Efficient Variable Screening for Multivariate Analysis

Silva, A. Pedro Duarte

doi:10.1006/jmva.2000.1920

Cited by 33 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We have followed the guidelines of Cadima and colleagues (2004) and used the GCD criterion. Given the small size of data set, it is advisable to use the Furnival‐Wilson‐type algorithm (Duarte Silva 2001, 2002), which ensures that the solution produced is optimal. Note that as the number ( k ) of variables selected increases, so does the percentage of variance explained.…”

Section: Application Of Proposed Approach To Waste Electrical and Elementioning

confidence: 99%

Dimensionality Reduction and Visualization of the Environmental Impacts of Domestic Appliances

Gutiérrez¹,

Lozano²,

Adenso‐Díaz³

2010

J of Industrial Ecology

View full text Add to dashboard Cite

show abstract

Section: Application Of Proposed Approach To Waste Electrical and Elementioning

confidence: 99%

Dimensionality Reduction and Visualization of the Environmental Impacts of Domestic Appliances

Gutiérrez¹,

Lozano²,

Adenso‐Díaz³

2010

J of Industrial Ecology

View full text Add to dashboard Cite

show abstract

“…A consolidated approach to input selection in linear regression problems is to use Branch and Bound algorithms, such as Leaps and Bounds (Furnival & Wilson, 1974) or its more recent variants (Duarte Silva, 2001, 2002). These algorithms are conceived to balance goodness‐of‐fit with model simplicity.…”

Section: Reconstruction Frameworkmentioning

confidence: 99%

Multi‐Proxy, Multi‐Season Streamflow Reconstruction With Mass Balance Adjustment

Nguyen

Galelli

et al. 2021

Water Resources Research

View full text Add to dashboard Cite

Despite having offered important hydroclimatic insights, streamflow reconstructions still see limited use in water resources operations, because annual reconstructions are not suitable for decisions at finer time scales. The few attempts toward sub‐annual reconstructions have relied on statistical disaggregation, which uses none or little proxy information. Here, we develop a novel framework that optimizes proxy combinations to simultaneously produce seasonal and annual reconstructions. Importantly, the framework ensures that total seasonal flow matches annual flow closely. This mass balance criterion is necessary to avoid misguiding water management decisions, such as the allocation of water rights or dam release decisions. Using the framework, and leveraging a multi‐species network of ring width and cellulose δ18O in Southeast Asia, we reconstruct seasonal and annual inflow to Thailand's largest reservoir. The reconstructions are statistically skillful. Furthermore, they preserve the mass balance well: the differences are mostly within 10% of the mean annual flow. As a result, the reconstructions provide more reliable estimates of the seasonal and annual surface water availability. This work is one step closer toward operational usability of streamflow reconstruction in water resources management.

show abstract

“…A consolidated approach to input selection in linear regression problems is to use Branch and Bound algorithms, such as Leaps and Bounds (Furnival & Wilson, 1974) or its more recent variants (Duarte Silva, 2001. These algorithms are conceived to balance goodness-of-fit with model simplicity.…”

Section: Optimal Input Selectionmentioning

confidence: 99%

Multi-Proxy, Multi-Season Streamflow Reconstruction with Mass Balance Adjustment

Nguyen

Galelli

et al. 2020

Preprint

View full text Add to dashboard Cite

Dendrohydrology, the study of past hydroclimate using tree rings, has been largely motivated by water resources management. The field traces back to Hardman and Reil (1936), who recognized that instrumental records were too short to understand drought trends and demonstrated that better understanding could be gained from exploring the links between tree rings and streamflow. Their work was motivated by contemporary droughts in California that affected irrigation. At the same time, Hawley (1937) found strong correlations between tree rings and streamflow in Tennessee, USA, and was probably the first to show the lagged relationship of streamflow to tree rings. Also to understand droughts, Schulman (1945) established a tree ring chronology for the Colorado River Basin, this time motivated by the war effort-to examine Hoover Dam's hydropower production reliability to meet wartime demand. While these early works stopped at studying tree ring indices, dendrohydrology took a big step when Stockton (1971), leveraging advanced multivariate techniques (Fritts et al., 1971), showed that reconstructing streamflow record back in time was feasible-long term surface water availability could now be quantified directly. Soon, multiple streamflow reconstructions were developed across the Colorado River Basin (Stockton & Jacoby, 1976), revealing the

show abstract

Efficient Variable Screening for Multivariate Analysis

Cited by 33 publications

References 21 publications

Dimensionality Reduction and Visualization of the Environmental Impacts of Domestic Appliances

Dimensionality Reduction and Visualization of the Environmental Impacts of Domestic Appliances

Multi‐Proxy, Multi‐Season Streamflow Reconstruction With Mass Balance Adjustment

Multi-Proxy, Multi-Season Streamflow Reconstruction with Mass Balance Adjustment

Contact Info

Product

Resources

About