Estimating Equations

To ease use, delicatessen comes with a variety of built-in estimating equations, covering a variety of common use cases. Below is reference documentation for currently supported estimating equations.

Basic

ee_mean(theta, y)	Estimating equation for the mean.
ee_mean_robust(theta, y, k[, loss, lower, upper])	Estimating equation for the (unscaled) robust mean.
ee_mean_variance(theta, y)	Estimating equations for the mean and variance. The estimating equations for the mean and
ee_percentile(theta, y, q)	Estimating equation for the q percentile.
ee_positive_mean_deviation(theta, y)	Estimating equations for the positive mean deviation.

Regression

ee_regression(theta, X, y, model[, weights, ...])	Estimating equation for regression.
ee_mlogit(theta, X, y[, weights, offset])	Estimating equation for multinomial logistic regression.
ee_glm(theta, X, y, distribution, link[, ...])	Estimating equation for regression with a generalized linear model.
ee_robust_regression(theta, X, y, model, k)	Estimating equations for (unscaled) robust regression.
ee_ridge_regression(theta, X, y, model, penalty)	Estimating equations for ridge regression.
ee_lasso_regression(theta, X, y, model, penalty)	Estimating equation for an approximate LASSO (least absolute shrinkage and selection operator) regressor.
ee_elasticnet_regression(theta, X, y, model, ...)	Estimating equations for Elastic-Net regression.
ee_bridge_regression(theta, X, y, model, ...)	Estimating equation for bridge penalized regression.
ee_additive_regression(theta, X, y, ...[, ...])	Estimating equation for Generalized Additive Models (GAMs).

Measurement

ee_rogan_gladen(theta, y, y_star, r[, weights])	Estimating equation for the Rogan-Gladen correction for mismeasured binary outcomes.
ee_rogan_gladen_extended(theta, y, y_star, r, X)	Estimating equation for the extended Rogan-Gladen correction for mismeasured binary outcomes.

Survival

ee_exponential_model(theta, t, delta)	Estimating equation for an exponential model.
ee_exponential_measure(theta, times, n, ...)	Estimating equation to calculate a survival measure (survival, density, risk, hazard, cumulative hazard) from the exponential model.
ee_weibull_model(theta, t, delta)	Estimating equation for a two-parameter Weibull model.
ee_weibull_measure(theta, times, n, measure, ...)	Estimating equation to calculate a survival measure (survival, density, risk, hazard, cumulative hazard) for the Weibull model.
ee_aft_weibull(theta, X, t, delta[, weights])	Estimating equation for accelerated failure time (AFT) model with a Weibull distribution.
ee_aft_weibull_measure(theta, times, X, ...)	Estimating equation to calculate a survival measure (survival, density, risk, hazard, cumulative hazard) given a specific covariate pattern and Weibull accelerated failure time (AFT) model.

Dose Response

ee_4p_logistic(theta, X, y)	Estimating equations for the 4-parameter logistic model (4PL).
ee_3p_logistic(theta, X, y, lower)	Estimating equations for the 3-parameter logistic model (3PL).
ee_2p_logistic(theta, X, y, lower, upper)	Estimating equations for the 2-parameter logistic model (2PL).
ee_effective_dose_delta(theta, y, delta, ...)	Default stacked estimating equation to pair with the 4 parameter logistic model for estimation of the \(delta\) effective dose.

Causal Inference

ee_gformula(theta, y, X, X1[, X0, ...])	Estimating equations for the g-formula (or g-computation).
ee_ipw(theta, y, A, W[, truncate, weights])	Estimating equation for inverse probability weighting (IPW) estimator.
ee_ipw_msm(theta, y, A, W, V, distribution, link)	Estimating equation for parameters of a marginal structural model estimated using inverse probability weighting.
ee_aipw(theta, y, A, W, X, X1, X0[, ...])	Estimating equation for augmented inverse probability weighting (AIPW) estimator.
ee_gestimation_snmm(theta, y, A, W, V[, X, ...])	Estimating equations for g-estimation of structural mean models (SMMs).
ee_mean_sensitivity_analysis(theta, y, ...)	Estimating equation for weighted sensitivity analysis estimator of the mean.