Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

mlogit review

Free#8 of 31 in Conjoint Analysis Software

Open-source R tooling for researchers modeling a wide range of discrete-choice designs.

8.4/10Editor score
mlogit8.4 Visit mlogit

Reviewed by iTechGuides Editors · Editorial team · Updated Nov 2026

mlogit is an open-source R package for maximum-likelihood estimation of random utility discrete-choice models. It is designed for researchers who need to specify, estimate and diagnose multinomial, nested, mixed or random-parameters, multinomial probit, and ranked ordered choice models. Its enhanced formula-data interface and data indexing support model preparation, while included stated-preference datasets and vignettes provide examples of data preparation, estimation and diagnostics.

The pricing model is straightforward: mlogit is free and open source, with no paid plan tiers described. It is distributed through CRAN and requires R 3.5 or newer. Deployment is desktop or self-hosted across Windows, macOS and Linux, so the package fits teams that already maintain an R-based research environment. The published feature set centers on estimation, testing infrastructure, marginal effects and elasticity calculations rather than a hosted application. That makes its ecosystem fit strongest where analysts want to work directly with R data and formulas.

Its main strength is breadth within discrete-choice modeling. Researchers can compare several model families in one package and use built-in testing, marginal effects and elasticity calculations for analysis. The scope is narrower than a complete conjoint-study platform: adaptive conjoint, MaxDiff and survey design are not provided, and the package does not present a hosted respondent workflow or deployment beyond desktop and self-hosted use. Choose mlogit when statistical model coverage and open-source R workflows matter most; choose a survey or conjoint platform instead when study programming, respondent management or adaptive design is central.

mlogit pros and cons

  • Where it wins
    • Covers multinomial, nested, mixed, probit and ranked ordered models
    • Includes hypothesis testing, marginal effects and elasticity calculations
    • Open-source, free and deployable on Windows, macOS, Linux or self-hosted
  • Where it doesn't
    • Requires R 3.5 or newer and desktop or self-hosted setup
    • Does not provide adaptive conjoint, MaxDiff or survey-design tools
    • Documentation is the listed support channel; no hosted study workflow

mlogit fact sheet, pricing and score →

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update