Predictor Space Research Articles

Walking fingerprinting

Abstract We consider the problem of predicting an individual’s identity from accelerometry data collected during walking. In a previous paper, we transformed the accelerometry time series into an image by constructing the joint distribution of the acceleration and lagged acceleration for a vector of lags. Predictors derived by partitioning this image into grid cells were used in logistic regression to predict individuals. Here, we (a) implement machine learning methods for prediction using the grid cell-derived predictors; (b) derive inferential methods to screen for the most predictive grid cells while adjusting for correlation and multiple comparisons; and (c) develop a novel multivariate functional regression model that avoids partitioning the predictor space. Prediction methods are compared on two open source acceleometry data sets collected from: (a) 32 individuals walking on a 1.06 km path; and (b) six repetitions of walking on a 20 m path on two occasions at least 1 week apart for 153 study participants. In the 32-individual study, all methods achieve at least 95% rank-1 accuracy, while in the 153-individual study, accuracy varies from 41% to 98%, depending on the method and prediction task. Methods provide insights into why some individuals are easier to predict than others.

On the sparsity of synthetic control method

ABSTRACT Synthetic Control Method (SCM) is a popular approach for causal inference in panel data, where the optimal weights for control units are often sparse. But the sparsity of SCM has received little attention in the literature except Abadie (2021), which explores the sparsity from the perspective of predictor space. In this paper, we make three contributions. First, we show that if there is a unique solution, then the number of positive weights is upper-bounded by the number of covariates. Second, we offer a simple alternative explanation about the sparsity of SCM from the perspective of parameter space. Third, we conduct a meta-analysis of empirical studies using SCM in the literature, which shows that the sparsity of SCM decreases with the relative number of covariates. A practical implication is that if the number of positive weights exceeds the number of covariates, there are multiple solutions and possibly unstable weights.

A hybrid physics-based and data-driven model for intra-day and day-ahead wind power forecasting considering a drastically expanded predictor search space

This work presents a novel hybrid (physics- and data-driven) model for short-term (intra-day and day-ahead, 3h-24h) wind power forecasting (STWPF). Traditionally, STWPF predictors admitted very few meteorological variables only from the grid points closest to the turbines. Here, with the aim to further capture the underlying atmospheric processes ruling the wind variability in the wind farm, the approach relies on drastically expanding the predictor space, composed of numerous meteorological variables throughout a large geographical domain, retrieved from a weather forecasting model (COSMO-1). An ad-hoc genetic algorithm that optimizes the selection of predictors is designed and combined with feed-forward artificial neural networks for its cost function evaluation. The introduced model is compared to multiple benchmark models in a 16-turbine wind farm in the Swiss Jura mountains. For +12h and +24h lead times, the new approach shows a root-mean squared error normalized to the installed wind farm capacity of 11% and 11.6%, respectively. These values entail ∼16% higher forecasting skill compared to state-of-the-art predictor frameworks. Results highlight the ability of the presented approach to systematically select as predictors different variables with a well-known impact on the wind farm performance, such as the turbulent kinetic energy or the vertical wind shear. Clustering the data according to the wind direction provides substantial benefit. In addition, it provides a better understanding of the attained improvement: largest performances occur in those wind directions affected by highly complex terrain. This indicates that the proposed model can be especially suitable for wind farms in complex terrain.

Granger non causality and predictor spaces

. In this article, we investigate the relationship between the concept of Granger causality and the notion of prediction space. In particular, we obtain three characterizations of the condition of non causality based on the concept of predictor space.

Local Gaussian Process Extrapolation for BART Models with Applications to Causal Inference

Bayesian additive regression trees (BART) is a semi-parametric regression model offering state-of-the-art performance on out-of-sample prediction. Despite this success, standard implementations of BART typically suffer from inaccurate prediction and overly narrow prediction intervals at points outside the range of the training data. This article proposes a novel extrapolation strategy that grafts Gaussian processes to the leaf nodes in BART for predicting points outside the range of the observed data. The new method is compared to standard BART implementations and recent frequentist resampling-based methods for predictive inference. We apply the new approach to a challenging problem from causal inference, wherein for some regions of predictor space, only treated or untreated units are observed (but not both). In simulation studies, the new approach boasts superior performance compared to popular alternatives, such as Jackknife+. Supplementary materials for this article are available online.

Robust scalar-on-function partial quantile regression

Compared with the conditional mean regression-based scalar-on-function regression model, the scalar-on-function quantile regression is robust to outliers in the response variable. However, it is susceptible to outliers in the functional predictor (called leverage points). This is because the influence function of the regression quantiles is bounded in the response variable but unbounded in the predictor space. The leverage points may alter the eigenstructure of the predictor matrix, leading to poor estimation and prediction results. This study proposes a robust procedure to estimate the model parameters in the scalar-on-function quantile regression method and produce reliable predictions in the presence of both outliers and leverage points. The proposed method is based on a functional partial quantile regression procedure. We propose a weighted partial quantile covariance to obtain functional partial quantile components of the scalar-on-function quantile regression model. After the decomposition, the model parameters are estimated via a weighted loss function, where the robustness is obtained by iteratively reweighting the partial quantile components. The estimation and prediction performance of the proposed method is evaluated by a series of Monte-Carlo experiments and an empirical data example. The results are compared favorably with several existing methods. The method is implemented in an R package robfpqr.

Robust variable selection and estimation via adaptive elastic net S-estimators for linear regression

Heavy-tailed error distributions and predictors with anomalous values are ubiquitous in high-dimensional regression problems and can seriously jeopardize the validity of statistical analyses if not properly addressed. For more reliable variable selection and prediction under these adverse conditions, adaptive PENSE, a new robust regularized regression estimator, is proposed. Adaptive PENSE yields reliable variable selection and coefficient estimates even under aberrant contamination in the predictors or residuals. It is shown that the adaptive penalty leads to more robust and reliable variable selection than other penalties, particularly in the presence of gross outliers in the predictor space. It is further demonstrated that adaptive PENSE has strong variable selection properties and that it possesses the oracle property even under heavy-tailed errors and without the need to estimate the error scale. Numerical studies on simulated and real data sets highlight the superior finite-sample performance in a vast range of settings compared to other robust regularized estimators in the case of contaminated samples. An R package implementing a fast algorithm for computing the proposed method and additional simulation results are provided in the supplementary materials.

A Machine Learning Approach to Predict Watershed Health Indices for Sediments and Nutrients at Ungauged Basins.

Effective water quality management and reliable environmental modeling depend on the availability, size, and quality of water quality (WQ) data. Observed stream water quality data are usuallEEy sparse in both time and space. Reconstruction of water quality time series using surrogate variables such as streamflow have been used to evaluate risk metrics such as reliability, resilience, vulnerability, and watershed health (WH) but only at gauged locations. Estimating these indices for ungauged watersheds has not been attempted because of the high-dimensional nature of the potential predictor space. In this study, machine learning (ML) models, namely random forest regression, AdaBoost, gradient boosting machines, and Bayesian ridge regression (along with an ensemble model), were evaluated to predict watershed health and other risk metrics at ungauged hydrologic unit code 10 (HUC-10) basins using watershed attributes, long-term climate data, soil data, land use and land cover data, fertilizer sales data, and geographic information as predictor variables. These ML models were tested over the Upper Mississippi River Basin, the Ohio River Basin, and the Maumee River Basin for water quality constituents such as suspended sediment concentration, nitrogen, and phosphorus. Random forest, AdaBoost, and gradient boosting regressors typically showed a coefficient of determination for suspended sediment concentration and nitrogen during the testing stage, while the ensemble model exhibited . Watershed health values with respect to suspended sediments and nitrogen predicted by all ML models including the ensemble model were lower for areas with larger agricultural land use, moderate for areas with predominant urban land use, and higher for forested areas; the trained ML models adequately predicted WH in ungauged basins. However, low WH values (with respect to phosphorus) were predicted at some basins in the Upper Mississippi River Basin that had dominant forest land use. Results suggest that the proposed ML models provide robust estimates at ungauged locations when sufficient training data are available for a WQ constituent. ML models may be used as quick screening tools by decision makers and water quality monitoring agencies for identifying critical source areas or hotspots with respect to different water quality constituents, even for ungauged watersheds.

Machine Learning Weather Analogs for Near-Surface Variables

Numerical weather prediction models and high-performance computing have significantly improved our ability to model near-surface variables, but their uncertainty quantification still remains a challenging task. Ensembles are usually produced to depict a series of possible future states of the atmosphere, as a means to quantify the prediction uncertainty, but this requires multiple instantiation of the model, leading to an increased computational cost. Weather analogs, alternatively, can be used to generate ensembles without repeated model runs. The analog ensemble (AnEn) is a technique to identify similar weather patterns for near-surface variables and quantify forecast uncertainty. Analogs are chosen based on a similarity metric that calculates the weighted multivariate Euclidean distance. However, identifying optimal weights for similarity metric becomes a bottleneck because it involves performing a constrained exhaustive search. As a result, only a few predictors were selected and optimized in previous AnEn studies. A new machine learning similarity metric is proposed to improve the theoretical framework on how weather analogs are identified. First, a deep learning network is trained to generate latent features using all the temporal multivariate input predictors. Analogs are then selected in this latent space, rather than the original predictor space. The proposed method does not require prior predictor selection and an exhaustive search, thus presenting a significant computational benefit and scalability. It is tested for surface wind speed and solar irradiance forecasts in Pennsylvania from 2017 to 2019. Results show that the proposed method is capable of handling a large number of predictors, and it outperforms the original similarity metric in RMSE, bias, and CRPS. Since the data-driven transformation network is trained using the historical record, the proposed method has been found to be more flexible for searching through a longer record.

The Application of Spearman Partial Correlation for Screening Predictors of Weight Loss in a Multiomics Dataset.

Obesity has reached epidemic proportions in the United States, but little is known about the mechanisms of weight gain and weight loss. Integration of omics data is becoming a popular tool to increase understanding in such complex phenotypes. Biomarkers come in abundance, but small sample size remains a serious limitation in clinical trials. In the present study, we developed a strategy to screen predictors from a multiomics, high-dimensional, and longitudinal dataset from a small cohort of 10 women with obesity who were provided an identical very-low calorie diet. Our proposal explores the combinatorial space of potential predictors from transcriptomics, microbiome, metabolome, fecal bile acids, and clinical data with the application of the first-order Spearman partial correlation coefficient. Two statistics are proposed for screening predictors, the partial association score, and the persistent significance. We applied our strategy to predict rates of weight loss in our sample of participants in a hospital metabolic facility. Our method reduced an initial set of 42,000 biomarker candidates to 61 robust predictors. The results show baseline fecal bile acids and regulation in RT-polymerase chain reaction as the most predictive data sources in forecasting the rate of weight-loss. In summary, the present study proposes a strategy based on nonparametric statistics for ranking and screening predictors of weight loss from a multiomics study. The proposed biomarker screening strategy warrants further translational clinical investigation in obesity and other complex clinical phenotypes.

Predicting the Internal Knee Abduction Impulse During Walking Using Deep Learning.

Knee joint moments are commonly calculated to provide an indirect measure of knee joint loads. A shortcoming of inverse dynamics approaches is that the process of collecting and processing human motion data can be time-consuming. This study aimed to benchmark five different deep learning methods in using walking segment kinematics for predicting internal knee abduction impulse during walking. Three-dimensional kinematic and kinetic data used for the present analyses came from a publicly available dataset on walking (participants n = 33). The outcome for prediction was the internal knee abduction impulse over the stance phase. Three-dimensional (3D) angular and linear displacement, velocity, and acceleration of the seven lower body segment’s center of mass (COM), relative to a fixed global coordinate system were derived and formed the predictor space (126 time-series predictors). The total number of observations in the dataset was 6,737. The datasets were split into training (75%, n = 5,052) and testing (25%, n = 1685) datasets. Five deep learning models were benchmarked against inverse dynamics in quantifying knee abduction impulse. A baseline 2D convolutional network model achieved a mean absolute percentage error (MAPE) of 10.80%. Transfer learning with InceptionTime was the best performing model, achieving the best MAPE of 8.28%. Encoding the time-series as images then using a 2D convolutional model performed worse than the baseline model with a MAPE of 16.17%. Time-series based deep learning models were superior to an image-based method when predicting knee abduction moment impulse during walking. Future studies looking to develop wearable technologies will benefit from knowing the optimal network architecture, and the benefit of transfer learning for predicting joint moments.

Spatiotemporal distribution of labeled data can bias the validation and selection of supervised learning algorithms: A marine remote sensing example

Supervised learning allows the prediction of variables measured in-situ from variables that can be measured from satellites. A labeled data set for this purpose is typically created by matching in-situ and satellite data and split into subsets for model training and initial validation. However, the available data are often not randomly distributed in space and time. In theory, this can bias estimates of prediction errors. Here, remote sensing of chlorophyll a in the Baltic Sea serves as an example to demonstrate the importance of this problem in marine remote sensing, and to test how well different statistical designs for validation mitigate it. Semi-synthetic data sets were created by combining daily chlorophyll a fields from a biogeochemical model hindcast with real-world locations and times of in-situ measurements, generated by sampling 2,000 combinations of cruises from an oceanographic database. These data sets were matched with co-located satellite data and used to train and validate four algorithms using remote sensing reflectances as input. The algorithms were validated using different methods including random hold-out sets and various block cross-validation designs based on geographical location, time, or location in predictor space. The resulting error estimates were compared to true errors calculated from differences to the biogeochemical model outputs serving as response variable. All validation methods underestimated prediction errors, in many cases by >30%. While a simple band-ratio algorithm had the smallest true errors (e.g., absolute percentage difference: APD = 50%), estimated errors were smallest for more complicated and in fact less accurate machine learning algorithms. For example, ten-fold cross-validation led to selection of the truly best algorithm among four candidates for <10% of data sets. The biases were smallest, but not absent, for spatial block cross-validation, which selected the truly best algorithm for 21–46% of data sets, depending on the error measure. When the analyses were repeated with data that were randomly distributed in space and time, the biases of error estimates based on random splits became much smaller (e.g., 10-fold cross-validation estimated errors within 2% of their true values and selected the truly best algorithm for >99% of data sets), spatial block cross-validation overestimated prediction errors (often by >40%), all algorithms achieved lower true errors, and a random forest made the most accurate predictions overall (APD = 27%). These results show that more attention should be paid to statistical methods for estimating the errors of supervised learning algorithms, e.g., by using multiple validation methods in combination and critically discussing error estimates considering questions of dependence, representativeness, and stationarity. Furthermore, non-random spatiotemporal distribution of labeled data can be a barrier to harnessing the full potential of machine learning algorithms in marine remote sensing.

The Dependent Dirichlet Process and Related Models

Standard regression approaches assume that some finite number of the response distribution characteristics, such as location and scale, change as a (parametric or nonparametric) function of predictors. However, it is not always appropriate to assume a location/scale representation, where the error distribution has unchanging shape over the predictor space. In fact, it often happens in applied research that the distribution of responses under study changes with predictors in ways that cannot be reasonably represented by a finite dimensional functional form. This can seriously affect the answers to the scientific questions of interest, and therefore more general approaches are indeed needed. This gives rise to the study of fully nonparametric regression models. We review some of the main Bayesian approaches that have been employed to define probability models where the complete response distribution may vary flexibly with predictors. We focus on developments based on modifications of the Dirichlet process, historically termed dependent Dirichlet processes, and some of the extensions that have been proposed to tackle this general problem using nonparametric approaches.

Abstract PO-236: Examining racial disparities in lung cancer stage of diagnosis among low-income adults living in the southeastern U.S.

Abstract Purpose: Black Americans experience poorer lung cancer survival than White Americans. Racial disparities in stage at diagnosis may contribute to these survival differences, but few studies have explored factors leading to racial disparities in lung cancer stage at diagnosis. We aimed to identify multilevel factors contributing to racial disparities in stage of lung cancer presentation. Methods: Using data from the Southern Community Cohort Study (SCCS), we examined factors associated with distant stage among adults diagnosed with incident lung cancer. SCCS participants were prospectively enrolled, primarily from community health centers between 2002 and 2009 across a 12-state area. Incident cancers were identified by linkage with state cancer registries through end of follow-up in 2019. Self-reported social, behavioral, and medical history information were ascertained at baseline via questionnaire. Cumulative exposure smoking histories were identified using the most recent follow-up questionnaires. Residential addresses and National Cancer Institute Comprehensive Cancer Center locations were geocoded, and residential addresses were linked to census data. Logistic and multinomial regression models were used to identify factors predictive of distant stage diagnosis. Penalized regression was used to shrink the predictor space of these models when necessary. Findings were replicated in an independent population. Results: Among 1,672 incident SCCS lung cancer cases (35% White, 61% Black, and 3% other self-reported race), a greater percentage of Black participants than White participants were diagnosed with distant stage lung cancer (56.4% vs 49.4%, respectively). Overall, Black participants had greater odds of distant vs local stage compared to White participants (odds ratio (OR) = 1.28, 95% confidence interval (CI): 1.05-1.58). Greater area deprivation was also associated with distant lung cancer stage (OR = 1.55, 95% CI: 1.17-2.04). After controlling for individual and area-level factors, there was no significant difference in the odds of distant stage disease for Black participants compared to White participants (OR = 1.03, 95% CI: 0.80-1.33). Significant interactions between race and area deprivation index were not observed. However, greater residential distance from a comprehensive cancer center was significantly associated with increased odds of distant stage disease in the final model (OR = 1.04, 95% CI: 1.00-1.08). No significant differences were observed in the odds of distant stage lung cancer among Black and White participants in the independent population. Conclusions: A greater percentage of Black participants were diagnosed with distant stage lung cancer; however, this disparity dissipated after adjusting for individual and area-level factors. Our findings suggest racial disparities in lung cancer stage at diagnosis may be ameliorated with modifiable factors, such as patient access to high quality cancer centers. Citation Format: Jennifer Richmond, Megan Hollister, Cato M. Milder, Ann G. Schwartz, Jeffrey D. Blume, Melinda C. Aldrich. Examining racial disparities in lung cancer stage of diagnosis among low-income adults living in the southeastern U.S. [abstract]. In: Proceedings of the AACR Virtual Conference: 14th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2021 Oct 6-8. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2022;31(1 Suppl):Abstract nr PO-236.

Interactive Slice Visualization for Exploring Machine Learning Models

Machine learning models fit complex algorithms to arbitrarily large datasets. These algorithms are well known to be high on performance and low on interpretability. We use interactive visualization of slices of predictor space to address the interpretability deficit; in effect opening up the black-box of machine learning algorithms, for the purpose of interrogating, explaining, validating and comparing model fits. Slices are specified directly through interaction, or using various touring algorithms designed to visit high-occupancy sections, or regions where the model fits have interesting properties. The methods presented here are implemented in the R package condvis2. Supplementary files for this article are available online.

Predicting into unknown space? Estimating the area of applicability of spatial prediction models

Abstract Machine learning algorithms have become very popular for spatial mapping of the environment due to their ability to fit nonlinear and complex relationships. However, this ability comes with the disadvantage that they can only be applied to new data if these are similar to the training data. Since spatial mapping requires predictions to new geographic space which in many cases goes along with new predictor properties, a method to assess the area to which a prediction model can be reliably applied is required. Here, we suggest a methodology that delineates the ‘area of applicability’ (AOA) that we define as the area where we enabled the model to learn about relationships based on the training data, and where the estimated cross‐validation performance holds. We first propose a ‘dissimilarity index’ (DI) that is based on the minimum distance to the training data in the multidimensional predictor space, with predictors being weighted by their respective importance in the model. The AOA is then derived by applying a threshold which is the (outlier‐removed) maximum DI of the training data derived via cross‐validation. We further use the relationship between the DI and the cross‐validation performance to map the estimated performance of predictions. We illustrate the approach in a simulated case study chosen to mimic ecological realities and test the credibility by using a large set of simulated data. The simulation studies showed that the prediction error within the AOA is comparable to the cross‐validation error of the trained model, while the cross‐validation error does not apply outside the AOA. This applies to models being trained with randomly distributed training data, as well as when training data are clustered in space and where spatial cross‐validation is applied. Using the relationship between DI and cross‐validation performance showed potential to limit predictions to the area where a user‐defined performance applies. We suggest to add the AOA computation to the modeller's standard toolkit and to present predictions for the AOA only. We further suggest to report a map of DI‐dependent performance estimates alongside prediction maps and complementary to (cross‐)validation performance measures and the common uncertainty estimates.

Post-Analysis of Predictive Modeling with an Epidemiological Example.

Post-analysis of predictive models fosters their application in practice, as domain experts want to understand the logic behind them. In epidemiology, methods explaining sophisticated models facilitate the usage of up-to-date tools, especially in the high-dimensional predictor space. Investigating how model performance varies for subjects with different conditions is one of the important parts of post-analysis. This paper presents a model-independent approach for post-analysis, aiming to reveal those subjects’ conditions that lead to low or high model performance, compared to the average level on the whole sample. Conditions of interest are presented in the form of rules generated by a multi-objective evolutionary algorithm (MOGA). In this study, Lasso logistic regression (LLR) was trained to predict cardiovascular death by 2016 using the data from the 1984–1989 examination within the Kuopio Ischemic Heart Disease Risk Factor Study (KIHD), which contained 2682 subjects and 950 preselected predictors. After 50 independent runs of five-fold cross-validation, the model performance collected for each subject was used to generate rules describing “easy” and “difficult” cases. LLR with 61 selected predictors, on average, achieved 72.53% accuracy on the whole sample. However, during post-analysis, three categories of subjects were discovered: “Easy” cases with an LLR accuracy of 95.84%, “difficult” cases with an LLR accuracy of 48.11%, and the remaining cases with an LLR accuracy of 71.00%. Moreover, the rule analysis showed that medication was one of the main confusing factors that led to lower model performance. The proposed approach provides insightful information about subjects’ conditions that complicate predictive modeling.

A Multiple Imputation Approach for Handling Missing Data in Classification and Regression Trees

Decision trees (DTs) is a machine learning technique that searches the predictor space for the variable and observed value that leads to the best prediction when the data are split into two nodes based on the variable and splitting value. The algorithm repeats its search within each partition of the data until a stopping rule ends the search. Missing data can be problematic in DTs because of an inability to place an observation with a missing value into a node based on the chosen splitting variable. Moreover, missing data can alter the selection process because of its inability to place observations with missing values. Simple missing data approaches (e.g., listwise deletion, majority rule, and surrogate split) have been implemented in DT algorithms; however, more sophisticated missing data techniques have not been thoroughly examined. We propose a modified multiple imputation approach to handling missing data in DTs, and compare this approach with simple missing data approaches as well as single imputation and a multiple imputation with prediction averaging via Monte Carlo Simulation. This study evaluated the performance of each missing data approach when data were MAR or MCAR. The proposed multiple imputation approach and surrogate splits had superior performance with the proposed multiple imputation approach performing best in the more severe missing data conditions. We conclude with recommendations for handling missing data in DTs.

Variable Selection and Regularization in Quantile Regression via Minimum Covariance Determinant Based Weights.

The importance of variable selection and regularization procedures in multiple regression analysis cannot be overemphasized. These procedures are adversely affected by predictor space data aberrations as well as outliers in the response space. To counter the latter, robust statistical procedures such as quantile regression which generalizes the well-known least absolute deviation procedure to all quantile levels have been proposed in the literature. Quantile regression is robust to response variable outliers but very susceptible to outliers in the predictor space (high leverage points) which may alter the eigen-structure of the predictor matrix. High leverage points that alter the eigen-structure of the predictor matrix by creating or hiding collinearity are referred to as collinearity influential points. In this paper, we suggest generalizing the penalized weighted least absolute deviation to all quantile levels, i.e., to penalized weighted quantile regression using the RIDGE, LASSO, and elastic net penalties as a remedy against collinearity influential points and high leverage points in general. To maintain robustness, we make use of very robust weights based on the computationally intensive high breakdown minimum covariance determinant. Simulations and applications to well-known data sets from the literature show an improvement in variable selection and regularization due to the robust weighting formulation.

Bayesian penalized cumulative logit model for high-dimensional data with an ordinal response.

Many previous studies have identified associations between gene expression, measured using high-throughput genomic platforms, and quantitative or dichotomous traits. However, we note that health outcome and disease status measurements frequently appear on an ordinal scale, that is, the outcome is categorical but has inherent ordering. Identification of important genes may be useful for developing novel diagnostic and prognostic tools to predict or classify stage of disease. Gene expression data are usually high-dimensional, meaning that the number of genes is much larger than the sample size or number of patients. Herein we describe some existing frequentist methods for modeling an ordinal response in a high-dimensional predictor space. Following Tibshirani (1996), who described the LASSO estimate as the Bayesian posterior mode when the regression coefficients have independent Laplace priors, we propose a new approach for high-dimensional data with an ordinal response that is rooted in the Bayesian paradigm. We show that our proposed Bayesian approach outperforms existing frequentist methods through simulation studies. We then compare the performance of frequentist and Bayesian approaches using a study evaluating progression to hepatocellular carcinoma in hepatitis C infected patients.