On the impact of predictor geometry on the performance on high-dimensional ridge-regularized generalized robust regression estimators

We extend the mean empirical likelihood inference for response mean with data missing at random. The empirical likelihood ratio confidence regions are poor when the response is missing at random, especially when the covariate is high-dimensional and the sample size is small. Hence, we develop three bias-corrected mean empirical likelihood approaches to obtain efficient inference for response mean. As to three bias-corrected estimating equations, we get a new set by producing a pairwise-mean dataset. The method can increase the size of the sample for estimation and reduce the impact of the dimensional curse. Consistency and asymptotic normality of the maximum mean empirical likelihood estimators are established. The finite sample performance of the proposed estimators is presented through simulation, and an application to the Boston Housing dataset is shown.

Download Full-text

Business strategy, performance appraisal and organizational results

Personnel Review ◽

10.1108/pr-09-2019-0498 ◽

2020 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Alberto Bayo-Moriones ◽

Jose Enrique Galdon-Sanchez ◽

Sara Martinez-de-Morentin

Keyword(s):

Firm Performance ◽

Human Resources ◽

Performance Appraisal ◽

Competitive Strategy ◽

Management Practices ◽

Robust Regression ◽

Innovation Strategy ◽

Content Type ◽

The Impact ◽

Developmental Performance

PurposeThe purpose of this study is to analyze how the design of performance appraisal is influenced by the competitive strategy of the firm. Then, this paper examines if the alignment between appraisal and strategy impacts firm performance.Design/methodology/approachThe study sample includes 258 Spanish firms in the manufacturing and services sectors. This information was gathered through questionnaires addressed to the CEO and the senior human resources manager. Several econometric models are estimated, using robust regression analysis and including a set of relevant control variables.FindingsA positive relationship is found between an innovation strategy and developmental performance appraisal. A cost strategy has a negative impact on the adoption of developmental performance appraisal. The findings also confirm that firms with a quality strategy and developmental appraisal have higher performance. In addition, firms adopting an innovation strategy and administrative appraisal enjoy higher return of equity.Research limitations/implicationsFuture research should analyze the dynamics of the relationships between appraisal, strategy and performance to rule out the flaws of cross-sectional data. Another potential extension is the analysis of the interactions of the design of other human resources management practices with both competitive strategy and firm performance.Practical implicationsFirms can improve performance by aligning performance appraisal design with strategy. Those with an innovation strategy should choose administrative appraisal, and those competing on quality should focus on developmental appraisal.Originality/valueThis paper compares the theoretical recommendations on performance appraisal for different competitive strategies, what firms actually do, and the impact that the alignment between appraisal and strategy has on firm performance.

Download Full-text

Specification tests for covariance structures in high-dimensional statistical models

Biometrika ◽

10.1093/biomet/asaa073 ◽

2020 ◽

Author(s):

X Guo ◽

C Y Tang

Keyword(s):

Statistical Models ◽

Nuisance Parameter ◽

Additive Model ◽

Covariance Structure ◽

Real Data ◽

Theoretical Development ◽

High Dimensional ◽

Test Statistics ◽

Estimation Errors ◽

The Impact

Summary We consider testing the covariance structure in statistical models. We focus on developing such tests when the random vectors of interest are not directly observable and have to be derived via estimated models. Additionally, the covariance specification may involve extra nuisance parameters which also need to be estimated. In a generic additive model setting, we develop and investigate test statistics based on the maximum discrepancy measure calculated from the residuals. To approximate the distributions of the test statistics under the null hypothesis, new multiplier bootstrap procedures with dedicated adjustments that incorporate the model and nuisance parameter estimation errors are proposed. Our theoretical development elucidates the impact due to the estimation errors with high-dimensional data and demonstrates the validity of our tests. Simulations and real data examples confirm our theory and demonstrate the performance of the proposed tests.

Download Full-text