TY - JOUR
T1 - Task complexity and response certainty in discrete choice experiments
T2 - An application to drug treatments for juvenile idiopathic arthritis
AU - Regier, Dean A.
AU - Watson, Verity
AU - Burnett, Heather
AU - Ungar, Wendy J.
N1 - The authors would like to thank the editor and two anonymous referees for their valuable comments which led to the improvement of this manuscript. The results and views expressed in this manuscript remain the authors own. Funding for this study was provided by a program grant from the Ontario Ministry of Health and Long-Term Care Drug Innovation Fund.The Canadian Centre for Applied Research in Cancer Control receives core funding from the Canadian Cancer Society.
Journal has changed it's name to The Journal of Behavioral and Experimental Economics (formerly the Journal of Socio-Economics)
PY - 2014/6
Y1 - 2014/6
N2 - Responding to a stated preference discrete choice experiment (DCE) is a complex task for respondents to undertake. Task complexity can induce response error, thereby decreasing the statistical precision of the econometric model. This study explores the link between task complexity and statistical precision as moderated by the level of thoughtful deliberation respondents exert when completing choice tasks. To do this, we make novel use of subjects’ certainty of response to DCE tasks as a measure of their deliberation. The distinction between intuitive and deliberate thought (System 1 and System 2, respectively) motivates how task complexity will differentially affect System 1 and System 2 respondents. The principle of utility balance in experimental design theory is used to understand how greater deliberation will increase task complexity, but will also improve statistical precision if respondents are engaging in System 2 processing. Our analyses find that increases in choice task utility balance decreases response certainty, and re-weighting the regression to favor respondents who are more uncertain of their choices increases the statistical precision of the econometric model.
AB - Responding to a stated preference discrete choice experiment (DCE) is a complex task for respondents to undertake. Task complexity can induce response error, thereby decreasing the statistical precision of the econometric model. This study explores the link between task complexity and statistical precision as moderated by the level of thoughtful deliberation respondents exert when completing choice tasks. To do this, we make novel use of subjects’ certainty of response to DCE tasks as a measure of their deliberation. The distinction between intuitive and deliberate thought (System 1 and System 2, respectively) motivates how task complexity will differentially affect System 1 and System 2 respondents. The principle of utility balance in experimental design theory is used to understand how greater deliberation will increase task complexity, but will also improve statistical precision if respondents are engaging in System 2 processing. Our analyses find that increases in choice task utility balance decreases response certainty, and re-weighting the regression to favor respondents who are more uncertain of their choices increases the statistical precision of the econometric model.
KW - discrete choice experiment
KW - stated response certainty
KW - random heterogeneity
KW - sampling uncertainty
KW - dual-process thinking
U2 - 10.1016/j.socec.2014.02.009
DO - 10.1016/j.socec.2014.02.009
M3 - Article
VL - 50
SP - 40
EP - 49
JO - Journal of Socio-Economics
JF - Journal of Socio-Economics
SN - 1053-5357
ER -