Search

The Department of Workforce Services (DWS) asked the Utah State Board of Education (USBE) to provide a longitudinal perspective on progress toward education outcomes for students experiencing intergenerational poverty (IGP). As of 2020, students affected by IGP often had higher rates of chronic absence and lower proficiency rates than students statewide. The authors first compiled a list of USBE administered programs that serve low-income students and then looked for available data that described the extent to which students participated in these programs. They include brief, narrative descriptions of all programs identified as serving low-income students, and for programs with data, the authors provide percentages of participation. The study presented in this report had two primary goals: (1) To create a comprehensive list of programs that serve low-income students and students affected by IGP, and; (2) To determine the extent to which the students affected by IGP are accessing programs and services that are designed to serve them. Information was gathered from USBE directors and coordinators about programs they administered that were designed to serve students from low-income backgrounds. Once a list of programs was complete, the authors determined if student participation in these programs was documented in the USBE data system or if program specialists at the USBE collected and maintained program participation records. The authors found 24 programs and 12 of those programs had available data. Results are organized into three categories that differentiate the extent to which programs were specifically designed to serve low-income students: (1) General programs, those designed for all students and that may benefit low-income students; (2) Student support programs, those designed to serve and benefit students who are underserved or who need additional academic support; and Targeted low-income programs, having been created to serve and benefit low-income students.

This paper presents the statistical model for Ticker [1], a novel probabilistic stereophonic single-switch text entry method for visually-impaired users with motor disabilities who rely on single-switch scanning systems to communicate. All terminology and notation are defined in [1].

Single-switch scanning systems allow nonspeaking individuals with motor disabilities to communicate by triggering a single switch (e.g., raising an eye brow). A problem with current single-switch scanning systems is that while they result in reasonable performance in noiseless conditions, for instance via simulation or tests with able-bodied users, they fail to accurately model the noise sources that are introduced when a non-speaking individual with motor disabilities is triggering the switch in a realistic use context. To help assist the development of more noise-resilient single-switch scanning systems we have developed a mathematical model of scanning systems which incorporates extensive noise modelling. Our model includes an improvement to the standard scanning method, which we call fast-scan, which we show via simulation can be more suitable for certain users of scanning systems.

Markov Chain Monte Carlo (MCMC) algorithms are routinely used to draw samples from distributions with intractable normalization constants. However, standard MCMC algorithms do not apply to doubly-intractable distributions in which there are additional parameter-dependent normalization terms; for example, the posterior over parameters of an undirected graphical model. An ingenious auxiliary-variable scheme (Moeller et al., 2004) offers a solution: exact sampling (Propp and Wilson, 1996) is used to sample from a Metropolis-Hastings proposal for which the acceptance probability is tractable. Unfortunately the acceptance probability of these expensive updates can be low. This paper provides a generalization of Moeller et al. (2004) and a new MCMC algorithm, which obtains better acceptance probabilities for the same amount of exact sampling, and removes the need to estimate model parameters before sampling begins., Comment: Appears in Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence (UAI2006)

Many probabilistic models introduce strong dependencies between variables using a latent multivariate Gaussian distribution or a Gaussian process. We present a new Markov chain Monte Carlo algorithm for performing inference in models with multivariate Gaussian priors. Its key properties are: 1) it has simple, generic code applicable to many models, 2) it has no free parameters, 3) it works well for a variety of Gaussian process based models. These properties make our method ideal for use while model building, removing the need to spend time deriving and tuning updates for more complex algorithms., Comment: 8 pages, 6 figures, appearing in AISTATS 2010 (JMLR: W&CP volume 6). Differences from first submission: some minor edits in response to feedback.

We present the Gaussian process density sampler (GPDS), an exchangeable generative model for use in nonparametric Bayesian density estimation. Samples drawn from the GPDS are consistent with exact, independent samples from a distribution defined by a density that is a transformation of a function drawn from a Gaussian process prior. Our formulation allows us to infer an unknown density from data using Markov chain Monte Carlo, which gives samples from the posterior distribution over density functions and from the predictive distribution on data space. We describe two such MCMC methods. Both methods also allow inference of the hyperparameters of the Gaussian process., Comment: 26 pages, 4 figures, submitted to the Annals of Statistics

Selection methods that require only a single-switch input, such as a button click or blink, are potentially useful for individuals with motor impairments, mobile technology users, and individuals wishing to transmit information securely. We present a single-switch selection method, "Nomon," that is general and efficient. Existing single-switch selection methods require selectable options to be arranged in ways that limit potential applications. By contrast, traditional operating systems, web browsers, and free-form applications (such as drawing) place options at arbitrary points on the screen. Nomon, however, has the flexibility to select any point on a screen. Nomon adapts automatically to an individual's clicking ability; it allows a person who clicks precisely to make a selection quickly and allows a person who clicks imprecisely more time to make a selection without error. Nomon reaps gains in information rate by allowing the specification of beliefs (priors) about option selection probabilities and by avoiding tree-based selection schemes in favor of direct (posterior) inference. We have developed both a Nomon-based writing application and a drawing application. To evaluate Nomon's performance, we compared the writing application with a popular existing method for single-switch writing (row-column scanning). Novice users wrote 35% faster with the Nomon interface than with the scanning interface. An experienced user (author TB, with > 10 hours practice) wrote at speeds of 9.3 words per minute with Nomon, using 1.2 clicks per character and making no errors in the final text., Comment: 14 pages, 5 figures, 1 table, presented at NIPS 2009 Mini-symposia

Changepoints are abrupt variations in the generative parameters of a data sequence. Online detection of changepoints is useful in modelling and prediction of time series in application areas such as finance, biometrics, and robotics. While frequentist methods have yielded online filtering and prediction techniques, most Bayesian papers have focused on the retrospective segmentation problem. Here we examine the case where the model parameters before and after the changepoint are independent and we derive an online algorithm for exact inference of the most recent changepoint. We compute the probability distribution of the length of the current ``run,'' or time since the last changepoint, using a simple message-passing algorithm. Our implementation is highly modular so that the algorithm may be applied to a variety of types of data. We illustrate this modularity by demonstrating the algorithm on three different real-world data sets., Comment: 7 pages, 4 figures, latex

We present sparse graph codes appropriate for use in quantum error-correction. Quantum error-correcting codes based on sparse graphs are of interest for three reasons. First, the best codes currently known for classical channels are based on sparse graphs. Second, sparse graph codes keep the number of quantum interactions associated with the quantum error correction process small: a constant number per quantum bit, independent of the blocklength. Third, sparse graph codes often offer great flexibility with respect to blocklength and rate. We believe some of the codes we present are unsurpassed by previously published quantum error-correcting codes., Comment: Version 7.3e: 42 pages. Extended version, Feb 2004. A shortened version was resubmitted to IEEE Transactions on Information Theory Jan 20, 2004