Time Models

Model 1 – Unadjusted Model 2 – Adjusted % Explained
Continuous Time 1.0259 1.0074 71.6
Discrete Time
 1988–1994 1.00 1.00 –
 1999–2002 1.13 0.95 140.1
 2003–2006 1.34 1.03 91.6
 2007–2010 1.63 1.19 70.3
 2011–2014 1.76 1.18 76.3

Odds ratios from Model 1 include no control for adiposity measures; those from Model 2 control for waist circumference and BMI 10 years prior to survey. For the continuous time models, observations are assigned to the midpoint of the survey wave. For the categorical models, survey periods are modeled using a series of indicator variables.