Choice Modeling - Diagnostic - Experimental Design - Parameter Standard Errors of Design extension

Calculates the parameter fits and their standard errors for a Choice Modeling - Experimental Designchoice model experimental design output.

Technical Details

Random responses are created for 300 respondents for the experimental design and the resulting data is fit with a multinomial logit model. The D-error is also calculated.

Example

Random design

Complete enumeration design

The values are generally compared between designs created by different algorithms for the same specification, rather than assessed on an individual basis.

For the examples above, the Random design has higher standard errors and d-error compared to the Complete enumeration design.

The parameter estimates from the logit model can general be ignored and are non-zero because of randomness.

References

Hoare, J. (2018, July 20). How Good is your Choice Model Experimental Design? [Blog post]. Accessed from https://www.displayr.com/how-good-is-your-choice-model-experimental-design/.

See also Choice Modeling - Experimental Design.

For details of the D-error calculation see

1. Yap, J. (2018, August 20). What is D-Error? [Blog post]. Accessed from https://www.displayr.com/what-is-d-error/.
2. Yap, J. (2018, August 21). How to Compute D-error for a Choice Experiment [Blog post]. Accessed from https://www.displayr.com/how-to-compute-d-error-for-a-choice-experiment/.
3. Huber, J., & Zwerina, K. (1996). The importance of utility balance in efficient choice designs. Journal of Marketing research, 307-317. Accessed from https://faculty.fuqua.duke.edu/~jch8/bio/Papers/Huber%20Zwerina%201996%20Marketing%20Research.pdf.

Code

includeWeb("QScript R Output Functions");

const menu_location = "Choice Modeling > Diagnostic > " +
      "Experimental Design > Parameter Standard Errors of Design";
errorIfExtensionsUnavailableInQVersion(menu_location);
createDiagnosticROutputFromSelection(menu_location);