Thresholding Approach for Low-Rank Correlation Matrix based on MM algorithm

Background: Low-rank approximation is a very useful approach for interpreting the features of a correlation matrix; however, a low-rank approximation may result in estimation far from zero even if the corresponding original value was far from zero. In this case, the results lead to misinterpretation. Methods: To overcome these problems, we propose a new approach to estimate a sparse low-rank correlation matrix based on threshold values combined with cross-validation. In the proposed approach, the MM algorithm was used to estimate the sparse low-rank correlation matrix, and a grid search was performed to select the threshold values related to sparse estimation. Results: Through numerical simulation, we found that the FPR and average relative error of the proposed method were superior to those of the tandem approach. For the application of microarray gene expression, the FPRs of the proposed approach with d=2,3, and 5 were 0.128, 0.139, and 0.197, respectively, while FPR of the tandem approach was 0.285. Conclusions: We propose a novel approach to estimate sparse low-rank correlation matrix. The advantage of the proposed method is that it provides results that are easy to interpret and avoid misunderstandings. We demonstrated the superiority of the proposed method through both numerical simulations and real examples.

Tutorial on the Use of the regsem Package in R

Sparse estimation through regularization is gaining popularity in psychological research. Such techniques penalize the complexity of the model and could perform variable/path selection in an automatic way, and thus are particularly useful in models that have small parameter-to-sample-size ratios. This paper gives a detailed tutorial of the R package regsem, which implements regularization for structural equation models. Example R code is also provided to highlight the key arguments of implementing regularized structural equation models in this package. The tutorial ends by discussing remedies of some known drawbacks of a popular type of regularization, computational methods supported by the package that can improve the selection result, and some other practical issues such as dealing with missing data and categorical variables.

Advanced Processing of a Blade Vibratory Response Obtained With Tip Timing Method Using Hyperparameter-Free Sparse Estimation Method

The study presents the application of a sparse estimation method which enables explicit identification of spectrum components of a vibratory signal of a blade obtained by means of blade tip timing measurement. The method exploits the sparse frequency content of the blade vibratory response and uses a data-adaptive weighting to achieve sparsity. In contrast to other approaches, this method obviates the need for any parameter tuning during the identification process and admits an online formulation that renders it capable of real-time data processing. In the study only experimentally acquired data from either prototype testing or field measurements are used to evoke the method applicability. For some considered test cases there were no strain gauges available, therefore proposed method was the only means to study blades vibratory response.

Efficient sparse estimation on interval-censored data with approximated L0 norm: Application to child mortality

A novel penalty for the proportional hazards model under the interval-censored failure time data structure is discussed, with which the subject of variable selection is rarely studied. The penalty comes from an idea to approximate some information criterion, e.g., the BIC or AIC, and the core process is to smooth the ℓ0 norm. Compared with usual regularization methods, the proposed approach is free of heavily time-consuming hyperparameter tuning. The efficiency is further improved by fitting the model and selecting variables in one step. To achieve this, sieve likelihood is introduced, which simultaneously estimates the coefficients and baseline cumulative hazards function. Furthermore, it is shown that the three desired properties for penalties, i.e., continuity, sparsity, and unbiasedness, are all guaranteed. Numerical results show that the proposed sparse estimation method is of great accuracy and efficiency. Finally, the method is used on data of Nigerian children and the key factors that have effects on child mortality are found.