MFX: Marginal Effects and Ratios for Probit, Logit, Poisson, and Beta Regression Models

Alan Fernihough's mfx package estimates marginal effects, odds ratios, and incidence rate ratios for generalized linear models. The output likely contains calculated statistical measures for models including probit, logit, Poisson, negative binomial, and beta regression. The methodology is based on a textbook introduction from Greene (2008, pp. 780-7).

Use Cases

• Interpreting logistic regression coefficients as odds ratios based on the described model outputs.
• Calculating marginal effects for probit models based on the described functionality.
• Estimating incidence rate ratios for Poisson and negative binomial regression models based on the described capabilities.
• Applying beta regression analysis based on the mentioned model type.

Strengths

• Provides outputs for five specific model types: probit, logit, Poisson, negative binomial, and beta regression.
• Implements a standard textbook methodology referenced from Greene (2008).

Limitations

• Row count, column definitions, and sample data are unknown, limiting suitability assessment.
• File formats, size, and license information are unavailable.
• Last update date is unknown; freshness unverified.

Provenance

Source

Alan Fernihough

Collection Method

Likely a software package or code for statistical computation.

Time Range

Methodology reference is from 2008.

Freshness

Last update date is unknown.

Geography

Geographic coverage is unknown.