A practical approach to spatio-temporal analysis

Jiang, Huijing; Schoergendorfer, Angela; Hwang, Youngdeok; Amemiya, Yasuo

doi:10.5705/ss.2013.262w

Cited by 5 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar problems are easily found in industrial applications, as the problem of prediction using real measurements at monitoring sensors and computer model outputs covering the entire domain is prevalent. For those problems, the overall goal is often managing a large complex system, such as micro-climate within a facility [Jiang et al (2015)] or environmental monitoring [Liu et al (2016)].…”

Section: Global Horizontal Irradiancementioning

confidence: 99%

“…These computer models have been extensively used in the service industry, in particular, to predict or simulate the environmental variables in various scales. For example, Jiang et al (2015) considered a computer model to simulate the data center thermal system, and Klein et al (2015) discussed a general platform to take advantage of various environmental models to develop predictive tools in industry.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Bottom-Up Estimation and Top-Down Prediction: Solar Energy Prediction Combining Information from Multiple Sources

Hwang¹,

Lu²,

Kim³

2018

ICSA Book Series in Statistics

Self Cite

View full text Add to dashboard Cite

Accurately forecasting solar power using the data from multiple sources is an important but challenging problem. Our goal is to combine two different physics model forecasting outputs with real measurements from an automated monitoring network so as to better predict solar power in a timely manner. To this end, we propose a new approach of analyzing large-scale multilevel models with great computational efficiency requiring minimum monitoring and intervention. This approach features a division of the large scale data set into smaller ones with manageable sizes, based on their physical locations, and fit a local model in each area. The local model estimates are then combined sequentially from the specified multilevel models using our novel bottom-up approach for parameter estimation. The prediction, on the other hand, is implemented in a top-down matter. The proposed method is applied to the solar energy prediction problem for the U.S.

show abstract

Section: Global Horizontal Irradiancementioning

confidence: 99%

mentioning

confidence: 99%

Bottom-Up Estimation and Top-Down Prediction: Solar Energy Prediction Combining Information from Multiple Sources

Hwang¹,

Lu²,

Kim³

2018

ICSA Book Series in Statistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Being able to build the right model for g t (s) largely determines whether the spatio-temporal variation of the ozone concentrations can be accurately predicted. In fact, sophisticated treatment of the random component Z t (s) might not yield a substantial payoff for prediction accuracy [12]. We model g t (s) as a linear function of five predictors as follows:…”

Section: The Deterministic Spatio-temporal Trendmentioning

confidence: 99%

“…Following the idea of [12], the spatio-temporal process in equation 1, Z t (s), is modeled as an autoregressive (AR) model of order L…”

Section: The Deterministic Spatio-temporal Trendmentioning

confidence: 99%

“…In fact, such commonly made assumptions may not even be validated using statistical approaches unless data arise from a large number of air quality monitoring stations [11]. To relax such limitations, this study employs a spatio-temporal prediction framework recently developed by researchers from IBM Watson Research Center [12]. Our study shows that this framework can effectively model ozone concentration and well balances the complexity and the practicality of a spatio-temporal prediction approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A statistical model for 1-hour- to 24-hour-ahead prediction of hourly ozone concentrations at ground level in Singapore

Liu¹,

Hwang²,

Yeo³

et al. 2014

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

A spatio-temporal statistical model is proposed for 1-to 24-hour-ahead prediction of hourly ozone concentrations. This is a joint work with the National Environmental Agency Singapore, and is Singapore's first predictive model for ozone concentrations. Unlike many existing models which focus on either daily maximum or 8h average daylight ozone concentrations, the present work is concerned with the prediction of hourly ozone concentrations which are usually associated with higher variability. A recently proposed framework for spatiotemporal prediction is used to model ozone concentration data. The macroscale spatio-temporal variation of ozone concentrations is modeled by a linear function of five carefully constructed predictors, while the micro-scale variation is captured by a mean-zero spatio-temporally correlated random process. We show that this model also provides useful insights about the effects of some complex environmental processes on ozone concentration; this is indeed an attractive feature for any data-driven air quality model.

show abstract

A Novel Penalized Inverse-Variance Weighted Estimator for Mendelian Randomization with Applications to COVID-19 Outcomes

Wang

Fung

et al. 2022

Biometrics

View full text Add to dashboard Cite

Mendelian randomization utilizes genetic variants as instrumental variables (IVs) to estimate the causal effect of an exposure variable on an outcome of interest even in the presence of unmeasured confounders. However, the popular inverse‐variance weighted (IVW) estimator could be biased in the presence of weak IVs, a common challenge in MR studies. In this article, we develop a novel penalized inverse‐variance weighted (pIVW) estimator, which adjusts the original IVW estimator to account for the weak IV issue by using a penalization approach to prevent the denominator of the pIVW estimator from being close to zero. Moreover, we adjust the variance estimation of the pIVW estimator to account for the presence of balanced horizontal pleiotropy. We show that the recently proposed debiased IVW (dIVW) estimator is a special case of our proposed pIVW estimator. We further prove that the pIVW estimator has smaller bias and variance than the dIVW estimator under some regularity conditions. We also conduct extensive simulation studies to demonstrate the performance of the proposed pIVW estimator. Furthermore, we apply the pIVW estimator to estimate the causal effects of five obesity‐related exposures on three coronavirus disease 2019 (COVID‐19) outcomes. Notably, we find that hypertensive disease is associated with an increased risk of hospitalized COVID‐19; and peripheral vascular disease and higher body mass index are associated with increased risks of COVID‐19 infection, hospitalized COVID‐19, and critically ill COVID‐19.

show abstract

A practical approach to spatio-temporal analysis

Cited by 5 publications

References 22 publications

Bottom-Up Estimation and Top-Down Prediction: Solar Energy Prediction Combining Information from Multiple Sources

Bottom-Up Estimation and Top-Down Prediction: Solar Energy Prediction Combining Information from Multiple Sources

A statistical model for 1-hour- to 24-hour-ahead prediction of hourly ozone concentrations at ground level in Singapore

A Novel Penalized Inverse-Variance Weighted Estimator for Mendelian Randomization with Applications to COVID-19 Outcomes

Contact Info

Product

Resources

About