OBJECTIVES: The EQ-5D-5L has the same five domains as in the EQ-5D but with 5 response options reflecting no, mild, moderate, severe, and extreme problems in each domain. The primary objective of this study was to develop a value set of the EQ-5D-5L in Canada. METHODS: The combination of traditional and lead-time time trade-off (TTO) was one of the main valuation techniques. A total of 80 health states plus the 5 very mild states (with only one dimension at level 2) randomly grouped into 10 blocks were evaluated using the TTO. State “55555”was included in every block. Each participant was asked to complete one block of 10 states through a face-to-face interview. Quota sampling was used to select a representative sample from the Canadian general population in terms of gender, age, and education. Interviews were conducted in Vancouver, Edmonton, Montreal and Hamilton between November 2012 and September 2013. Various functional forms and model estimators were used to estimate a TTO-based value set.  RESULTS: A total of 1209 participants completed the interview with the mean age of 47.6 years and 54.8% being female. Candidate models were compared using face validity (severer states have lower values), mean absolute error (MAE), mean squared error (MSE), and Akaike Information Criterion (AIC). The main effects were presented using either dummy variables or as linear terms. Additional terms were explored to account for interactions between domains. Among the candidate models, a random effects model with main effects presented as linear terms, terms for level 3 or higher in usual activities, pain/discomfort (PD), and anxiety/depression (AD), a term for whether dimension was at level 4 or level 5, and the interaction term between PD and AD performed better than the other models.   CONCLUSIONS: This model can be used to estimate a Canadian TTO-based EQ-5D-5L value set.