Related Experiment Video
Updated: Jun 17, 2026

Measuring Delay Discounting in Humans Using an Adjusting Amount Task
Published on: January 9, 2016
Minimally important difference in health gain valuation
Mirna Bobinac1, Ana Bobinac2, Ismar Velić2
1Department of Anesthesiology, Intensive Care and Pain Medicine, Clinical Hospital Centre Rijeka, Department of Anesthesiology, Resuscitation, Emergency and Intensive Care Medicine, Faculty of Medicine, University of Rijeka, Rijeka, Croatia.
Background:
Minimal important difference (MID) thresholds distinguish noticeable from meaningful health gains, yet reimbursement decisions often fund high-cost therapies with marginal benefit. Clarifying meaningful patient-reported improvement is important for interpreting evidence and allocating resources.
Research Design And Methods:
We reviewed how MID concepts are defined and used across outcomes research, clinical trials and health technology assessment (HTA), and estimated Croatia's first EuroQol Visual Analogue Scale (EQ-VAS) MID in a representative sample (n = 401), examining whether thresholds vary by baseline health and a €100/month co-payment. Respondents stated the smallest noticeable and meaningful EQ-VAS improvement for a free intervention and the same intervention requiring a co-payment for 1 year. Analyses combined descriptive statistics, rank-based tests, and multivariable regression.
Results:
Mean MID was 7.9 EQ-VAS points when treatment was free and increased to 8.7 with co-payment, with higher thresholds among those with poorer baseline health. The co-payment scenario is interpreted cautiously as reflecting a worthwhile-improvement threshold rather than a pure intrinsic MID.
Conclusions:
Elicited thresholds were context-sensitive; however, the co-payment scenario captures what respondents considered worth paying for, arguing against universal MID cutoffs. In HTA, MIDs should serve as patient-centered interpretive benchmarks complementing cost-effectiveness evidence and considerations such as equity and societal preferences.
Related Concept Videos
Bioequivalence Data: Statistical Interpretation
Testing a Claim about Standard Deviation
The hypothesis testing for the claim of population standard deviation (or variance) requires the data and samples to be random and unbiased. The population distribution also must be normal. There is no specific requirement on the sample size as the estimation is based on the chi-square distribution.
As a first step, the hypothesis (null and alternative) concerning the claim about...
Sensitivity, Specificity, and Predicted Value
Sensitivity is the...
Bioequivalence: Overview
Bioequivalence studies: Biowaivers
Bioavailability Study Design: Healthy Subjects Versus Patients