ORCID Profile
0000-0003-4960-2259
Current Organisation
The University of Memphis
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Cold Spring Harbor Laboratory
Date: 04-11-2022
DOI: 10.1101/2022.11.03.22281896
Abstract: Malnutrition imposes enormous costs resulting from lost investments in human capital and increased healthcare expenditures. There is a dearth of research focusing on the prediction of women’s body mass index (BMI), and the malnutrition outcomes (underweight, overweight and obesity) in developing countries. This paper attempts to fill out this knowledge gap by predicting the BMI and the risks of malnutrition outcomes for Bangladeshi women of childbearing age from their economic, health, and demographic features. Data from the 2017-18 Bangladesh Demographic and Health Survey and a series of supervised machine learning (SML) techniques are used. Additionally, this study circumvents the imbalanced distribution problem in obesity classification by utilizing an overs ling approach. Study findings demonstrate that support vector machine and k-nearest neighbor are the two best-performing methods in BMI prediction based on coefficient of determination ( R 2 ), root mean square error (RMSE), and mean absolute error (MAE). The combined predictor algorithms consistently yield top specificity, Cohen’s kappa, F1-score, and AUC in classifying the malnutrition status, and their performance is robust to alternative standards. The feature importance ranking based on several nonparametric and combined predictors indicates that socioeconomic status, women’s age, and breastfeeding status are the most important features in predicting women’s nutritional outcomes. Furthermore, the conditional inference trees corroborate that those three features along with the partner’s educational attainment and employment significantly predict malnutrition risks. To the best of our knowledge, this is the first study that predicts BMI and one of the pioneer studies to classify all three malnutrition outcomes for women of childbearing age in Bangladesh, let alone in any lower-middle income country, using SML techniques. Moreover, in the context of Bangladesh, this paper is the first to identify and rank features that are critical in predicting nutritional outcomes using several feature selection algorithms. The estimators from this study predict the outcomes of interest most accurately and efficiently compared to other existing studies in the relevant literature. Therefore, study findings can aid policymakers in designing policy and programmatic approaches to address the double burden of malnutrition among Bangladeshi women, thereby reducing the country’s economic burden.
Publisher: Emerald
Date: 30-08-2021
DOI: 10.1108/IMEFM-03-2021-0124
Abstract: The transformation of coronavirus disease (COVID-19) from a regional health crisis in a Chinese city to a global pandemic has caused severe damage not only to the natural and economic lives of human beings but also to the financial markets. The rapidly pervading and daunting consequences of COVID-19 spread have plummeted the stock markets to their lowest levels in many decades especially in South Asia. This concern motivates us to investigate the stock markets’ response to the COVID-19 pandemic in four South Asian countries: Bangladesh, India, Pakistan and Sri Lanka. This study aims to investigate the causal impact of the number of confirmed COVID-19 cases on stock market returns using panel data of the countries stated above. This study collects and analyzes the daily data on COVID-19 spread and stock market return over the period May 28, 2020 to October 01, 2020. Using Dumitrescu and Hurlin panel Granger non-causality test, the empirical results demonstrate that the COVID-19 spread measured through its daily confirmed cases in a country significantly induces stock market return. This paper cross-validates the results using the pairwise Granger causality test. The empirical results suggest unidirectional causality from COVID-19 to stock market returns, indicating that the spread of COVID-19 has a dominant short-term influence on the stock movements. To the best of the knowledge, this study provides the first empirical insights into the impact of COVID-19 on the stock markets of selected South Asian countries taking the cross-sectional dependence into account. The results are also in line with the findings of other existing literature on COVID-19. Moreover, the results are robust across the two tests used in this study. The findings are equally insightful to the fund managers and investors in South Asian countries. Taking into account the possible impact of COVID-19 on stock markets’ returns, investors can design their optimal portfolios more effectively. This study has another important implication in the sense that the impact of COVID-19 on the stock markets of South Asian countries may have spillover effects on other developing or even developed countries.
Publisher: Public Library of Science (PLoS)
Date: 12-05-2023
DOI: 10.1371/JOURNAL.PONE.0277738
Abstract: Malnutrition imposes enormous costs resulting from lost investments in human capital and increased healthcare expenditures. There is a dearth of research focusing on the prediction of women’s body mass index (BMI) and malnutrition outcomes (underweight, overweight, and obesity) in developing countries. This paper attempts to fill out this knowledge gap by predicting the BMI and the risks of malnutrition outcomes for Bangladeshi women of childbearing age from their economic, health, and demographic features. Data from the 2017–18 Bangladesh Demographic and Health Survey and a series of supervised machine learning (SML) techniques are used. Additionally, this study circumvents the imbalanced distribution problem in obesity classification by utilizing an overs ling approach. Study findings demonstrate that the support vector machine and k-nearest neighbor are the two best-performing methods in BMI prediction based on the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE). The combined predictor algorithms consistently yield top specificity, Cohen’s kappa, F1-score, and AUC in classifying the malnutrition status, and their performance is robust to alternative standards. The feature importance ranking based on several nonparametric and combined predictors indicates that socioeconomic status, women’s age, and breastfeeding status are the most important features in predicting women’s nutritional outcomes. Furthermore, the conditional inference trees corroborate that those three features, along with the partner’s educational attainment and employment status, significantly predict malnutrition risks. To the best of our knowledge, this is the first study that predicts BMI and one of the pioneer studies to classify all three malnutrition outcomes for women of childbearing age in Bangladesh, let alone in any lower-middle income country, using SML techniques. Moreover, in the context of Bangladesh, this paper is the first to identify and rank features that are critical in predicting nutritional outcomes using several feature selection algorithms. The estimators from this study predict the outcomes of interest most accurately and efficiently compared to other existing studies in the relevant literature. Therefore, study findings can aid policymakers in designing policy and programmatic approaches to address the double burden of malnutrition among Bangladeshi women, thereby reducing the country’s economic burden.
No related grants have been discovered for Md. Mohsan Khudri.