Weighted Likelihood Estimation Research Articles

Variable selection using inverse probability of censoring weighting.

In this article, we propose two variable selection methods for adjusting the censoring information for survival times, such as the restricted mean survival time. To adjust for the influence of censoring, we consider an inverse probability of censoring weighted for subjects with events. We derive a least absolute shrinkage and selection operator (lasso)-type variable selection method, which considers an inverse weighting for of the squared losses, and an information criterion-type variable selection method, which applies an inverse weighting of the survival probability to the power of each density function in the likelihood function. We prove the consistency of the inverse probability of censoring weighted lasso estimator and the maximum inverse probability of censoring weighted likelihood estimator. The performance of the inverse probability of censoring weighted lasso and inverse probability of censoring weighted information criterion are evaluated via a simulation study with six scenarios, and then their variable selection ability is demonstrated using data from two clinical studies. The results confirm that inverse probability of censoring weighted lasso and the inverse probability of censoring weighted likelihood function produce good estimation accuracy and consistent variable selection. We conclude that our two proposed methods are useful variable selection tools for adjusting the censoring information for survival time analyses.

Telenursing: The view of care professionals in selected EU countries. A pilot study

BackgroundWith the growth of digital nursing, several studies have focused on recording patients' views on remote care, or specialised nurse staffing aspects. This is the first international survey on telenursing focused exclusively on clinical nurses that analyses the dimensions of usefulness, acceptability, and appropriateness of telenursing from the staff point of view. MethodsA previously validated structured questionnaire including demographic variables, 18 responses with a Likert-5 scale, three dichotomous questions, and one overall percentual estimation of holistic nursing care susceptible to being undertaken by telenursing, was administered (from 1 September to 30 November 2022) to 225 clinical and community nurses from three selected EU countries. Data analysis: descriptive data, classical and Rasch testing. ResultsThe results show adequacy of the model for measurement of the domains of usefulness, acceptability, and appropriateness of telenursing (overall Cronbach's alpha 0.945, Kaiser-Meyer-Olkin 0.952 and Bartlett's p < 0.001). Answers in favour of telenursing ranked 4 out of 5 in Likert scale, both globally and by the three domains. Rasch: reliability coefficient 0.94, Warm's main weighted likelihood estimate reliability 0.95. In the ANOVA analysis, the results for Portugal were significantly higher than those for Spain and Poland, both overall and for each of the dimensions. Respondents with bachelor's, master's and doctoral degrees score significantly higher than those with certificates or diplomas. Multiple regression did not yield additional data of interest. ConclusionsThe tested model proved to be valid, but although the majority of nurses are in favour of telenursing, given the nature of the care, which is mainly face-to-face, according to the respondents, the chances of carrying out their activities by telenursing is only 35.3%. The survey provides useful information on what can be expected from the implementation of telenursing and the questionnaire proves to be a useful tool to be applied in other countries.

Maximum weighted likelihood estimator for robust heavy-tail modelling of finite mixture models

Insurance claim severity data are characterized by complex distributional phenomenons, where flexible density estimation tools such as the finite mixture models (FMM) are necessary. However, maximum likelihood estimations (MLE) often produce unstable tail estimates for the FMM. Motivated by this challenge, this article presents a maximum weighted likelihood estimator (MWLE) for robust estimations of heavy-tailed FMM. Under some regularity conditions, the proposed MWLE is consistent and asymptotically normal. Since the MWLE has a probabilistic interpretation, we are able to develop two distinctive versions of the Generalized Expectation-Maximization (GEM) algorithm to estimate the MWLE parameters more efficiently and reliably than the standard gradient-based algorithms. We apply the proposed MWLE to two simulation studies and a real motor insurance dataset to demonstrate that it better extrapolates the extreme losses than the MLE, without sacrificing the flexibility of the FMM in capturing the small attritional claims.

Validation of a New Telenursing Questionnaire: Testing the Test

Background: Existing surveys on telenursing refer to specific areas of nursing after the implementation of a programme, but telenursing in general has not been fully evaluated from a prospective approach. Aim: Design and statistical validation of a telenursing questionnaire. Methods: A new questionnaire was designed with 18 paired (to avoid leading) questions (Likert-5) plus three dichotomous questions (randomly ordered, inspired by existing validated tests) to analyse the dimensions of: acceptance, usefulness and appropriateness of telenursing from the nursing point of view (7 min test). The questionnaire was validated by classical tests and item response tests (Rasch) using six computer-generated databases with different response profiles (tendency to be positioned against, neutral and positioned in favour) with two degrees of agreement between each pair of responses for each option. Results: Classical testing: Cronbach’s alphas (from 0.8 to 0.95), Kaiser–Meyer–Olkin (KMO) (0.93 to 0.95) and a significant p &lt; 0.0001 for Bartlett’s test of sphericity were obtained. Rasch analysis: Reliability coefficients (0.94). Warm’s mean weighted likelihood estimates (0.94). Extreme infit-t and outfit-t values (+1.61 to −1.98). Conclusions: Both the classical test and the Rasch approaches confirm the usefulness of the new test for assessing nurses’ positioning in relation to telenursing.

RID-Noise: Towards Robust Inverse Design under Noisy Environments

From an engineering perspective, a design should not only perform well in an ideal condition, but should also resist noises. Such a design methodology, namely robust design, has been widely implemented in the industry for product quality control. However, classic robust design requires a lot of evaluations for a single design target, while the results of these evaluations could not be reused for a new target. To achieve data-efficient robust design, we propose Robust Inverse Design under Noise (RID-Noise), which can utilize existing data to train a conditional invertible neural network. Specifically, we estimate the robustness of a design parameter by its predictability, measured by the prediction error of a forward neural network. We also define a sample-wise weight, which can be used in the maximum weighted likelihood estimation of an inverse model based on a conditional invertible neural network. With the visual results from experiments, we clearly justify how RID-Noise works by learning the distribution and robustness from data. Further experiments on several real-world benchmark tasks with noises confirm that our method is more effective than other state-of-the-art inverse design methods. Code and supplementary is publicly available at https://github.com/ThyrixYang/rid-noise-aaai22

Effects of Opportunities to Learn on Peruvian Students’ Science Achievement in Program for International Student Assessment 2015

Opportunities to learn (OTL) are considered important variables to enable equitable educational standards in teaching. The main objective of this work was to test a five-level hierarchical model to explain the general achievement and science competencies of Peruvian students in the Program for International Student Assessment (PISA) 2015, controlling for the student’s age and gender, and the economic, social, and cultural status, both for the student (ESCS) and the school (MESCS). The Peru database was taken from PISA 2015 and was based on the results of 6,971 Peruvian students from 281 schools. The 10 plausible values of performance in science reported by PISA 2015 were used, and each of the four sub-competencies was evaluated. The values weighted likelihood estimate (WLE) of the following composite variables were standardized: (1) In teaching-learning activities, the disciplinary environment in science classes, teaching support in science classes at the students’ choice, and inquiry-based science teaching-learning practices; teacher-directed science instruction were considered. (2) For the formative evaluation factor, feedback, student perception about the evaluation, and adaptation of the instruction to the formative evaluation were considered. (3) The control variables were as follows: the age and gender of the students, the index of social, economic, and cultural status (ESCS) at the student level, and the average of the index of the social, economic, and cultural status of each school (MESCS), as well as the interaction of OTL variables with ESCS. The results of the linear hierarchical analysis showed that the achievement of Peruvian students in science in PISA 2015 (general competence) is mainly due to feedback perceived, adaptive instruction, teacher-directed science instruction, and inquiry-based science teaching-learning practices. The feedback perceived and the inquiry-based science teaching predicted negatively and significantly to science performances. The effect of inquiry-based science teaching-learning on science achievement decreased as hierarchical analysis models became more complex and decreased substantially when simultaneously interacting with perceived feedback, the student gender, and ESCS. The results also showed that the gender, the ESCS of the students, and the MESCS of the school were significant and positive predictors of academic performance. When considering each of the scientific competencies evaluated, the models are like the general score. Mainly, the MESCS of the school controls or diminishes the effect that the instructional variables have on science performance, except for the negative effect of feedback on academic performance, even when the ESCS is controlled by the school level.

Robust active learning with binary responses

We introduce a method of Robust Learning (‘robl’) for binary data, and propose its use in situations where Active Learning is appropriate, and where sampling the predictors is easy and cheap, but learning the responses is hard and expensive. We seek robustness against both modelling errors and the mislabelling of the binary responses. Thus we aim to sample effectively from the population of predictors, and learn the responses only for an ‘influential’ sub-population. This is carried out by probability weighted sampling, for which we derive optimal ‘unbiased’ sampling weights, and weighted likelihood estimation, for which we also derive optimal estimation weights. The robustness issues can lead to biased estimates and classifiers; it is somewhat remarkable that our weights eliminate the mean of the bias – which is a random variable as a result of the sampling – due to both types of errors mentioned above. These weights are then tailored to minimize the mean squared error of the predicted values. Simulation studies indicate that when bias is of significant concern, robl allows for substantial reductions, relative to Passive Learning, in the prediction errors. The methods are then illustrated in real-data analyses.

Reply to “Comment on ‘High-Definition Mapping of the Gutenberg–Richter b-Value and Its Relevance: A Case Study in Italy’ by M. Taroni, J. Zhuang, and W. Marzocchi” by Laura Gulia, Paolo Gasperini, and Stefan Wiemer

Abstract Taroni et al. (2021; hereafter TZM21) proposed a method to perform a spatial b-value mapping based on the weighted-likelihood estimation and applied this method to the Italian region as a tutorial example. In the accompanying comment, Gulia et al. (2021; hereafter GGW21) did not challenge the TZM21’s method, but they argued that the catalog used by TZM21 is contaminated by quarry blasts, introducing a bias that may impact any seismotectonic or hazard interpretations. Although in TZM21 the application to the Italian territory was only a tutorial example and we purposely did not make any thorough discussion on the meaning of the results in terms of seismotectonic or seismic hazards (that would have required many more analyses), we acknowledge the potential role of the quarry blasts, and we add some further analysis here. We thank GGW21 for giving us this opportunity. Here, removing the part of the catalog contaminated by quarry blasts and applying the same analysis as in TZM21, we obtain results that are very similar to the ones reported in TZM21; specifically, only one region that is characterized by low natural seismicity rate shows a marked effect of the quarry blasts on the b-value.

Topology tracking of dynamic UAV wireless networks

Wireless network is the communication foundation that supports the intelligentization of Unmanned Aerial Vehicle (UAV) swarm. The topology of UAV communication network is the key to understanding and analyzing the behavior of UAV swarm, thus supporting the further prediction of UAV operations. However, the UAV swarm network topology varies over time due to the high mobility and diversified mission requirements of UAVs. Therefore, it is important but challenging to research dynamic topology inference for tracking the topology changes of the UAV network, especially in non-cooperative manner. In this paper, we study the problem of inferring UAV swarm network topology based on external observations, and propose a dynamic topology inference method. First, we establish a sensing framework for acquiring the communication behavior of the target network over time. Then, we expand the multi-dimensional dynamic Hawkes process to model the communication event sequence in a dynamic wireless network. Finally, combining the sliding time window mechanism, the maximum weighted likelihood estimation is applied to inferring the network topology. Extensive simulation results demonstrate the effectiveness of the proposed method.

Health-related fitness knowledge in adolescence: evaluation of a\xa0new test considering different psychometric approaches (CTT and IRT)

Fostering health-related fitness knowledge is a common goal across physical education curricula. However, carefully developed knowledge tests that satisfy the psychometric criteria of educational assessment are lacking. Therefore, two studies were conducted to evaluate a newly developed health-related fitness knowledge test within the framework of classical test and item response theory regarding item quality, test reliability, construct validity, and dimensionality. Overall, 794 ninth graders (Mage = 14.3 years, 50.6% girls) took part in Study 1. They differed in the type of physical education classes (minor or major subject) and school (lower or higher educational level) they attended. Study 2 incorporated 834 ninth graders at the same educational level (Mage = 14.2 years, 52.5% girls). Item–test correlation, test reliability, and validity were examined. In addition, item and test quality were investigated using unidimensional two-parameter logistic item response models. In Study 1, pupils at the same educational level with physical education as a major achieved higher knowledge scores than pupils with physical education as a minor (t = −5.99, p < 0.001; d = 0.58), which confirmed the test’s construct validity. In Study 2, the weighted likelihood estimate reliability of the final 27 items was 0.65, and the test–retest reliability reached rtt = 0.70. The items satisfied the assumption of local independence. The final test fulfilled the psychometric criteria of reliability and construct validity to assess health-related fitness knowledge in cross-sectional and interventional studies. This test extends the possibilities of research on health-related fitness knowledge in physical education.

Item-Weighted Likelihood Method for Measuring Growth in Longitudinal Study With Tests Composed of Both Dichotomous and Polytomous Items.

In this paper, a new item-weighted scheme is proposed to assess examinees’ growth in longitudinal analysis. A multidimensional Rasch model for measuring learning and change (MRMLC) and its polytomous extension is used to fit the longitudinal item response data. In fact, the new item-weighted likelihood estimation method is not only suitable for complex longitudinal IRT models, but also it can be used to estimate the unidimensional IRT models. For example, the combination of the two-parameter logistic (2PL) model and the partial credit model (PCM, Masters, 1982) with a varying number of categories. Two simulation studies are carried out to further illustrate the advantages of the item-weighted likelihood estimation method compared to the traditional Maximum a Posteriori (MAP) estimation method, Maximum likelihood estimation method (MLE), Warm’s (1989) weighted likelihood estimation (WLE) method, and type-weighted maximum likelihood estimation (TWLE) method. Simulation results indicate that the improved item-weighted likelihood estimation method better recover examinees’ true ability level for both complex longitudinal IRT models and unidimensional IRT models compared to the existing likelihood estimation (MLE, WLE and TWLE) methods and MAP estimation method, with smaller bias, root-mean-square errors, and root-mean-square difference especially at the low-and high-ability levels.

Weighted likelihood CFAR detection for Weibull background

In modern radar detection systems, constant false alarm rate (CFAR) control is a key technique for automatic target detection in clutter level unknown environments. The maximum likelihood criterion is often used to design the CFAR detector for which it has the best detection performance with the expected probability of false alarm. However, the heterogeneous environments, viz., multiple-target scenario and clutter power transition, will deteriorate the performance of the optimal CFAR detector. In this paper, we propose a novel CFAR detector for Weibull background with known shape parameter. The new CFAR detector is based on robust weighted likelihood estimator, with robustness to interferences. In addition, to prove the CFAR property of it, we introduce the invariant theory. Computation analysis and simulation results verify the effectiveness and superiority of our proposed CFAR detector.

Investigation of Classification Accuracy, Test Length and Measurement Precision at Computerized Adaptive Classification Tests

This study aims to compare Sequential Probability Ratio Test (SPRT) and Confidence Interval (CI) classification criteria, Maximum Fisher Information method on the basis of estimated-ability (MFI-EB) and Cut-Point (MFI-CB) item selection methods while ability estimation method is Weighted Likelihood Estimation (WLE) in Computerized Adaptive Classification Testing (CACT), according to the Average Classification Accuracy (ACA), Average Test Length (ATL), and measurement precision under content balancing (Constrained Computerized Adaptive Testing: CCAT and Modified Multinomial Model: MMM) and item exposure control (Sympson-Hetter Method: SH and Item Eligibility Method: IE) when the classification is done based on two, three, or four categories for a unidimensional pool of dichotomous items. Forty-eight conditions are created in Monte Carlo (MC) simulation for the data, generated in R software, including 500 items and 5000 examinees, and the results are calculated over 30 replications. As a result of the study, it was observed that CI performs better in terms of ATL, and SPRT performs better in ACA and correlation, bias, Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) values, sequentially; MFI-EB is more useful than MFI-CB. It was also seen that MMM is more successful in content balancing, whereas CCAT is better in terms of test efficiency (ATL and ACA), and IE is superior in terms of item exposure control though SH is more beneficial in test efficiency. Besides, increasing the number of classification categories increases ATL but decreases ACA, and it gives better results in terms of the correlation, bias, RMSE, and MAE values.

Comparison of the New Estimators: The Semi-Parametric Likelihood Estimator, SPW, and the Conditional Weighted Pseudo Likelihood Estimator, WPCE

The analysis of sample-based studies involving sampling designs for small sample size, is challenging because the sample selection probabilities (as well as the sample weights) is dependent on the response variable and covariates. The study has focused on using systems of weighted regression estimating equations, using different modified weights, to estimate the coefficients of Weighted Likelihood Estimators. Usually, the design-consistent (Weighted) estimators are obtained by solving (sample) weighted estimating equations. They are then used to construct estimates which have better relative efficiencies and smaller finite small sample bias than the estimates from the Horvitz-Thompson Weighted Estimator with unmodified weight, option A. The purpose of our study is to compare derived Estimators of the weighted regression estimating equations for estimating the coefficients of Weighted Likelihood Estimators, the Semi-Parametric Weighted Likelihood Estimator, SPW and the Weighted Conditional Pseudo Likelihood Estimator, WCPE with the conventional Horvitz-Thompson Weighted Likelihood Estimator, using relative efficiency, sample bias and Standard Error for small sample size. The constructed estimates from the system of weighted regression estimating equations, using different modified weights, are actually the Weighted Likelihood Estimators. The study compared the two new estimators, the Semi-parametric weighted estimator, SPW and the Weighted Conditional Pseudo Likelihood estimator, WCPE, for both the unmodified and modified Weights, which were found to have better relative efficiency and smaller finite small sample bias than the estimates from conventional Horvitz-Thompson Weighted Estimator, for both generated and for real data. The outcome of the tests show strong similarity in performance to those obtained using the simulated data. Estimates were constructed which have better relative efficiencies and smaller finite small sample bias than the estimates from the Horvitz-Thompson Weighted Estimator with unmodified weight, option A.

Robust and Efficient Reliability Estimation for Exponential Distribution

In modeling reliability data, the exponential distribution is commonly used due to its simplicity. For estimating the parameter of the exponential distribution, classical estimators including maximum likelihood estimator represent the most commonly used method and are well known to be efficient. However, the maximum likelihood estimator is highly sensitive in the presence of contamination or outliers. In this study, a robust and efficient estimator of the exponential distribution parameter was proposed based on the probability integral transform statistic. To examine the robustness of this new estimator, asymptotic variance, breakdown point, and gross error sensitivity were derived. This new estimator offers reasonable protection against outliers besides being simple to compute. Furthermore, a simulation study was conducted to compare the performance of this new estimator with the maximum likelihood estimator, weighted likelihood estimator, and M-scale estimator in the presence of outliers. Finally, a statistical analysis of three reliability data sets was conducted to demonstrate the performance of the proposed estimator.

3 ve 4PL Madde Tepki Kuramı Modellerine Göre Farklı Yetenek Kestirim Yöntemlerinin Karşılaştırılması

This research analyzed the two-category Item Response Theory (IRT) models as part of different ability estimation methods. The research was carried out in consideration of responses to 20 items under the Mathematics subtest of TEOG (National Transition from Primary to Secondary Education) exam by the 8th-grade students in 2015-2016. The study group consisted of 400 students who were randomly selected from the students participated in the TEOG exam. Ability estimations and standard error values for these estimations were calculated based on the data. These estimations were compared by two-way analysis of variance (ANOVA) for repeated measurements According to the research findings; it was revealed that the four-parameter logistic (4PL) item model fit better. In terms of ability estimation methods, the accuracy of Weighted Likelihood Estimation (WLE) was higher than Maximum A Posteriori (MAP) and Expected A Posteriori (EAP). WLE and MAP ability estimation model gave lower standard error values compared to the 4PL and 3PL model, respectively. The highest marginal reliability coefficient value for the 3PL model was calculated using estimations made according to MAP while estimations made according to WLE were used for the 4PL model. According to the research findings, it was concluded that the accuracy of ability scores obtained by the WLE estimation method under the 4PL model was higher

Robust bootstrap prediction intervals for univariate and multivariate autoregressive time series models

ABSTRACT The bootstrap procedure has emerged as a general framework to construct prediction intervals for future observations in autoregressive time series models. Such models with outlying data points are standard in real data applications, especially in the field of econometrics. These outlying data points tend to produce high forecast errors, which reduce the forecasting performances of the existing bootstrap prediction intervals calculated based on non-robust estimators. In the univariate and multivariate autoregressive time series, we propose a robust bootstrap algorithm for constructing prediction intervals and forecast regions. The proposed procedure is based on the weighted likelihood estimates and weighted residuals. Its finite sample properties are examined via a series of Monte Carlo studies and two empirical data examples.

Robust semiparametric inference for polytomous logistic regression with complex survey design

Analyzing polytomous response from a complex survey scheme, like stratified or cluster sampling is very crucial in several socio-economics applications. We present a class of minimum quasi weighted density power divergence estimators for the polytomous logistic regression model with such a complex survey. This family of semiparametric estimators is a robust generalization of the maximum quasi weighted likelihood estimator exploiting the advantages of the popular density power divergence measure. Accordingly robust estimators for the design effects are also derived. Using the new estimators, robust testing of general linear hypotheses on the regression coefficients are proposed. Their asymptotic distributions and robustness properties are theoretically studied and also empirically validated through a numerical example and an extensive Monte Carlo study.

Introduction to the LIVECAT web-based computerized adaptive testing platform.

This study introduces LIVECAT, a web-based computerized adaptive testing platform. This platform provides many functions, including writing item content, managing an item bank, creating and administering a test, reporting test results, and providing information about a test and examinees. The LIVECAT provides examination administrators with an easy and flexible environment for composing and managing examinations. It is available at http://www.thecatkorea.com/. Several tools were used to program LIVECAT, as follows: operating system, Amazon Linux; web server, nginx 1.18; WAS, Apache Tomcat 8.5; database, Amazon RDMS—Maria DB; and languages, JAVA8, HTML5/CSS, Javascript, and jQuery. The LIVECAT platform can be used to implement several item response theory (IRT) models such as the Rasch and 1-, 2-, 3-parameter logistic models. The administrator can choose a specific model of test construction in LIVECAT. Multimedia data such as images, audio files, and movies can be uploaded to items in LIVECAT. Two scoring methods (maximum likelihood estimation and expected a posteriori) are available in LIVECAT and the maximum Fisher information item selection method is applied to every IRT model in LIVECAT. The LIVECAT platform showed equal or better performance compared with a conventional test platform. The LIVECAT platform enables users without psychometric expertise to easily implement and perform computerized adaptive testing at their institutions. The most recent LIVECAT version only provides a dichotomous item response model and the basic components of CAT. Shortly, LIVECAT will include advanced functions, such as polytomous item response models, weighted likelihood estimation method, and content balancing method.

Application of Iterative Maximum Weighted Likelihood Estimation in 3-D Target Localization

Time-of-flight (ToF)-based 3-D target localization is a very challenging topic because of the pseudo-targets introduced by ToF measurement errors in traditional ToF-based methods. Although the influence of errors in ToF measurement can be reduced by the probability-based ToF method, the accuracy of localization is not very high. This paper proposes a new 3-D target localization method, Iterative Maximum Weighted Likelihood Estimation (IMWLE), that takes into account the spatial distribution of pseudo-targets. In our method, each pseudo-target is initially assigned an equal weight. At each iteration, Maximum Weighted Likelihood Estimation (MWLE) is adopted to fit a Gaussian distribution to all pseudo-target positions and assign new weight factors to them. The weight factors of the pseudo-targets, which are far from the target, are reduced to minimize their influence on localization. Therefore, IMWLE can reduce the influence of pseudo-targets that are far from the target and improve the accuracy of localization. The experiments were carried out in a water tank to test the performance of the IMWLE method. Results revealed that the estimated target area can be narrowed down to the target using IMWLE and a point estimate of target location can also be obtained, which shows that IMWLE has a higher degree of accuracy than the probability-based ToF method.