USPS-package {USPS}R Documentation

Unsupervised and Supervised Propensity Score Adjustment for Bias and Confounding

Description

Define Local Treatment Differences (LTDs) and Local Average Outcomes (LAOs) within Clusters of patients who have been relatively well-matched on their baseline X-covariates. The resulting distribution of LTD effect-size estimates can be interpreted much like a Bayesion posterior yet has been formed, via Nonparametric Preprocessing, in a purely Objective way.

Details

Package: USPS
Type: Package
Version: 1.3
Date: 2018-4-2
License: GPL

SUPERVISED OUTCOME BINNING AND SMOOTHING VIA ESTIMATED PROPENSITY SCORES:

Once one has fitted a somewhat smooth curve through scatters of observed outcomes, Y, versus fitted propensity scores, X, for the patients in each of the two treatment groups, one can consider the question: "Over the range where both smooth curves are defined (i.e. their common support), what is the (weighted) average signed difference between these two curves?"

UNSUPERVISED NEAREST NEIGHBORS / LOCAL TREATMENT DIFFERENCES:

Multiple calls to UPSnnltd(n) for varying numbers of clusters, n, are typically made after first invoking UPShclus() to hierarchically cluster patients in X-space and then invoking UPSaccum() to specify a Y outcome variable and a two-level (binary) treatment factor t. UPSnnltd(n) then determines the LTD Distribution corresponding to n clusters and, optionally, displays this distribution in a "Snowball" plot.

UNSUPERVISED INSTRUMENTAL VARIABLES / LOCAL AVERAGE y-OUTCOME EFFECTS:

The Observed Propensity Score (OPS) is defined here to be the local (within-cluster) observed fraction of experimental units (patients) choosing the new treatment (t=1) over the control treatment (t=0). Multiple calls to UPSivadj(n) for varying numbers of clusters, n, then yield alternative linear fits to LAO estimates plotted versus their X = OPS. The slope of each such fit determines both the direction and strength of CER preferences for treatment or control.

Author(s)

Bob Obenchain <wizbob@att.net>

References

Green PJ, Silverman BW. (1994) Nonparametric Regression and Generalized Linear Models: A Roughness Penalty Approach. Chapman and Hall.

McClellan M, McNeil BJ, Newhouse JP. (1994) Does More Intensive Treatment of Myocardial Infarction in the Elderly Reduce Mortality?: Analysis Using Instrumental Variables. JAMA 272: 859-866.

Obenchain RL. (2004) Unsupervised Propensity Scoring: NN and IV Plots. Proceedings of the American Statistical Association (on CD) 8 pages.

Obenchain RL. (2018) USPS_in_R.pdf http://localcontrolstatistics.org 40 pages.

Rosenbaum PR, Rubin RB. (1983) The Central Role of the Propensity Score in Observational Studies for Causal Effects. Biometrika 70: 41-55.

Rubin DB. (1980) Bias reduction using Mahalanobis metric matching. Biometrics 36: 293-298.

Examples

  demo(abcix)

[Package USPS version 1.3 Index]