Model Estimates Research Articles

Precision estimation of winter wheat crop height and above-ground biomass using unmanned aerial vehicle imagery and oblique photoghraphy point cloud data.

Crop height and above-ground biomass (AGB) serve as crucial indicators for monitoring crop growth and estimating grain yield. Timely and accurate acquisition of wheat crop height and AGB data is paramount for guiding agricultural production. However, traditional data acquisition methods suffer from drawbacks such as time-consuming, laborious and destructive sampling. The current approach to estimating AGB using unmanned aerial vehicles (UAVs) remote sensing relies solely on spectral data, resulting in low accuracy in estimation. This method fails to address the ill-posed inverse problem of mapping from two-dimensional to three-dimensional and issues related to spectral saturation. To overcome these challenges, RGB and multispectral sensors mounted on UAVs were employed to acquire spectral image data. The five-directional oblique photography technique was utilized to construct the three-dimensional point cloud for extracting crop height. This study comparatively analyzed the potential of the mean method and the Accumulated Incremental Height (AIH) method in crop height extraction. Utilizing Vegetation Indices (VIs), AIH and their feature combinations, models including Random Forest Regression (RFR), eXtreme Gradient Boosting (XGBoost), Gradient Boosting Regression Trees (GBRT), Support Vector Regression (SVR) and Ridge Regression (RR) were constructed to estimate winter wheat AGB. The research results indicated that the AIH method performed well in crop height extraction, with minimal differences between 95% AIH and measured crop height values were observed across various growth stages of wheat, yielding R2 ranging from 0.768 to 0.784. Compared to individual features, the combination of multiple features significantly improved the model's estimate accuracy. The incorporation of AIH features helps alleviate the effects of spectral saturation. Coupling VIs with AIH features, the model's R2 increases from 0.694-0.885 with only VIs features to 0.728-0.925. In comparing the performance of five machine learning algorithms, it was discovered that models constructed based on decision trees were superior to other machine learning algorithms. Among them, the RFR algorithm performed optimally, with R2 ranging from 0.9 to 0.93. In conclusion, leveraging multi-source remote sensing data from UAVs with machine learning algorithms overcomes the limitations of traditional crop monitoring methods, offering a technological reference for precision agriculture management and decision-making.

Dementia risk prediction using decision-focused content selection from medical notes

Several general-purpose language model (LM) architectures have been proposed with demonstrated improvement in text summarization and classification. Adapting these architectures to the medical domain requires additional considerations. For instance, the medical history of the patient is documented in the Electronic Health Record (EHR) which includes many medical notes drafted by healthcare providers. Direct processing of these notes may not be possible because the computational complexity of LMs imposes a limit on the length of input text. Therefore, previous applications resorted to content selection using truncation or summarization of the text. Unfortunately, these text processing techniques may lead to information loss, redundancy or irrelevance. In the present paper, a decision-focused content selection technique is proposed. The objective of this technique is to select a subset of sentences from the medical notes of a patient that are relevant to the target outcome over a predefined observation period. This decision-focused content selection methodology is then used to develop a dementia risk prediction model based on the Longformer LM architecture. The results show that the proposed framework delivers an AUC of 78.43 when the summary is restricted to 1024 tokens, outperforming previously proposed content selection techniques. This performance is notable given that the model estimates dementia risk with a one year prediction horizon, relies on an observation period of only one year and solely uses medical notes without other EHR data modalities. Moreover, the proposed techniques overcome the limitation of machine learning models that use a tabular representation of the text by preserving contextual content, enable feature engineering from raw text and circumvent the computational complexity of language models.

Machine Learning for the Prediction of Surgical Morbidity in Placenta Accreta Spectrum.

We sought to create a machine learning (ML) model to identify variables that would aid in the prediction of surgical morbidity in cases of placenta accreta spectrum (PAS). A multicenter analysis including all cases of PAS identified by pathology specimen confirmation, across five tertiary care perinatal centers in New York City from 2013 to 2022. We developed models to predict operative morbidity using 213 variables including demographics, obstetrical information, and limited prenatal imaging findings detailing placental location. Our primary outcome was prediction of a surgical morbidity composite defined as including any of the following: blood loss (>1,500 mL), transfusion, intensive care unit admission, vasopressor use, mechanical ventilation/intubation, and organ injury. A nested, stratified, cross-validation approach was used to tune model hyperparameters and estimate generalizability. Gradient boosted tree classifier models incorporated preprocessing steps of standard scaling for numerical variables and one-hot encoding for categorical variables. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), positive and negative predictive values (PPV, NPV), and F1 score. Variable importance ranking was also determined. Among 401 PAS cases, 326 (81%) underwent hysterectomy. Of the 401 cases of PAS, 309 (77%) had at least one event defined as surgical morbidity. Our predictive model had an AUC of 0.79 (95% confidence interval: 0.69, 0.89), PPV 0.79, NPV 0.76, and F1 score of 0.88. The variables most predictive of surgical morbidity were completion of a hysterectomy, prepregnancy body mass index (BMI), absence of a second trimester ultrasound, socioeconomic status zip code, BMI at delivery, number of prenatal visits, and delivery time of day. By identifying social and obstetrical characteristics that increase patients' risk, ML models are useful in predicting PAS-related surgical morbidity. Utilizing ML could serve as a foundation for risk and complexity stratification in cases of PAS to optimize surgical planning. · ML models are useful models are useful in predicting PAS-related surgical morbidity.. · Optimal management for PAS remains unclear.. · Utilizing ML can serve as a foundation for risk and complexity stratification in cases of PAS..

Estimating community-wide indirect effects of influenza vaccination: triangulation using mathematical models and bias analysis.

Understanding whether influenza vaccine promotion strategies produce community-wide indirect effects is important for establishing vaccine coverage targets and optimizing vaccine delivery. Empirical epidemiologic studies and mathematical models have been used to estimate indirect effects of vaccines but rarely for the same estimand in the same dataset. Using these approaches together could be a powerful tool for triangulation in infectious disease epidemiology because each approach is subject to distinct sources of bias. We triangulated evidence about indirect effects from a school-located influenza vaccination program using two approaches: a difference-in-difference (DID) analysis, and an age-structured, deterministic, compartmental model. The estimated indirect effect was substantially lower in the mathematical model than in the DID analysis (2.1% (95% Bayesian credible intervals 0.4 - 4.4%) vs. 22.3% (95% CI 7.6% - 37.1%)). To explore reasons for differing estimates, we used sensitivity analyses and probabilistic bias analyses. When we constrained model parameters such that projections matched the DID analysis, results only aligned with the DID analysis with substantially lower pre-existing immunity among school-age children and older adults. Conversely, DID estimates corrected for potential bias only aligned with mathematical model estimates under differential outcome misclassification. We discuss how triangulation using empirical and mathematical modelling approaches could strengthen future studies.

Thermal coal futures trading volume predictions through the neural network

Purpose Predicting commodity futures trading volumes represents an important matter to policymakers and a wide spectrum of market participants. The purpose of this study is to concentrate on the energy sector and explore the trading volume prediction issue for the thermal coal futures traded in Zhengzhou Commodity Exchange in China with daily data spanning January 2016–December 2020. Design/methodology/approach The nonlinear autoregressive neural network is adopted for this purpose and prediction performance is examined based upon a variety of settings over algorithms for model estimations, numbers of hidden neurons and delays and ratios for splitting the trading volume series into training, validation and testing phases. Findings A relatively simple model setting is arrived at that leads to predictions of good accuracy and stabilities and maintains small prediction errors up to the 99.273th quantile of the observed trading volume. Originality/value The results could, on one hand, serve as standalone technical trading volume predictions. They could, on the other hand, be combined with different (fundamental) prediction results for forming perspectives of trading trends and carrying out policy analysis.

Driving Under the Influence of Alcohol and Cannabis by Sexual Identity, Race, Ethnicity, and Gender: A Nationwide Analysis Using the 2016 to 2019 National Survey on Drug Use and Health.

Sexual minority populations experience higher rates of substance use and related problems, but little is known about their specific involvement in driving under the influence (DUI) of alcohol (DUIA) and cannabis (DUIC) incidents. Using data from the 2016 to 2019 National Survey on Drug Use and Health, we used logistic regression models to estimate the interactive effects of sexual identity, race/ethnicity, and gender on past-year DUIA among adults who used alcohol and DUIC among adults who used cannabis, accounting for covariates. Using model estimates and linear combinations, we calculated the predicted probabilities of each outcome and compared sexual identity differences within and across race/ethnicity and gender. With few exceptions, the predicted probabilities of DUIA and DUIC were significantly higher among sexual minority women than heterosexual women of similar race/ethnicity. The results were more variable among men with the probabilities of DUIA and DUIC being significantly higher for some groups of sexual minority men and some groups having probabilities equal to or lower than similar heterosexual men. Some of the largest sexual minority gaps in DUIA and DUIC were observed among Hispanic and Other lesbian women and Black gay men. Sexual minority individuals are more likely to report DUI than their heterosexual counterparts; however, the risk of DUI among sexual minority populations varies by racial/ethnic and gender subgroup. Our findings indicate the importance of applying an intersectional framework when addressing substance-use-related disparities and when designing effective DUI prevention interventions for sexual minority populations.

A calibration method for telecentric line-scan cameras with an enhanced dynamic imaging model and initial estimates derived from direct linear transformation

This study presents a calibration method for telecentric line-scan cameras, incorporating a dynamic imaging model and initial estimates derived from direct linear transformation. The enhanced dynamic imaging model includes an inclination parameter instead of velocities in three orthogonal spatial directions. It is applicable to any direction of motion, considers lens distortion, and accommodates the line sensor at an arbitrary position relative to the optical axis. Employing the enhanced camera model, the initial values of telecentric line-scan camera parameters are determined derived from direct linear transformation. Sensitivity of our method with respect to the noise level of image points and the number of pattern planes are assessed through numerical simulations, while effectiveness and robustness are validated through experiments using real-world data, achieving a reprojection error of 0.6386 pixels and a standard deviation of 0.0160 pixels. The versatility of the proposed method can be extended to measurement applications utilizing flatbed scanners.

Effect of Data Quality and Data Quantity on the Estimation of Intrinsic Solubility: Analysis Based on a Single-Source Data Set.

Aqueous solubility is one of the most important physicochemical properties of drug molecules and a major driving force for oral drug absorption. To date, the performance of in silico models for the estimation of solubility for novel chemical space is limited. To investigate possible reasons and remedies for this, the Johnson and Johnson in-house aqueous solubility data with over 40,000 compounds was leveraged. All data were generated through the same high-throughput assay, providing a unique opportunity to explore the relationship between data quality, quantity, and model estimations. Six intrinsic solubility data sets with different sizes and noise levels were generated by making use of three different approaches: (i) inclusion or exclusion of amorphous solid residue, (ii) measured or experimental log D to identify the intrinsic solubility, and (iii) adopting or omitting a quality check process in the data processing workflow. A random forest regressor was trained on the data sets with three different sets of descriptors calculated from RDKit, ADMET predictor, or Mordred, and the performances were evaluated with nested cross-validation as well as ten refined test sets. The models confirm, as expected, that with the same data set size, high-quality data leads to better model performance; however, also, models trained with larger data sets containing analytical variability can give equally accurate estimations compared to models trained with small, clean, and diverse data sets. However, noise introduced by including the presence of amorphous solid postsolubility measurement in the training data set cannot be overcome by increasing data size, as they are introducing a biased systematic positive error in the data set, confirming the importance of critical data review. Finally, two top-performing models were tested on the first test set from the second solubility challenge, achieving RMSE values of 0.74 and 0.72 and log S ± 0.5 of 46 and 48%, respectively. These results demonstrated improved performance compared to those reported in the findings of the competition, highlighting that a single-source curated data set can enhance the prediction of intrinsic solubility.

393 The role of on-animal sensors in understanding feed intake, behavior, and performance of grazing livestock

Abstract Intake by grazing animals is difficult to reliably measure in the field, particularly in more diverse grazing systems where pastures vary greatly across time and space in resource availability, which in turn leads to greater variation in animal time budgets and intake patterns. Advances in remote livestock monitoring (e.g., on-animal sensors, walk -over-weighing), and advanced analytics such as machine learning algorithms can contribute to the development of robust, adaptable tools for better understanding of animal performance and behavior in grazing systems. Many existing tools for predicting livestock production require estimates of feed intake, and while estimates based on forage sward characteristics have been developed and used for temperate, relatively homogenous pastures, they are less well defined for more diverse rangelands. These diverse pastures are more difficult to characterize due to their greater variation in quantity and quality; consequently, animal selectivity is greater in more variable pastures. However, such feedback loops between pasture diversity and animal behavior may not yet be adequately represented in biophysical models. On-animal sensors such as accelerometers and GPS devices can be used to develop new ways of assessing relative intake by providing accurate estimates of animal location and behavior profiles, such as the use of machine learning algorithms to detect how much time is spent grazing, walking, ruminating, or resting. Measurements of animal behavior could then be combined with other animal-based methods such as walk-over-weighing and fecal NIR to improve estimates of intake and production for a wide range of extensive grazing environments. Sensor-derived measurements of animal movement could also be used to improve estimates of the energetic costs of grazing, thereby improving estimates of energy available for growth. As an example, data on recent activity and paddock use from on-animal sensors could be entered into a model to estimate current feeding requirements, then combined with weather and pasture quality forecasts. The ensuing baseline could then be used to explore the potential variability of these projections and generate a range for possible expected performance over the next month or season. This approach could be repeated over time, and animal performance and behavior measures used to update model estimates and improve forward projections. These methods could also be used in conjunction with estimates of animal energy requirements to provide real-time prediction of relative feed intake, which would provide a step-change in modelling livestock production in extensive grazing systems. For these approaches to be successful, additional calibration data are needed across a wide variety of environments and species, and the tools must be cost-effective to implement. In summary, on-animal measurements provide an adaptable, data-driven approach that could be integrated with existing tools to improve our understanding of feed intake, behavior, and performance of grazing animals.

General Population Mortality Adjustment in Survival Extrapolation of Cancer Trials: Exploring Plausibility and Implications for Cost-Effectiveness Analyses in HER2-Positive Breast Cancer in Sweden.

In economic evaluations of novel therapies, assessing lifetime effects based on trial data often necessitates survival extrapolation, with the choice of model affecting outcomes. The aim of this study was to assess accuracy and variability between alternative approaches to survival extrapolation. Data on HER2-positive breast cancer patients from the Swedish National Breast Cancer Register were used to fit standard parametric distribution (SPD) models and excess hazard (EH) models adjusting the survival projections based on general population mortality (GPM). Models were fitted using 6-y data for stage I and II, 4-y data for stage III, and 2-y data for stage IV cancer reflecting an early data cutoff while maintaining sufficient events for comparison of model estimates with actual long-term outcomes. We compared model projections of 15-y survival and restricted mean survival time (RMST) to 15-y registry data and explored the variability between models in extrapolations of long-term survival. Among 11,224 patients compared with the observed registry 15-y RMST estimates across the disease stages, EH cure models provided the most accurate estimates in patients with stage I to III cancer, whereas EH models without cure most closely matched survival in patients with stage IV cancer, in which cure assumption was less plausible. The Akaike information criterion-averaged model projections varied as follows: -8.2% to +5.3% for SPD models, -4.9% to +5.2% for the EH model without a cure assumption, and -19.3% to -0.2% for the EH model with a cure assumption. EH models significantly reduced between-model variance in the predicted RMSTs over a 50-y time horizon compared with SPD models. EH models may be considered as alternatives to SPD models to produce more accurate and plausible survival extrapolation that accounts for general population mortality. Excess hazard (EH) methods have been suggested as an approach to incorporate background mortality rates in economic evaluation using survival extrapolation.We highlight that EH models with or without a cure assumption can produce more accurate survival projections and significantly reduce between-model variability in comparison with standard parametric distribution models across cancer stages.EH models may be a preferred modeling method to reduce model uncertainty in health economic modeling since models that would otherwise have produced implausible extrapolations are constrained by the EH framework.Reduced uncertainty in economic evaluations will enhance the application of evidence-based health care decision making.

First Red List of Ecosystems assessment of a tropical glacier ecosystem to diagnose the pathways towards imminent collapse

Abstract Tropical glaciers are rapidly disappearing, particularly in isolated mountain peaks below 5,000 m elevation. These glaciers are fundamental substrates for unique cryogenic ecosystems in high tropical environments where the ice, melting water and rocky substrate sustain microbiological communities and other meso- and macro-biota. This study uses the Red List of Ecosystems guidelines to diagnose the collapse of the tropical glacier ecosystem of the Cordillera de Mérida, Venezuela. We undertook the assessment with existing estimates of glacier ice extent, indirect historical estimates of ice mass balance and global mechanistic models of future ice mass balance. We complemented these with additional statistical analysis of trends and bioclimatic suitability modelling to calculate and predict rates of decline and relative severity of degradation in selected ecosystem indicators. The evidence suggests an extreme risk of collapse (Critically Endangered) because of a prolonged and acute reduction in ice extent and changes in climatic conditions that are leading to the complete loss of ice mass. The ice substrate has declined 90% in the last 20 years, and observed acceleration of the rate of decline suggests it will probably disappear within the next 5 years. Loss of ice substrate will trigger an immediate loss of supraglacial, englacial and subglacial biotic compartments and initiate a decades-long succession of forefield vegetation. However, ongoing inventories of native biota and monitoring of ecosystem transitions can provide valuable insights and lessons for other ecosystems facing similar risks. The Red List of Ecosystems assessment protocol provides a useful framework for comparative analysis of cryogenic ecosystems.

Effect of Fintech on Sustainable Development Goals: An Empirical Analysis

Abstract This paper empirically examines the impact of financial technology (FinTech) and financial inclusion on sustainable development goals (SDGs). The adoption of FinTech has a significant positive effect on key SDGs in developing nations. Specifically, FinTech contributes to reducing income inequality and poverty, while promoting gender equality, access to basic sanitation, clean energy, and education. Additionally, the increasing adoption of FinTech is linked to overall economic growth. To address potential biases from heteroscedasticity and endogeneity, we conduct robustness checks using simultaneous equation modeling and Poisson pseudo-maximum likelihood estimations. Our findings confirm that the benchmark results are robust. JEL Codes: O1, O19, O20, Q01. Keywords: Sustainable Development Goals, SDG, Fintech, Financial Inclusion, Pseudo – Poisson Maximum Likelihood (PPML), Simultaneous Equations Model (SEM).

Probabilistic Record Linkage for Families (PRLF): A Discussion of the Development and Validation of this Open-Source Linkage Tool

Linking administrative records across programs can yield person-centered information, including client characteristics, public service trajectories, and outcomes and help to answer policy-related questions. Several solutions are available for undertaking record linkage, producing linkage keys for merging data sources for positively matched pairs of records. In this session, we will demonstrate a new application of the Python RecordLinkage package to family-based record linkages with machine learning algorithms for probability scoring, which we call probabilistic record linkage for families (PRLF). First, we will demonstrate the utility of PRLF with a simulation of administrative records and assess linkage accuracy with variations in match rates and data degradation. Second, we will compare generalized linear model estimates across three record linkage solutions (PRLF, ChoiceMaker, and Link Plus). Findings from the simulation study indicate linkage accuracy is largely influenced by degradation (e.g., missing data fields, erroneous or incomplete values) compared to the proportion of simulated matches between datasets. Results from the methods comparison using real world data indicate that all three solutions, when optimized, provide similar results for researchers. We discuss the strengths of our process, such as the use of ensemble methods, to improve match accuracy. We then will identify caveats of record linkage in the context of administrative data. The tool was developed in Python to allow for researchers to work with open-source software and adjust the basic workflow to fit their linkage needs. We will identify several partnerships where this collaboration has worked successfully and empower attendees with access to this useful tool.

Internal rates of return for public R&D from VECM estimates for 17 OECD Countries

Public R&D stimulates domestic private and foreign private and public R&D, together enhancing technical change and thereby GDP. In this paper, we evaluate vector-error-correction model (VECM) estimations and simulations of a companion paper in regard to internal rates of return (and related aspects) to additional public R&D of OECD countries and compare them to the macroeconomic literature. We show (i) internal rates of return to public R&D shocks, and (ii) the related payback periods, gain/GDP ratios, and sums of discounted (at 4%) gains. Fourteen of 17 countries show high internal rates of return, short payback periods, and high gains/GDP ratios from positive public R&D shocks if projects are stopped when gains get negative. Three countries show crowding-out effects and require (initial) reductions of public R&D before showing positive results.

Linear and nonlinear models for assessing carcass composition using dual X-ray absorptiometry in egg- and meat-type chickens

The objective of this study was to develop appropriate correction equations for dual energy X-ray absorptiometry (DXA) for total carcass composition of live meat- and egg-type chickens. Linear (bivariate linear and multivariate linear) and nonlinear (polynomial, multivariate polynomial, broken-line and Gompertz) equations were used to estimate carcass composition of DXA-scanned birds based on chemical proximate analysis. A total of 288 laying females (10-30 wk of age) and 305 broiler breeder females (4-32 wk of age) were used. The same birds scanned by DXA were dissected and utilized for whole-body proximate chemical analysis for body lean, fat, and mineral content (ash). As indicators of carcass fat and lean, abdominal fat pad and breast muscle weights were also recorded. Models were evaluated using root mean square error (RMSE), Bayesian Information Criterion (BIC), coefficient of determination (R2), Durbin Watson test for autocorrelation (DW), and residuals observation (RES). Model estimations were done separately by strain or combined. Estimations of composition responses fit at least 1 of each linear and nonlinear models for the egg- and meat-type chickens on all parameters estimated (P < 0.05). In the egg-type chickens, multivariate linear regression was the best fit for body lean with the lowest RMSE and BIC, and highest R2 whereas body fat, body ash, and breast muscle were best predicted by the multivariate polynomial model. In the meat-type chickens, body lean was best predicted by the multivariate linear model with the lowest RMSE and BIC, and the highest R2 whereas the multivariate polynomial was the most parsimonious model for body fat, body ash, and abdominal fat. Positive autocorrelations were observed in several models tested for body fat, body ash, breast muscle, and abdominal fat pad when both strains were analyzed combined (P < 0.05). In summary, a strain-based correction is recommended to all the parameters, with exception of the BW estimation. Correction equations developed in this study demonstrated that the DXA technique is a reliable alternative to proximate chemical analysis in egg- and meat-type chickens.

Reconstruction of the social cash transfers system in Poland and household wellbeing: 2015–2018 evidence

This study examines the impact of changes in the social benefits system on the wellbeing, poverty, and economic activity in Poland. The core element of those changes was a programme of large cash transfers, referred to as Family 500+, introduced in 2016. It was intended to support families with children, especially the least affluent ones, and to foster fertility. The impact of the transfers has been examined through the observation of changes in the monetary and multidimensional wellbeing of households. The study also analysed the changes in recipients’ economic activity using estimates of regression models and treatment effects. The Family 500+ programme proved to be successful as an anti-poverty tool and also resulted in the increase in the average wellbeing for the whole population. However, its side-effects included the fall in the economic activity of some recipients, especially in 2016 and 2017. The above trends partly reversed in 2018. As some income data in the lower parts of the distribution seemed to be flawed, income imputations, based on regression on income correlates, were applied in the study.

Reproductive intentions of Russians in 2022—2023: Тhe role of subjective factors

This study examines how the reproductive intentions of Russians changed during the socio-economic shocks in 2022—2023 basing on the data from a representative survey of respondents of reproductive age conducted in May 2023. We used multiple-choice models to identify the factors that influenced changes in fertility decisions. Most individuals who had planned to have children before the crisis did not change their plans (60.2%), 9.5% of respondents decided not to have children, while, on the contrary, 9.2% decided to have children earlier. The rest of the respondents postponed having children. The econometric model included both objective and subjective characteristics of respondents. Objective factors included income, housing availability, health, family status, and the presence of children. Subjective factors comprised emotions such as anxiety, fear, appeasement, happiness, and attitude to the political course of the country. The study found that psychological factors played a more significant role in decision-making. Anxiety and fear as well as disagreement with the country’s political course led respondents to postpone having children for an indefinite period. Conversely, a positive emotional background and the presence of a partner encouraged respondents to have children earlier. The decision not to have children was mainly explained by physiological limitations and attitudes to political course, while the income and emotional indicators had a more minor but significant influence. The results of model estimates are consistent with the cluster analysis of answers to the openended question about changes in reproductive intentions. We also discovered significant differences in decision-making for respondents before and after the age of 30 as well as for those with and without children. A series of demographic and social policy recommendations are suggested.

Improved Liu-ridge-type estimates for the beta regression model

The main objective of this paper is to introduce a new class of estimators for the ill-conditioned beta regression model. The new class, named the Liu-ridge-type (LRT), incorporates two shrinkage parameters that allow it to include the maximum-likelihood estimator (MLE), the ridge estimator (RE), and the Liu estimator (LE) as special cases. The LRT estimator has been shown to outperform the LE, the RE, and the MLE in terms of the mean squared error (MSE) matrix under certain conditions. Simulated and real applications illustrate the potential benefits of the new LRT estimator.

Inflation, exchange rate, and economic growth in Ethiopia: A time series analysis

This study aims to investigate the dynamic relationship between inflation, exchange rate, and economic growth in Ethiopia for the period 1991–2020. This is because of rampant inflation, continuously devalued domestic currency, and the declining growth rate of the country due to violent conflicts. The study uses the ARDL model for short-run and long-run dynamics, the Bound test of co-integration to confirm if the target variables go together or not, and Granger causality tests are performed to detect dynamic effects. The ARDL model estimates suggested that inflation and exchange rate are negatively related to economic growth. This implies that an increase in the price level reduces the production of goods and services, while devaluation has a negative impact by reducing imports of intermediate goods. Thus, increasing domestic resource mobilization, improving regulatory quality, and deepening the financial sector can be viewed as solutions to decrease chronic foreign exchange shortages, lower inflation, and boost economic growth rates.

Machine learning models for estimating the compressive strength of rubberized concrete subjected to elevated temperature: Optimization and hyper-tuning

The incorporation of rubber fibers (RFs) brings about significant divergence in the characteristics of rubberized concrete when contrasted with traditional varieties. Thus, raising concerns about performance under elevated temperature and prolonged exposure. This study effectively addresses the challenges of incorporating rubber fibers in concrete by using artificial neural network (ANN), gene expression programming (GEP), and bagging to examine the impact of input factors such as water-to-cement ratio (W/C), rubber fiber content (RF), elevated temperature (T), and exposure duration (t) on air-cooled compressive strength (CSA). The comprehensive literature review and advanced modeling techniques reveal that ANN excels in capturing complex relationships. In addition, GEP provides clear and accurate models through its unique approach, and Bagging enhances model stability and accuracy. These methods together offer a robust framework for estimating the CSA of rubberized concrete. Thus, contributing valuable insights for optimizing its use in construction. All three models exhibited strong performance, with the ANN emerging as the most effective choice among the evaluated models. Notably, ANN displayed the highest coefficient of determination (R2) value of 0.984, indicating its superior predictive accuracy compared to both GEP (0.982), and bagging (0.970). Moreover, ANN demonstrated the lowest mean absolute error (MAE) score of 0.621 and root mean square error (RMSE) of 0.867, underscoring its precision in forecasting the CSA of rubberized concrete with minimal deviation from experimental values. In addition, the SHapley Additive exPlaination (SHAP) method is employed to comprehend the model estimations. The ICE and PDP plots demonstrate an initial increase in CSA up to 150°C, followed by a significant decrease as temperature rises. Furthermore, CSA decreases with higher RF contents, and linearly declines with increasing W/C ratio. The SHAP analysis provides clear evidence of the strong negative correlation between T and CSA, along with a negative association with RF. A graphical user interface has been developed to estimate the CSA of rubberized concrete, enabling efficient and user-friendly model interaction without the need for physical experimentation.