Search

Traditional methods for evaluating a potential treatment have focused on the average treatment effect. However, there exist situations where individuals can experience significantly heterogeneous responses to a treatment. In these situations, one needs to account for the differences among individuals when estimating the treatment effect. Li et al. (2022) proposed a method based on random forest of interaction trees (RFIT) for a binary or categorical treatment variable, while incorporating the propensity score in the construction of random forest. Motivated by the need to evaluate the effect of tutoring sessions at a Math and Stat Learning Center (MSLC), we extend their approach to an ordinal treatment variable. Our approach improves upon RFIT for multiple treatments by incorporating the ordered structure of the treatment variable into the tree growing process. To illustrate the effectiveness of our proposed method, we conduct simulation studies where the results show that our proposed method has a lower mean squared error and higher optimal treatment classification, and is able to identify the most important variables that impact the treatment effect. We then apply the proposed method to estimate how the number of visits to the MSLC impacts an individual student’s probability of passing an introductory statistics course. Our results show that every student is recommended to go to the MSLC at least once and some can drastically improve their chance of passing the course by going the optimal number of times suggested by our analysis.

We expand methods for estimating an optimal treatment regime (OTR) from the personalized medicine literature to educational data mining applications. As part of this development, we detail and modify the current state-of-the-art, assess the efficacy of the approaches for student success studies, and provide practitioners the machinery to apply the methods in their specific problems. Our particular interest is to estimate an optimal treatment regime for students enrolled in an introductory statistics course at San Diego State University (SDSU). The available treatments are combinations of three programs SDSU implemented to foster student success in this large enrollment, bottleneck STEM course. We leverage tree-based reinforcement learning approaches based on either an inverse probability-weighted purity measure or an augmented probability-weighted purity measure. The thereby deduced OTR promises to significantly increase the average grade in the introductory course and also reveals the need for program recommendations to students as only very few, on their own, selected their optimal treatment.

Despite the importance of monsoon rainfall to over half of the world's population, many climate models of the current generation struggle to capture some of the major features of the various monsoon systems. Studies of the development of errors in several tropical regions have shown that they start to develop very quickly, within the first few days of a model simulation, and can then persist to climate timescales. Understanding the sources of such errors requires the combination of various modelling techniques and sensitivity experiments of varying complexity. Here, we demonstrate how such analysis can shed light on the way in which monsoon errors develop, their local and remote drivers and feedbacks. We make use of the seamless modelling approach adopted by the Met Office, whereby different applications of the Met Office Unified Model (MetUM) use essentially the same model configuration (dynamical core and physical parameterisations) across a range of spatial and temporal scales. Using the Asian summer monsoon (ASM) as an example, we show that error patterns in circulation and rainfall over the ASM region in the MetUM are similar between multidecadal climate simulations and seasonal hindcasts initialised in spring. Analysis of the development of these errors on both short-range and seasonal timescales following model initialisation suggests that both the Maritime Continent and the oceans around the Philippines play a role in the development of East Asian summer monsoon errors, with the Indian summer monsoon region providing an additional contribution, while the errors over the Indian summer monsoon region itself appear to arise locally. Regional modelling with various lateral boundary locations helps to separate local and remote contributions to the errors, while regional relaxation experiments shed light on the influence of errors developing within particular areas on the region as a whole.

Background and Objectives Selecting applications for college admission is critical for university operation and development. This paper leverages machine learning techniques to support enrollment management teams through data-informed decision-making in this otherwise laborious admissions processing. Research Design and Measures Two aspects of university admissions are considered. An ensemble learning approach, through the SuperLearner algorithm, is used to predict student show (yield) rate. The goal is to improve prediction accuracy to minimize over- or under-enrollment. A combinatorial optimization framework is proposed to weigh academic performance and experiential factors for ranking and selecting students for admission. This framework uses simulated annealing, and an efficacy study is presented to evaluate performance. Results The proposed framework is illustrated for selecting an incoming class by optimizing predicted graduation rate and by developing an eligibility index. Each example presents a selection process under potential academic performance and experiential factor targets a university may place on an admitted class. R code is provided for higher education researchers and practitioners to apply the proposed methods in their own settings.

Serotonin plays an important role in the development of brainstem circuits that control breathing. Here, we test the hypothesis that developmental nicotine exposure (DNE) alters the breathing-related motor response to serotonin (5HT). Pregnant rats were exposed to nicotine or saline, and brainstem-spinal cord preparations from 1- to 5-day-old pups were studied in a split-bath configuration, allowing drugs to be applied selectively to the medulla or spinal cord. The activity of the fourth cervical ventral nerve roots (C4VR), which contain axons of phrenic motoneurons, was recorded. We applied 5HT alone or together with antagonists of 5HT1A, 5HT2A, or 5HT7 receptor subtypes. In control preparations, 5HT applied to the medulla consistently reduced C4VR frequency and this reduction could not be blocked by any of the three antagonists. In DNE preparations, medullary 5HT caused a large and sustained frequency increase (10 min), followed by a sustained decrease. Notably, the transient increase in frequency could be blocked by the independent addition of any of the antagonists. Experiments with subtype-specific agonists suggest that the 5HT7 subtype may contribute to the increased frequency response in the DNE preparations. Changes in C4VR burst amplitude in response to brainstem 5HT were uninfluenced by DNE. Addition of 5HT to the caudal chamber modestly increased phasic and greatly increased tonic C4VR activity, but there were no effects of DNE. The data show that DNE alters serotonergic signaling within brainstem circuits that control respiratory frequency but does not functionally alter serotonin signaling in the phrenic motoneuron pool.

In this paper, we propose a new random forest method based on completely randomized splitting rules with an acceptance–rejection criterion for quality control. We show how the proposed acceptance–rejection (AR) algorithm can outperform the standard random forest algorithm (RF) and some of its variants including extremely randomized (ER) trees and smooth sigmoid surrogate (SSS) trees. Twenty datasets were analyzed to compare prediction performance and a simulated dataset was used to assess variable selection bias. In terms of prediction accuracy for classification problems, the proposed AR algorithm performed the best, with ER being the second best. For regression problems, RF and SSS performed the best, followed by AR, and then ER at the last. However, each algorithm was most accurate for at least one study. We investigate scenarios where the AR algorithm can yield better predictive performance. In terms of variable importance, both RF and SSS demonstrated selection bias in favor of variables with many possible splits, while both ER and AR largely removed this bias.