This PR addresses the following issues: #7, #9, #10.
For #7, I modified code in cbc_design() to avoid duplicate choice sets for the same respondents in random designs.
For #9 and #10, I modified code in cbc_design() to allow Bayesian D-efficient designs with restricted profile sets. I also added some input checks to make sure that the program would stop or throw warnings appropriately if the input settings made it impossible to create a design.
This PR addresses the following issues: #7, #9, #10.
For #7, I modified code in
cbc_design()
to avoid duplicate choice sets for the same respondents in random designs.For #9 and #10, I modified code in
cbc_design()
to allow Bayesian D-efficient designs with restricted profile sets. I also added some input checks to make sure that the program would stop or throw warnings appropriately if the input settings made it impossible to create a design.