Fig. 5From: Exploring the importance of controlling heteroskedasticity and heterogeneity in health valuation: a case study on Dutch EQ-5D-5LScatter plot of 3125 EQ-5D-5L profiles for conditional logit and heteroskedastic model. *values were estimated in a pits scale where v (55555) = 0 and v (11111) = 1. 95% Confidence interval for Pearson’s correlation 0.9950–0.9956, and for Lin’s concordance: 0.9922–0.9932Back to article page