Maximum Likelihood Estimation Technique Research Articles

Acoustic object canceller: removing a known signal from monaural recording using blind synchronization

In this paper, we propose a technique for removing a specific type of interference from a monaural recording. Nonstationary interferences are generally challenging to eliminate from such recordings. However, if the interference is a known sound like a cell phone ringtone, music from a CD or streaming service, or a radio or TV broadcast, its source signal can be easily obtained. In our method, we define such interference as an acoustic object. Even if the sampling frequencies of the recording and the acoustic object do not match, we compensate for the mismatch and use the maximum likelihood estimation technique with the auxiliary function to remove the interference from the recording. We compare several probabilistic models for representing the object-canceled signal. Experimental evaluations confirm the effectiveness of our proposed method.

Bayesian inference using MCMC algorithm of sine truncated Lomax distribution with application

This study makes a significant contribution to the creation of a versatile trigonometric extension of the well-known truncated Lomax distribution. Specifically, we construct a novel one-parameter distribution known as the sine truncated Lomax (STLo) distribution using characteristics from the sine generalized family of distributions. Quantiles, moments, stress–strength reliability, some information measures, residual moments, and reversed residual moments are a few of the crucial elements and characteristics we explored in our research. The flexibility of the STLo distribution in terms of the forms of the hazard rate and probability density functions illustrates how effectively it is able to match many types of data. Maximum likelihood and Bayesian estimation techniques are used to estimate the model parameter. The squared error loss function is employed in the Bayesian approach. To evaluate how various estimates behave, a Monte Carlo simulation study is carried out with the aid of a useful algorithm. Additionally, the STLo distribution has a good fit, making it a viable option when compared to certain other competing models using specific criteria to describe the given dataset.

Stochastic soiling loss models for heliostats in Concentrating Solar Power plants

Reflectance losses on solar mirrors due to soiling are a significant challenge for Concentrating Solar Power (CSP) plants. Soiling losses can vary significantly from site to site — with (absolute) reflectance losses varying from fractions of a percentage point up to several percentage points per day (pp/day), a fact that has motivated several studies in soiling predictive modelling. Yet, existing studies have so far neglected the characterization of statistical uncertainty in their parameters and predictions. In this paper, two reflectance loss models are proposed that model uncertainty: an extension of a previously developed physical model and a simplified model. A novel uncertainty characterization enables Maximum Likelihood Estimation techniques for parameter estimation for both models, and permits the estimation of parameter (and prediction) confidence intervals.The models are applied to data from ten soiling campaigns conducted at three Australian sites (Brisbane, Mount Isa, Wodonga). The simplified model produces high-quality predictions of soiling losses on novel data, while the semi-physical model performance is mixed. The statistical distributions of daily losses were estimated for different dust loadings. Under median conditions, the daily soiling losses for Brisbane, Mount Isa, and Wodonga are estimated as 0.53±0.66, 0.08±0.08, and 0.58±0.15 pp/day, respectively. Yet, higher observed dust loadings can drive average losses as high as 2 pp/day.Overall, the results suggest a relatively simple approach characterizing the statistical distributions of soiling losses using airborne dust measurements and short reflectance monitoring campaigns.

Integration of the technology acceptance model and the information systems success model in the analysis of Moodle's satisfaction and continuity of use

PurposeThis paper aims to analyse the factors that influence the satisfaction and intention of continuity of use, of teachers and students, regarding using Moodle in undergraduate courses in one Campus at the Federal Institute of Rondônia in Brazil. The starting point was an integration of DeLone and McLean's Information Systems Success Model (ISSM) with Davis' Technology Acceptance Model (TAM).Design/methodology/approachA quantitative research approach was adopted. After the definition of the hypotheses, data were collected through self-administered questionnaires. The questionnaires were designed to measure the five constructs: Quality of Information (QI), Perceived Ease of Use (PEOU), Perceived Usefulness (PU), User Satisfaction (US) and Behavioural Intention to use (BI) that make up the conceptual model of the study. The data were analysed based on 144 valid questionnaires. The technique of maximum likelihood estimation was adopted in the data analysis through structural equation modelling (SEM).FindingsThe results confirmed six of the nine hypothesised relationships. QI positively impacts PEOU and US. PEOU positively impacts PU, which in turn positively impacts US and BI. Similarly, US positively impacts Moodle's BI. It was also evidenced that PU is the strongest predictor of US.Practical implicationsThese results can help educational institutions, managers, administrators and designers of e-learning systems to develop strategies to increase Moodle's user satisfaction.Originality/valueThis study provides insights into the perception of students and teachers regarding the use of Moodle. A model that integrates constructs from two models widely used in research related to e-learning (TAM and ISSM) was used in a developing country context. This is important, given cultural differences and social idiosyncrasies in different contexts, particularly in an educational institution in the Amazonia region in northern Brazil.

Application of the Beta Distribution Model to the Customer Churn Rate

The beta distribution model has been applied in many different research environments due to the flexibility of its two parameters. In this research, we fit this probabilistic model for mod- eling a recurring problem confronted for many businesses called the customer churn rate (or churn rate). It represents the proportion of customers who cancel their subscriptions after a given time. We use data from a Brazilian media service company to develop the modeling. The parameters are estimated by the maximum likelihood estimation (MLE) technique. Finally, we perform the MLE technique by considering two programming languages; Ox and R.

Optimization of Gamma–Power–Log–logistic distribution and its applications in modelling volume of oil spillage

Oil spillage is one of the major problems in the Niger Delta region of Nigeria, which have affected human health and aquaculture. There is a need to estimate the volume of spill per incidence. Estimating the volume of crude oil after spill is a problem in environmental sciences. In this research, a newly-convoluted gamma–power generalized linear model (GLM), which was derived from Gamma–Power–Log–logistic distribution was developed. The proposed model was used to fit a regression model to estimate the spill volume of crude oil in the South–south geopolitical zone of Nigeria. Some statistical properties of the distribution such as, the transformation to a gamma distribution and the likelihood ratio test were derived. The Maximum Likelihood Estimation (MLE) technique, using generalized Newton Approximation with Expectation Maximization (EM) algorithm was used to obtain the model parameters and the consistency of the parameters estimated was justified by a simulation study. The simulation study result showed that the parameters estimated are consistent. The result of the likelihood ratio test (LRT) and other selection criteria adopted showed that the novel GPGLM outperformed other models. The LRT showed how much better the proposed model could be when compared to gamma and normal models as a good fit to bimodal skewed leptokurtic dependent response variable in a regression settings. The new model is an extension of the gamma model and would be very useful for modelling bimodal, skewed and leptokurtic dependent variable in a regression model. The study recommended that clean-up should be done promptly in order to achieve the Sustainable Development Goal of access to clean water and improved quality of life.

The Topp-Leone-Gompertz-Exponentiated Half Logistic-G Family of Distributions with Applications

This paper introduces and investigates a new family of distributions called the Topp-Leone-Gompertz-exponentiated half logistic-G (TL-Gom-EHL-G) distribution. Some mathematical and statistical properties of this family of distributions are derived. To estimate and evaluate the model parameters, the maximum likelihood estimation technique is used, and the consistency of maximum likelihood estimators is examined using Monte Carlo simulation. Applications to three real data sets from different areas were used to demonstrates the usefulness and versatility of the TL-Gom-EHL-G family of distributions.

Real Estate Return Distributions with New NCREIF Data Series

The accuracy of real estate return distribution parameter estimation is affected by the tools used to do the work as well as the data sets employed. Consistent with previous studies, investment risk models with infinite variance describe distributions of individual property returns in the new NCREIF Indicators: Capital Performance and Property Operations individual property database over the period 1990–2021. Applying Maximum Likelihood Estimation (MLE) to historic data shows real estate investment risk to be heteroscedastic, but the Characteristic Exponent of the investment risk function varies more among property types than previously reported whether computed by MLE or other estimation techniques.

Kth-order equilibrium Weibull distribution: properties, simulation, and its applications

A generalization of some well-known probability distributions (viz., Weibull, exponential, gamma, Maxwell, and Chi-square) is introduced using the concept of weighted probability distributions. The introduced model is named Kth-order equilibrium Weibull distribution (KEWD). Various properties of the new distribution are studied in detail. One of the important properties of KEWD is that its hazard rate shows increasing, decreasing, and constant behavior. It is also shown that the new model belongs to the log exponential family. Various ordering relations of the KEWD are studied in comparison with the baseline model, i.e. Weibull distribution. Parameters are estimated using the concept of the maximum likelihood estimation technique. Using the Anderson–Darling test statistic, a simulation study is carried out to analyze the asymptotic normality behavior of maximum likelihood estimators. The behaviors of bias and mean square error are observed with the increase in sample size. The applications of new distribution are illustrated through its fitting to some incorporated real-life data sets. Finally, a comparison is made between KEWD, its sub-models, and some other introduced extensions of Weibull distribution in terms of fitting using the Akaike information criterion (AIC).

The Gamma-Topp-Leone-Type II-Exponentiated Half Logistic-G Family of Distributions with Applications

The new Ristić and Balakhrisnan or Gamma-Topp-Leone-Type II-Exponentiated Half Logistic-G (RB-TL-TII-EHL-G) family of distributions is introduced and investigated in this paper. This work derives and studies some of the main statistical characteristics of this new family of distributions. The maximum likelihood estimation technique is used to estimate the model parameters, and a simulation study is used to assess the consistency of the estimators. Applications to three real-life datasets from various fields show the value and adaptability of the new RB-TL-TII-EHL-G family of distributions. From our results, it is evident that the new proposed distribution is flexible enough to characterize datasets from different fields compared to several other existing distributions in the literature.

On The New Modified Burr XII Distribution: Development, Properties, Characterizations and Applications

A new distribution with flexible hazard rate function is introduced which is called new modified Burr XII (NMBXII) distribution. The proposed distribution is derived from the T-X family technique and compounding the generalized Nadarajah–Haghighi (GNH) and gamma distributions. We highlighted the shapes of NMBXII density and failure rate functions. The density function of NMBXII model can take shapes such as J, reverse J, positively skewed and symmetrical. The proposed model can produce almost all types of failure rates such as increasing, decreasing, increasing-decreasing, decreasing-increasing, bimodal, inverted bathtub and modified bathtub. To show the importance of the proposed distribution, we established various mathematical properties such as quantiles, moments, incomplete moments, inequality measures, residual life functions and reliability measures theoretically. We have characterized the NMBXII distribution via two techniques. We addressed the maximum likelihood estimation technique for model parameters. The precision of the MLEs is estimated via a simulation study. We have considered three real data sets for applications to demonstrate the potentiality and utility of the NMBXII model. Then, we have established empirically that the proposed model is suitable for tax revenue, time periods between successive earthquakes and flood discharges applications. Finally, various model selection criteria, the goodness of fit statistics and graphical tools were used to examine the adequacy of the NMBXII distribution.

Type II Exponentiated Half-Logistic Gompertz-G Family of Distributions: Properties and Applications

ABSTRACT In this work, a new family of distributions referred to as type II exponentiated half-logistic-Gompertz-G (TIIEHL-Gom-G) family of distributions is introduced and studied. Some of the main statistical properties of these family of distributions are derived. The model parameters are estimated using the maximum likelihood estimation technique and consistency of maximum likelihood estimators is evaluated by performing a simulation study. The importance and versatility of the TIIEHL-Gom-G family of distributions is demonstrated in an application to two real data sets from different fields.

Export Spillovers from Foreign Direct Investment in Kenya's Manufacturing Sector: A Double Hurdle Approach

ABSTRACT: This paper investigates export spillovers from foreign direct investment on the exporting activities of domestic manufacturing firms in Kenya. Specifically, the paper aims at identifying the transmission channels through which foreign direct investment affects the export propensity and export intensity decisions of domestically-owned firms. The study also examines the importance of firm-level heterogeneity on the occurrence and behavior of spillover channels. The study uses a panel data set for manufacturing firms in Kenya, obtained from the World Bank Enterprise Surveys, conducted in three waves covering the period 2007–2018. Employing the Double-Hurdle model approach, and using the maximum likelihood estimation technique, we empirically demonstrate the relevance and significance of distinguishing three channels for intra-industry (horizontal) spillovers – demonstration effects, information effects and competition effects channels and one channel for vertical spillovers, that is, backward linkage channel. Findings of this study shows that domestically-owned firms in Kenya experience significant positive export spillovers on their export participation decisions through the demonstration effects channel and significant negative spillovers via the competition effects channel. The findings also show significant positive export spillover effects on the export intensity decisions of domestically-owned firms via information and competition effects channels and significant negative export spillover effects via the backward linkages channel. The results further provide evidence that firms belonging to industries with low technological levels were unable to absorb spillover benefits from foreign presence via the demonstration effects channel. The results also indicate that small and medium firms were unable to reap export spillovers benefits via information effects and backward linkage channels. The findings have important policy implications for managers of firms and policymakers in Kenya and other developing countries. To enhance export-related spillover benefits, domestic firms need to enhance their absorptive capacities by upgrading their technical capacities and improving quality standards. Governments should facilitate the exchange of information on investor needs, their capacities and skills requirements, thus bridging information gaps between domestic suppliers and foreign investors in addition to supporting domestic market linkages.

Johnson–Schumacher Split-Plot Design Modelling of Rice Yield

Summary In this research, an intrinsically nonlinear split-plot design model (INSPDM) is formulated and studied. It was formulated by fitting a Johnson–Schumacher (JS) function to the split-plot model mean function. The fitted model parameters are estimated using the estimated generalized least squares (EGLS) technique based on a Gauss–Newton procedure with Taylor series expansion, by minimizing the objective function of the model. The variance components for the whole plot and subplot random effects are estimated using restricted maximum likelihood estimation (REML) techniques. The adequacy of the fitted INSPDM was tested using four median adequacy measures: resistant coefficient of determination, resistant prediction coefficient of determination, the resistant modeling efficiency statistic, and the median square error prediction statistic based on the residuals of the fitted model. Akaike’s Information Criterion (AIC), Corrected Akaike’s Information Criterion (AICC) and Bayesian Information Criterion (BIC) statistics are used to select the best parameter estimation technique. The results obtained are compared with the techniques of ordinary least squares (OLS) and EGLS via maximum likelihood estimation (MLE). The results showed the model to be adequate, reliable, stable, and a good fit based on EGLS-REML when compared with OLS and EGLS-MLE fitted model parameter estimates.

The Ristić–Balakrishnan–Topp–Leone–Gompertz-G Family of Distributions with Applications

In this paper, we introduce the newly generated Ristić–Balakrishnan–Topp–Leone–Gompertz-G family of distributions. Statistical and mathematical properties of this new family including moments, moment generating function, incomplete moments, conditional moments, probability weighted moments, distribution of the order statistics, stochastic ordering, and Rényi entropy are derived. The unknown parameters of the family are inferred using the maximum likelihood estimation technique. A Monte Carlo simulation study is performed to investigate the convergence of the maximum likelihood estimation. Three real-life data sets are used to demonstrate the flexibility and capacity of the new family of distributions.

Estimating extreme monthly rainfall for Spain using non-stationary techniques

ABSTRACT In hydrology, extreme value analysis is normally applied at stationary yearly maxima. However, climate variability can bias the estimation of extremes by partially invalidating the stationary assumption. Extreme value analysis for sub-yearly data may depart from stationarity (since maxima from one month may not be exchangeable with maxima from another) in terms of requiring to include it in the analysis. Here, we analyse the non-stationary structure of extreme monthly rainfall in Spain using two approaches: a parametric approach and an approach based on autoregressive time series models. Our analysis considers seasonality, climate variability and long-term trends for both approaches, and it compares both including their goodness of fit and complexity. The approach uses maximum likelihood estimation and Bayesian techniques. Our results show that autoregressive models outperform parametric models, providing a more accurate representation of extreme events when extrapolating outside of the period of fit.

An Alternative Statistical Model to Analysis Pearl Millet (Bajra) Yield in Province Punjab and Pakistan

Background. A country’s agriculture reflects a backbone and performs a vital part in the betterment of the economy and individuals. Facts and figures of the agriculture sector offer a solid foundation and factual pathway intended for upcoming decisions in favor of a country. Accordingly, the probability models have a more significant influence not only in reliability engineering, hydrology, ecology, and medicine but also in agriculture sciences. Objective. The primary objective of this study is to propose a reliable and efficient model for pearl millet yield analysis, thereby empowering decision-makers to make informed decisions about their farming practices. With the successful implementation of this model, farmers can potentially increase their pearl millet yield, leading to higher incomes and improved livelihoods for the rural population of Pakistan. Model. This study proposes a novel probability model, namely, the alpha transformed odd exponential power function (ATOE-PF) distribution, for analyzing pearl millet yield in Punjab, Pakistan. Data. For data collection, two secondary data sets are explored that are electronically available on the site of the Directorate of Agriculture (Economics and Marketing) Punjab, Lahore, Pakistan. Results. The maximum likelihood estimation technique is used for estimating the model parameters. For the selection of a better fit model, we follow some accredited goodness of fit tests. The efficiency and applicability of the ATOE-PF distribution are discussed over the province of Punjab (with RMSE = 4.9176) and Pakistan (with RMSE = 4.5849). Better estimates and closest fit to data among the well-established neighboring models offer robust evidence in support of ATOE-PF distribution as well.

Modeling Extreme Values with Alpha Power Inverse Pareto Distribution

Abstract The study focuses on the development of a new probability distribution with applications to extreme values. The distribution is proposed by incorporating an additional parameter into the inverse Pareto distribution using the α-Power Transformation. Various properties of the new distribution are derived. The paper also explores the estimation of the parameters by the Maximum Likelihood Estimation (MLE) technique. Simulations are performed to evaluate the performance of the MLEs. In addition, two real data sets with extreme values are used to evaluate the efficacy of the proposed model. It is concluded that the proposed model performs well in the case of extreme values compared to the existing distributions.

THE EXTENDED ODD FRÉCHET INVERTED EXPONENTIAL DISTRIBUTION: PROPERTIES AND APPLICATION

This research introduces a new three-parameter continuous distribution from the extended odd Fréchet (EOF) family of distributions called the extended odd Fréchet inverted exponential (EOFIE) distribution. Derivations of EOFIE distribution statistical properties are derived and its parameters are estimated using the technique of maximum likelihood (ML) estimation. The ML estimates finite sample performance of the EOFIE distribution is evaluated through simulation. Results obtained from the application of the EOFIE distribution to two real-life datasets showed that it provides a better fit than other competing distributions.

On Construction and Estimation of Mixture of Log-Bilal Distributions

Recently, the use of mixed models for analyzing real data sets with infinite domains has gained favor. However, only a specific type of mixture model using mostly maximum likelihood estimation technique has been exercised in the literature, and fitting the mixture models for bounded data (between zero and one) has been neglected. In statistical mechanics, unit distributions are widely utilized to explain practical numeric values ranging between zero and one. We presented a classical examination for the trade share data set using a mixture of two log-Bilal distributions (MLBDs). We examine the features and statistical estimation of the MLBD in connection with three techniques. The sensitivity of the presented estimators with respect to model parameters, weighting proportions, sample size, and different evaluation methodologies has also been discussed. A simulation investigation is also used to endorse the estimation results. The findings on maximum likelihood estimation were more persuasive than those of existing mixture models. The flexibility and importance of the proposed distribution are illustrated by means of real datasets.