Jianguo Sun

Bio: Jianguo Sun is an academic researcher from University of Missouri. The author has contributed to research in topics: Regression analysis & Nonparametric statistics. The author has an hindex of 35, co-authored 257 publications receiving 4195 citations. Previous affiliations of Jianguo Sun include University of Maryland, College Park & University of Waterloo.

The Statistical Analysis of Interval-censored Failure Time Data

Abstract: Inference for Parametric Models and Imputation Approaches.- Nonparametric Maximum Likelihood Estimation.- Comparison of Survival Functions.- Regression Analysis of Current Status Data.- Regression Analysis of Case II Interval-censored Data.- Analysis of Bivariate Interval-censored Data.- Analysis of Doubly Censored Data.- Analysis of Panel Count Data.- Other Topics.

Hydroxyl-Dependent Evolution of Oxygen Vacancies Enables the Regeneration of BiOCl Photocatalyst

Abstract: Photoinduced oxygen vacancies (OVs) are widely investigated as a vital point defect in wide-band-gap semiconductors. Still, the formation mechanism of OVs remains unclear in various materials. To elucidate the formation mechanism of photoinduced OVs in bismuth oxychloride (BiOCl), we synthesized two surface hydroxyl discrete samples in light of the discovery of the significant variance of hydroxyl groups before and after UV light exposure. It is noted that OVs can be obtained easily after UV light irradiation in the sample with surface hydroxyl groups, while variable changes were observed in samples without surface hydroxyls. Density functional theory (DFT) calculations reveal that the binding energy of Bi–O is drastically influenced by surficial hydroxyl groups, which is intensely correlated to the formation of photoinduced OVs. Moreover, DFT calculations reveal that the adsorbed water molecules are energetically favored to dissociate into separate hydroxyl groups at the OV sites via proton transfer to a...

Stepwise Electrocatalysis as a Strategy against Polysulfide Shuttling in Li–S Batteries

Abstract: Most issues with Li-S batteries are caused by the slowness of the multielectron sulfur electrochemical reaction resulting in the loss of sulfur as soluble polysulfides to the electrolyte and the redox shuttling of polysulfides between the cathode and anode during battery charge and discharge. The acceleration of the polysulfide conversion reaction to their end products via electrocatalysis has the appeal of a root-cause solution. However, the polysulfide electrocatalysts developed to date have rarely considered polysulfide conversion as a multistep reaction and, as such, were not optimized to target specific steps in the overall S8 ↔ Li2Sn ↔ Li2S conversion. The targeting approach is however beneficial, as it can be used to design multicatalyst systems to reduce as many rate-limiting steps in the overall catalysis as effectively possible. This article demonstrates the concept and implementation of stepwise electrocatalysis in polysulfide conversion, using Fe-N and Co-N co-doped carbons to selectively catalyze the long-chain polysulfide conversion (S8 ↔ Li2S4) and the short-chain polysulfide conversion reactions (Li2S4 ↔ Li2S), respectively. The two electrocatalysts were deployed in the sulfur cathode as a dual layer, using an ordered spatial separation to synergize their catalytic effects. A sulfur electrode designed as such could utilize ∼90% of the sulfur theoretical specific capacity and support a high areal capacity of ∼8.3 mAh cm-2 and a low electrolyte/sulfur ratio of 5 μL mg-1.

A non-parametric test for interval-censored failure time data with application to AIDS studies.

Abstract: Interest often centres on the comparison of failure time distributions based on interval-censored failure time data such as in the work by Finkelstein, in which she proposed a score test under continuous proportional hazards model. In this article, we consider a different situation in which the underlying failure time is a discrete variable or the observed times correspond with a discrete scale. To compare failure time distributions in these situations, we propose a non-parametric test, a generalization of the usual logrank test for right-censored failure time data. Simulation results indicate that the test performs satisfactorily.

A correlation principal component regression analysis of NIR data

Abstract: The use of principal component regression (PCR) as a multivariate calibration method has been discussed by a number of authors. In most situations principal components are included in the regression model in sequence based on the variances of the components, and the principal components with small variances are rarely used in regression. As pointed out by some authors, a low variance for a component does not necessarily imply that the corresponding component is unimportant, especially when prediction is of primary interest. In this paper we investigate a different version of PCR, correlation principal component regression (CPCR). In CPCR the importance of principal components in terms of predicting the response variable is used as a basis for the inclusion of principal components in the regression model. Two typical examples arising from calibrating near-infrared (NIR) instruments are discussed for the comparison of the two different versions of PCR along with partial least squares (PLS), a commonly used regression approach in NIR analysis. In both examples the three methods show similar optimal prediction ability, but CPCR performs better than standard PCR and PLS in terms of the number of components needed to achieve the optimal prediction ability. Similar results are also seen in other NIR examples.

Flexible Imputation of Missing Data

Abstract: Basics Introduction The problem of missing data Concepts of MCAR, MAR and MNAR Simple solutions that do not (always) work Multiple imputation in a nutshell Goal of the book What the book does not cover Structure of the book Exercises Multiple imputation Historic overview Incomplete data concepts Why and when multiple imputation works Statistical intervals and tests Evaluation criteria When to use multiple imputation How many imputations? Exercises Univariate missing data How to generate multiple imputations Imputation under the normal linear normal Imputation under non-normal distributions Predictive mean matching Categorical data Other data types Classification and regression trees Multilevel data Non-ignorable methods Exercises Multivariate missing data Missing data pattern Issues in multivariate imputation Monotone data imputation Joint Modeling Fully Conditional Specification FCS and JM Conclusion Exercises Imputation in practice Overview of modeling choices Ignorable or non-ignorable? Model form and predictors Derived variables Algorithmic options Diagnostics Conclusion Exercises Analysis of imputed data What to do with the imputed data? Parameter pooling Statistical tests for multiple imputation Stepwise model selection Conclusion Exercises Case studies Measurement issues Too many columns Sensitivity analysis Correct prevalence estimates from self-reported data Enhancing comparability Exercises Selection issues Correcting for selective drop-out Correcting for non-response Exercises Longitudinal data Long and wide format SE Fireworks Disaster Study Time raster imputation Conclusion Exercises Extensions Conclusion Some dangers, some do's and some don'ts Reporting Other applications Future developments Exercises Appendices: Software R S-Plus Stata SAS SPSS Other software References Author Index Subject Index

Orthogonal projections to latent structures (O-PLS)

Abstract: A generic preprocessing method for multivariate data, called orthogonal projections to latent structures (O-PLS), is described. O-PLS removes variation from X (descriptor variables) that is not correlated to Y (property variables, e.g. yield, cost or toxicity). In mathematical terms this is equivalent to removing systematic variation in X that is orthogonal to Y. In an earlier paper, Wold et al. (Chemometrics Intell. Lab. Syst. 1998; 44: 175-185) described orthogonal signal correction (OSC). In this paper a method with the same objective but with different means is described. The proposed O-PLS method analyzes the variation explained in each PLS component. The non-correlated systematic variation in X is removed, making interpretation of the resulting PLS model easier and with the additional benefit that the non-correlated variation itself can be analyzed further. As an example, near-infrared (NIR) reflectance spectra of wood chips were analyzed. Applying O-PLS resulted in reduced model complexity with preserved prediction ability, effective removal of non-correlated variation in X and, not least, improved interpretational ability of both correlated and non-correlated variation in the NIR spectra.

Applied Longitudinal Data Analysis for Epidemiology: A Practical Guide

Abstract: This book discusses the most important techniques available for longitudinal data analysis, from simple techniques such as the paired t-test and summary statistics, to more sophisticated ones such as generalized estimating of equations and mixed model analysis A distinction is made between longitudinal analysis with continuous, dichotomous and categorical outcome variables The emphasis of the discussion lies in the interpretation and comparison of the results of the different techniques The second edition includes new chapters on the role of the time variable and presents new features of longitudinal data analysis Explanations have been clarified where necessary and several chapters have been completely rewritten The analysis of data from experimental studies and the problem of missing data in longitudinal studies are discussed Finally, an extensive overview and comparison of different software packages is provided This practical guide is essential for non-statisticians and researchers working with longitudinal data from epidemiological and clinical studies