A recent article in this journal addressed the choice between specialized heuristics and mixed-integer programming (MIP) solvers for automated test assembly. This reaction is to comment on the mischaracterization of the general nature of MIP solvers in this article, highlight the quite inefficient modeling of the test-assembly problems used in its empirical examples, and counter these examples by presenting the MIP solutions for a set of 35 real-world multiple-form assembly problems.
ArielA.VeldkampB. P.van der LindenW. J. (2004). Constructing rotating item pools for constrained adaptive testing. Journal of Educational Measurement, 41, 345-359.
2.
ArmstrongR. D.JonesD. H.WuI. L. (1992). An automated test development of parallel tests from a seed test. Psychometrika, 57, 271-288.
3.
BixbyR. E. (2012). A brief history of linear and mixed-integer programming. Documenta Mathematica, Extra Volume ISMP, 107-121.
4.
ChenD. S.BatsonR. H.DangY. (2010). Applied integer programming. New York, NY: John Wiley.
5.
ChenP. H. (2016). Three-element item selection procedures for multiple forms assembly: An item matching approach. Applied Psychological Measurement, 40, 114-127.
6.
ChoiS.MoelleringK.LiJ.van der LindenW. J. (2016). Optimal reassembly of shadow tests in computerized adaptive testing. Applied Psychological Measurement. Advance online publication. doi:10.1177/0146621616654597
NemhauserG. L.WolseyL. A. (1999). Integer and combinatorial optimization. New York, NY: John Wiley.
12.
van der LindenW. J. (2005). Linear models for optimal test design. New York, NY: Springer.
13.
van der LindenW. J.Boekkooi-TimmingaE. (1988). A zero-one programming approach to Guiliksen’s matched random subtests method. Applied Psychological Measurement, 12, 201-209.
