TheRPackagethregto Implement Threshold Regression Models

Abstract

This paper introduces the R package threg, which implements the estimation procedure of a threshold regression model, which is based on the first-hitting-time of a boundary by the sample path of a Wiener diffusion process. The threshold regression methodology is well suited to applications involving survival and time-to-event data, and serves as an important alternative to the Cox proportional hazards model.This new package includes four functions: threg, and the methods hr, predict and plot for 'threg' objects returned by threg. The threg function is the model-fitting function which is used to calculate regression coefficient estimates, asymptotic standard errors and p values. The hr method for 'threg' objects is the hazard-ratio calculation function which provides the estimates of hazard ratios at selected time points for specified scenarios (based on given categories or value settings of covariates). The predict method for 'threg objects is used for prediction. And the plot method for 'threg' objects provides plots for curves of estimated hazard functions, survival functions and probability density functions of the first-hitting-time; function curves corresponding to different scenarios can be overlaid in the same plot for comparison to give additional research insights.

Causal Inference in Threshold Regression and the Neural Network Extension (TRNN)

“…The standard error was computed based on 1000 repetitions. All models were fitted in R [28] with the threg package [29].…”

“…In this application, for the µ network, we considered baseline covariates, including the smoking status (smoker vs non-smoker), gender (female vs male), race (white vs non-white), age at enrollment (younger than 18, 19-25, 25-29, and older than 30), marital status (married or living as married, divorced or separated or widowed, never married), baseline BMI, and baseline SBP. For the y 0 network, we considered gender (female vs male), race (white vs non-white), age at enrollment (younger than 19,[19][20][21][22][23][24][25][25][26][27][28][29], and older than 29), marital status (married or living as married, divorced or separated or widowed, never married), baseline BMI, baseline SBP, exercise intensity score, employment status (full-time/part-time/unemployed), education level (less than high school or GED/some college or college/college above), self-reported diabetic, hypertension, high cholesterol, whether father/mother had a heart attack, and whether father/mother had a stroke. Nevertheless, TRNN is capable of handling highdimensional input.…”

Group sequential design for randomized trials using “first hitting time” model

“…As the NPH scenario continues to draw researchers' attention, the TR model has become increasingly popular during the past few years. TR has been successfully applied to many medical research topics and is available in several types of off-the-shelf software, such as STATA 24 and R. 25,26 Also, the TR model has been used in analyzing clinical trial data. 27 The application of TR in clinical trial design and GSD, however, has not been explored yet, a gap that we plan to fill in this article.…”