TY - JOUR
AU - Sullivan, Patrick W.
AB - EDITORIAL Are Utilities Bounded at 1.0? Implications for Statistical Analysis and Scale Development Patrick W. Sullivan, PhD careful consideration of the fundamental charac- corresponded to a value of 0.1, each year after the Ateristics of preference-based QALY weights (here- patient entered the health state of death 0.1 QALYs after referred to as utilities for simplicity) can help us would accrue in perpetuity). Similarly, assigning better understand how we should approach their sta- 1.0 to full health ensures that each year survived tistical estimation. In an article in this issue, Pulle- in full health has a QALY value of 1.0. Much like nayegum and others argue: ‘‘Although negative temperature, however, these convenient characteris- utilities are allowed because there are health states tics of QALYs do not imply that the death and full 2(p175) worse than death, utilities cannot exceed 1 because health anchors cannot be exceeded. youcannotdobetterthanfullhealth.’’ Basedonthis Although the anchor of death (0.0) is measurable argument, the authors suggest that censored regression and concrete, the description of ‘‘full health’’ is models (such as Tobit and CLAD) are biased and that much more nebulous and will vary across descrip- specific statistical analyses and/or manipulations tive systems. There is no ambiguity 
TI - Are Utilities Bounded at 1.0? Implications for Statistical Analysis and Scale Development
JF - Medical Decision Making
DO - 10.1177/0272989X11400755
DA - 2011-11-01
UR - https://www.deepdyve.com/lp/sage/are-utilities-bounded-at-1-0-implications-for-statistical-analysis-and-fk07eawDNw
SP - 787
EP - 789
VL - 31
IS - 6
DP - DeepDyve
ER -