Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 35 for “"Variable Importance"”.

  1. Quantifying the Effects of Correlated Covariates on Variable Importance Estimates from Random Forests

    … models. This study examined the effectiveness of variable importance estimates from the random forest algorithm in identifying the true predictor among a large number of candidate predictors. A simulation study was conducted using twenty different levels of association among the independent …

    vcu Repository record for Quantifying the Effects of Correlated Covariates on Variable Importance Estimates from Random Forests (opens in a new tab)

  2. Dimension reduction methods for quantifying local variable importance and the statistical analysis of network data

    Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2024-08-01

    uiuc Repository record for Dimension reduction methods for quantifying local variable importance and the statistical analysis of network data (opens in a new tab)

  3. Kernel Machines are Not Black Boxes - On the Interpretability of Kernel-based Nonparametric Models

    … is however questionable; permutation-based variable importance, for example, is one approach for interpreting various nonparametric models. Unfortunately, besides being computationally intensive, permutation-based variable importance is merely a predictor importance measure for supervised …

    toronto-retro Repository record for Kernel Machines are Not Black Boxes - On the Interpretability of Kernel-based Nonparametric Models (opens in a new tab)

  4. Three Essays on the Interpretability of Random Forests: Methods, Insights, and Innovations

    … of interaction for each research area. The variable importance of random forests is an easy-to-understand metric that intends to make the predictions of random forests more transparent by assessing the contribution of each covariate to the prediction of the response. However, due to its …

    passau-thes Repository record for Three Essays on the Interpretability of Random Forests: Methods, Insights, and Innovations (opens in a new tab)

  5. Informing decision-making in single-objective, mixed-variable design problems

    Data-driven decision-making in mixed-variable design problems presents a variety of challenges and opportunities, especially in the increasingly data-rich field of emissions in architectural and structural design. Designers can benefit from an underlying knowledge about, for example, whether …

    mit Repository record for Informing decision-making in single-objective, mixed-variable design problems (opens in a new tab)

  6. Random survival forests: quantifying uncertainties and other extensions

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-15 without embargo terms

    uiuc Repository record for Random survival forests: quantifying uncertainties and other extensions (opens in a new tab)

  7. Causal Effect Random Forest Of Interaction Trees For Learning Individualized Treatment Regimes In Observational Studies: With Applications To Education Study Data

    … For all treatment settings, the CERFIT provides variable importance ranking in terms of treatment effects. Extensive simulation studies for assessing estimation accuracy and variable importance ranking are presented. CERFIT demonstrates competitive performance among all competing methods in …

    claremont Repository record for Causal Effect Random Forest Of Interaction Trees For Learning Individualized Treatment Regimes In Observational Studies: With Applications To Education Study Data (opens in a new tab)

  8. Essays on Model Selection Uncertainty and Model Averaging: Computational and Empirical Work with Beta Regression, Multiple Linear Regression with ARMA Innovations, and the Minimum Description Length Principle

    … more accurate claims of estimate precision, variable importance, and model stability. Utility of the tool was demonstrated through a study of model selection consistency and variable importance in clickstream data. In Chapter 3, model averaging to improve model qualityin the context of time …

    ku Repository record for Essays on Model Selection Uncertainty and Model Averaging: Computational and Empirical Work with Beta Regression, Multiple Linear Regression with ARMA Innovations, and the Minimum Description Length Principle (opens in a new tab)

  9. Comparison of growth curve models for assessing height in a South African birth cohort

    … compared to a random forest model. Methods for variable importance in classification problems using tree-based methods were explored. The random forest model appeared to perform similarly to the logistic regression model in terms of predictive power and variable interpretation. This dissertation …

    cape-town Repository record for Comparison of growth curve models for assessing height in a South African birth cohort (opens in a new tab)

  10. Developing a Data-Driven Strategy for In-Process Quality Assurance for Additive Manufacturing

    … are achieved for each quality test. First, input variable importance is quantified, enabling a deeper understanding of the significance of each leveraged data set in predicting quality. Second, models are designed to enable a double-digit percent reduction in testing volumes, enabling cost savings …

    mit Repository record for Developing a Data-Driven Strategy for In-Process Quality Assurance for Additive Manufacturing (opens in a new tab)

  11. Incorporating Climate Sensitivity for Southern Pine Species into the Forest Vegetation Simulator

    … such as receiver operating curves (ROC) and variable importance plots were examined to assess model performance. Presence-absence classification models had out-of-bag error rates ranging from 6.32% to 16.06%, and areas under ROC curves ranging from 0.92-0.98. Regression models explained …

    vt Repository record for Incorporating Climate Sensitivity for Southern Pine Species into the Forest Vegetation Simulator (opens in a new tab)

  12. An evaluation of a data-driven approach to regional scale surface runoff modelling

    … of one another. Accuracy statistics and variable importance measures from the random forest algorithm reveal that precipitation was the most important variable to the model, but including climatological data from multiple months as predictors significantly improves the model performance. …

    vt Repository record for An evaluation of a data-driven approach to regional scale surface runoff modelling (opens in a new tab)

  13. Integrating Digital Aerial Photography and Lidar-Derived Information For Object-Based Coastal Tidal Marsh Classification Using Tree-Based Ensemble Algorithms

    … with segmentation scales <= 40. A feature importance analysis indicated that both Random Forest and Adaboost tree considered LiDAR altimetry and intensity information as important variables, although Adaboost gave them higher variable importance ranks. This research contributes to better …

    south-carolina Repository record for Integrating Digital Aerial Photography and Lidar-Derived Information For Object-Based Coastal Tidal Marsh Classification Using Tree-Based Ensemble Algorithms (opens in a new tab)

  14. Applications of Machine Learning and First-Principle Modeling to Evaluate Design Enhancements in Autoinjectors

    … like partial dependence and permutation variable importance charts to enhance the understanding of results generated by a machine learning model.

    mit Repository record for Applications of Machine Learning and First-Principle Modeling to Evaluate Design Enhancements in Autoinjectors (opens in a new tab)

  15. Data-Driven Modeling of the Lake Chad Basin Hydrologic Systems

    … is intended to identify the main climate variables affecting river discharge, lake level, and groundwater level fluctuations and to create data-driven models to predict them by using remote sensing climate data. The climate variables employed for this study are air temperature, …

    umkc Repository record for Data-Driven Modeling of the Lake Chad Basin Hydrologic Systems (opens in a new tab)

  16. A Machine Learning Model for Octane Number Prediction

    … the data frame was small, with only 12 input variables and 350 observations. Prior to training the models, an Explanatory Data Analysis was carried out to assess the potential dimensionality reduction, correlations and outliers. The final regression model was the interaction model with a test …

    cape-town Repository record for A Machine Learning Model for Octane Number Prediction (opens in a new tab)

  17. Analisador virtual para a determinação do teor dos contaminantes mapd em um reator tricklebed

    … variáveis utilizando o gráfico de escores VIP (Variable Importance in Projection) obtido durante o desenvolvimento dos modelos PLS. As variáveis mais importantes foram selecionadas e os modelos PLS construídos apenas com essas variáveis mantiveram a capacidade de predição em ambos os leitos, com …

    brazil-ufba Repository record for Analisador virtual para a determinação do teor dos contaminantes mapd em um reator tricklebed (opens in a new tab)

  18. Penalised regression for high-dimensional data: an empirical investigation and improvements via ensemble learning

    … datasets are generated for which the number of variables p exceeds the sample size n. Penalised likelihood methods are widely used to tackle regression problems in these high-dimensional settings. In this thesis, we carry out an extensive empirical comparison of the performance of popular …

    cambridge Repository record for Penalised regression for high-dimensional data: an empirical investigation and improvements via ensemble learning (opens in a new tab)

  19. Facilitating golden mole conservation in South African highland grasslands : a predictive modelling approach

    … based on interpolated data for 19 bioclimatic variables, continuous altitude data, as well as categorical spatial data for landtypes, WWF ecoregions and vegetation types. These initial models helped to effectively focus survey efforts within a vast study area, with surveying during the austral …

    cape-town Repository record for Facilitating golden mole conservation in South African highland grasslands : a predictive modelling approach (opens in a new tab)

  20. Physics-Informed Interpretable Attention-based Machine Learning for Jet Turbine Prediction

    … into time horizon attention and model-discovered variable importance. While there is further exploration in the extent of robustness and accuracy of physics-informed attention networks, we expect this approach to lead to models with reduced training time, higher accuracy, increased user confidence …

    vt Repository record for Physics-Informed Interpretable Attention-based Machine Learning for Jet Turbine Prediction (opens in a new tab)

Page 1 of 2