Preface
Organisation
Acknowledgements
Contents
Part I Applied Statistics and Bayesian Modeling
1 Applied Bayesian Modeling for Assessment of Interpretation Uncertainty in Spatial Domains
1.1 Introduction
1.2 Materials and Methods
1.2.1 Samples
1.2.2 Spatial Domains
1.2.3 Handheld X-Ray Fluorescence Measurement
1.2.4 Statistical Analysis Methods
1.2.4.1 Variable Selection
1.2.4.2 Bayesian Methodology
1.3 Results
1.4 Discussion
References
2 Computing Robust Statistics via an EM Algorithm
2.1 Overview of Estimating Statistical Model Parameters
2.2 Model
2.3 Robust Estimation Based on Our Algorithm
2.4 Standard Error of
2.5 Choice of g
2.6 Simulation Studies
2.7 Applications
2.7.1 Speed of Light
2.7.2 Chem Data
2.7.3 Abbey Data
2.8 Conclusion
Appendix A: Proof of Equation (2.9)
References
3 Determining Risk Factors of Antenatal Care Attendance and its Frequency in Bangladesh: An Application of Count Regression Analysis
3.1 Introduction
3.2 Methods
3.2.1 Data Description
3.2.2 Statistical Models
3.2.3 Model Selection
3.3 Results and Discussion
3.4 Conclusions
References
4 On Propensity Score Methodology
4.1 Propensity Score Methods β Estimating Causal Effects
4.1.1 A Framework to Model Propensity Score Methods
4.2 Methods to Estimate the Effect of Treatment Using Propensity Scores
4.2.1 Matching on the Propensity Scores (Matching)
4.2.1.1 Matching βwithβ or βwithoutβ Replacement
4.2.2 Inverse Probability Weighing
4.2.3 Subclassification
4.2.4 Covariance Adjustment
4.2.5 Diagnostics of Matching, Subclassification and Covariate Adjustment Methods
4.2.5.1 Balance
4.2.5.2 Assessing Balance
4.2.5.3 Estimating Treatment Results
4.2.5.4 Alternate Methods to Estimate the Treatment Effect
4.2.6 Other Issues Identified Associated with Propensity Score Methodologies
4.2.6.1 Misspecification of the Dataset
4.2.6.2 Misspecification of the Matching, Subclassification and Covariate Adjustment Methods
4.3 Probability of Treatment Using Propensity Score Methods
4.3.1 Probability of Treatment Using Regression Methods
4.3.1.1 Logistic Regression
4.3.1.2 Probit Regression
4.3.2 Probability of Treatment Using Decision Trees
4.3.2.1 Generalized Boosted Model
4.3.3 Estimated Probability of Treatment Results
4.4 Propensity Score Methods Applied to Regional Centres
4.5 Concluding Remarks
References
5 Asking Good Questions to Understand Voluntary Enrolments in Mathematics
5.1 Introduction
5.2 Motivation Model
5.3 Model Components
5.3.1 Self-Concept and Self-Efficacy in Mathematics
5.3.2 Subjective Task Values
5.3.3 Maths Anxiety
5.3.4 From Constructs to Items
5.4 Pilot Study and Validation
5.4.1 Participants
5.4.2 Procedure
5.4.3 Results
5.5 Remarks
References
Part II Agricultural Statistics and Policy Analysis
6 Modeling for Prospect of Aman Rice Production in Dhaka Division, Bangladesh
6.1 Introduction
6.1.1 Objective of the Study
6.1.2 Literature Review
6.2 The Methodology and Model
6.3 Results and Discussion
6.4 Conclusion
6.4.1 Required Model
6.4.2 Forecasting
6.4.3 Summary
References
7 Impacts and Determinants of Adoption in River-Based Tilapia Cage Culture
7.1 Introduction
7.2 Methodology
7.2.1 Data Sources
7.2.2 Analytical Techniques
7.2.2.1 Factors Affecting Adoption
7.2.2.2 Impact Assessment
7.3 Results and Discussion
7.3.1 Descriptive Statistics of the Variables Used in the Models
7.3.2 Adoption Status of Improve Practices
7.3.3 Factors Affecting Adoption
7.3.4 Cost and Return of Cage Cultivation
7.3.5 Impact of Improve Cage Culture Practices Adoption
7.3.5.1 Impact on Productivity
7.3.5.2 Impact on Profitability
7.4 Conclusions and Policy Implications
References
8 Policy into Practice; Statistics the Forgotten Gatekeeper
8.1 Background
8.1.1 The Carbon Farming Initiative
8.1.2 Sequestering Soil Carbon
8.1.3 Testing Policy
8.2 Methods
8.2.1 Partnerships
8.2.2 Development of Spatial Classes
8.2.3 Treatment Application
8.2.4 Soil Sampling and Carbon Analysis
8.2.5 Crop Yield
8.2.6 Analysis of Treatment Effects
8.3 Results
8.3.1 Soil Carbon
8.3.2 Yield
8.4 Discussion
8.5 Conclusions
References
9 Nutrient Loading in the River Systems Around Major Cities in Bangladesh: A Quantitative Estimate with Consequences and Potential Recycling Options
9.1 Introduction
9.2 Materials and Methods
9.2.1 Data Collection
9.2.2 Calculation of Nutrient Loading
9.2.3 Determination of Environmental Consequences of Nutrient Loading
9.2.3.1 Fish Production Calculation
9.2.3.2 Property Rent Calculation
9.2.4 Determination of Potential Recycling Options
9.2.5 Calculation of Nutrient Recycling Potential Through Pyrolysis and Co-composting of Organic Waste
9.2.6 Calculation of Nutrient Recycling Potential Through Pyrolysis of Faeces and Use of Biochar as Sorbent to Urine
9.3 Results and Discussion
9.3.1 Waste Disposal Systems in Bangladesh
9.3.2 Human Excreta Disposal Systems in Bangladesh
9.3.3 Nutrient Loading from Organic Waste Disposal
9.3.4 Nutrient Loading from Human Excreta Disposal
9.3.5 Impacts of Nutrient Loading on Aquatic Ecosystems
9.3.6 Proposed Recycling Options
9.3.7 Quantitative Estimate of Nutrient Recycling Using Pyrolysis of Faeces and Sorption of Nutrients from Wastewater with Biochar
9.3.8 Limitation of the Study
9.4 Conclusions and Future Direction of Research
References
10 Analysing Informal Milk Supply Chains Data to Identify Seasonal Occurrences of Antibiotic Residues
10.1 Introduction
10.2 Materials and Methods
10.2.1 Experimental Site
10.2.2 Sample Collection
10.2.3 Antibiotic Residues Analysis
10.2.4 Growth, Identification and Purification of Bacillus subtilis and Preparation of Plates
10.2.5 Screening of Milk Samples for Antibiotic Residues
10.2.6 High Performance Liquid Chromatography (HPLC) Analyses
10.3 Results
10.3.1 Screening of Milk Samples Through Qualitative Field Disc Assay
10.3.2 Occurrence of Ξ²-Lactam at Different Levels of Milk Marketing Chains in Different Seasons of the Year
10.3.3 Amoxicillin
10.3.4 Ampicillin
10.3.5 Penicillin
10.4 Discussion
10.5 Conclusion
References
Part III Data Science and Image Processing Statistics
11 Detection of Vegetation in Environmental Repeat Photography: A New Algorithmic Approach in Data Science
11.1 Introduction
11.2 Dataset
11.3 Proposed Methodology
11.3.1 Image Pre-processing
11.3.2 Image Registration
11.3.2.1 Feature Detection
11.3.2.2 Feature Matching
11.3.2.3 Model Estimation for Transformation
11.3.2.4 Image Transformation
11.3.3 Image Feature Extraction
11.3.3.1 Color Features
11.3.3.2 Texture Features
11.3.4 Classification for Segmentation
11.3.5 Calculating Vegetation Index
11.4 Results
11.5 Conclusion
References
12 Can Data Fusion Increase the Performance of Action Detection in the Dark?
12.1 Introduction
12.2 Prior Work
12.3 The Context Data Fusion in Night-Time Videos
12.3.1 The Motivation
12.3.2 Contextual Data Fusion
12.4 Spatio-Temporal Feature Extraction and Fusion
12.4.1 Motion and Colour Information Cues
12.4.2 Contextual Information Cues
12.4.3 Spatio-Temporal Feature Fusion
12.5 Action-02MCF: 3D Feature-Based Zero-Aliasing Maximum-Margin Correlation Filter
12.6 Experimental Results and Discussion
12.6.1 Actions Dataset and Experimental Set-Up
12.6.2 Experiment No. 1: The Role of Contextual Data Fusion in Terms of Recognition Accuracy
12.6.3 Experiment No. 2: Filter Performance for Action Detection and Localization
12.6.4 Experiment No.3: Quantitative Evaluation of Filter Robustness
12.7 Conclusion
References
13 Data Privacy and Security in the Cloud
13.1 Introduction
13.2 Literature Review
13.2.1 Relevant Technologies & Its Applications
13.2.2 Data Integrity
13.2.3 Data Confidentiality
13.2.4 Data Availability
13.2.5 Privacy Definitions
13.3 Research Significance
13.3.1 Research Gap and Relevant Issues
13.4 Proposed Method
13.5 Investigation Methods and Sample Collection
13.6 Ethical Issues
13.7 Recommendation
13.8 Discussion and Conclusion
References
14 Evaluating Faster-RCNN and YOLOv3 for Target Detection in Multi-sensor Data
14.1 Introduction
14.2 The Contextual Data Fusion in Night-Time Videos
14.2.1 The Motivation
14.2.2 Contextual Data Fusion
14.3 Deep Object Detection
14.4 Experimental Results and Discussion
14.4.1 Multi-sensor Datasets and Experimental Set-Up
14.5 Conclusion
References
15 Wavelet-Based Quantile Density Function Estimation Under Random Censorship
15.1 Introduction
15.2 Wavelet Estimators
15.3 Asymptotic Results
15.3.1 Auxiliary Results
15.4 A Simulation Study
15.5 Conclusion
References
Part IV Health Statistics and Social Policy
16 Factors Associated with Coronary Heart Disease among Elderly People in Different Communities
16.1 Background
16.2 Methods
16.2.1 Study Design
16.2.2 Response Variable
16.2.3 Predictor Variables
16.2.4 Statistical Analyses
16.3 Results
16.3.1 Socio-economic Status
16.3.2 Food Consumption
16.3.3 Risk Factors
16.3.4 Multiple Logistic Regression Model
16.3.5 Hosmer and Lemeshow Goodness of Fit Test
16.4 Discussion
16.5 Conclusion
References
17 Finite Mixture Modelling Approach to Identify Factors Affecting Children Ever Born for 15β49 Year Old Women in Asian Country
17.1 Introduction
17.2 Methods and Materials
17.2.1 Data Sources and Variables
17.2.2 Methods
17.3 Results and Discussion
17.4 Conclusion
References
18 An Assessment of Influencing Factors for Motherhood During Childhood in Bangladesh Using Factor Analysis and Logistic Regression Methods
18.1 Introduction
18.2 Data and Methodology
18.2.1 The Data
18.2.2 Unit of Analysis
18.2.3 Variables
18.2.3.1 Dependent Variable
18.2.3.2 Independent Variables
18.2.4 Methods
18.3 Results and Discussions
18.4 Conclusions and Policy Implications
18.5 Limitations of the Study
References
19 Effect of Women's Education on Skilled Birth Attendants in South and South East Asia: A Cross-Country Assessment on Sustainable Development Goal 3.1
19.1 Introduction
19.2 Materials and Methods
19.2.1 Data Overview
19.2.2 Surveys
19.2.3 Variable
19.2.4 Statistical Analysis
19.3 Results
19.4 Discussion
19.5 Conclusion
References
Part V Small Area Estimation and Spatial Microsimulation
20 Estimation of Child Undernutrition at Disaggregated Administrative Tiers of a North-Eastern District of Bangladesh: An Application of Small Area Estimation Method
20.1 Introduction
20.2 Data Sources
20.2.1 Sunamganj Population and Housing Census (SPHC) Data, 2011
20.2.2 Sunamganj Child Morbidity and Nutrition Survey (SCMNS) Data, 2018
20.3 Statistical Methods
20.4 Results and Discussion
20.4.1 Multilevel Modeling of Child Undernutrition Indicators
20.4.2 Prevalence of Stunting among Under-5 Children in Sunamganj District
20.4.3 Prevalence of Underweight among Under-5 Children in Sunamganj District
20.5 Conclusion
Appendix (Tables 20.8 and 20.9)
References
21 Using a Spatial Farm Microsimulation Model for Australia to Estimate the Impact of an External Shock on Farmer Incomes
21.1 Introduction
21.2 Spatial Microsimulation and Its Application to the Farm
21.3 Data and Methodology
21.3.1 Data
21.3.2 Methodology
21.4 Estimating Poverty Rates and Validation
21.5 Applying an External Shock
21.6 Conclusions
References
22 A Tax Benefit Model for Policy Evaluation in Luxembourg: LuxTaxBen
22.1 Introduction
22.2 Data
22.3 Empirical Framework
22.3.1 Static Micro-simulation Model
22.3.2 Behavioural or Structural Labour Supply Model
22.3.3 An Evaluation of Individual Tax Reform
22.4 Conclusion
References
Part VI Business Analytics and Managements Policy Analysis
23 Finding Significant Determinants and Impacts of Farm-Level Integrated Pest Management Practices Using Statistical Tools
23.1 Introduction
23.2 Methodology
23.2.1 Data Sources
23.2.2 Analytical Techniques
23.2.2.1 Factors Affecting Adoption
23.2.2.2 Impact Assessment
23.3 Results and Discussion
23.3.1 Descriptive Statistics
23.3.2 Adoption of IPM Practices
23.3.3 Factors Affecting Adoption
23.3.4 Impact of IPM on Productivity and Pesticide Application
23.4 Conclusions and Policy Implications
References
24 Consumers Adoption Behavior Prediction through Technology Acceptance Model and Machine Learning Models
24.1 Introduction
24.2 Literature Review and Theory Foundation
24.2.1 Technology Acceptance Theories/Models
24.2.2 Machine Learning in E-Commerce
24.3 Model of O2O Mobile APP Consumers Adoption Behavior
24.3.1 UTAUT
24.3.2 Additional Influencing Factors for the New Proposed Model
24.3.2.1 Information Quality
24.3.2.2 Sales Promotion
24.3.2.3 Consumer Innovativeness
24.4 Machine Learning Based Methods
24.4.1 Linear Discriminant Analysis
24.4.2 Logistic Regression
24.5 Experimental Results and Analysis
24.5.1 What Factors Influence Consumers Adoption Behavior of O2O Mobile APP?
24.5.2 Which Approach of Machine Learning Is Better to Predict Consumers Adoption Behavior of O2O Mobile APP?
24.6 Conclusions
References
25 Shaping the Future of Multidimensional Project Management in Retail Industry Using Statistical and Big-Data Theories
25.1 Introduction
25.2 Research Significance
25.3 Literature Review
25.3.1 Chaos & Complexity
25.3.2 The Theory of Constraints
25.3.3 Cynefin
25.3.4 The Project Management Paradigm
25.4 Current Study
25.5 Research Challenges
25.6 Research Design and Methodological Approach
25.7 Conclusion
References
26 Technical Efficiency and Value Chain Analysis of Potato in a South-East Asian Country
26.1 Introduction
26.2 Methodology
26.2.1 Technical Inefficiency Effect Model
26.3 Results
26.3.1 Demographic Profile
26.3.2 Land Holding Capacity of Household
26.3.2.1 Land of Household
26.3.2.2 Cropping Pattern
26.3.3 Socio Demographic Profile of Traders
26.3.3.1 Profile of Traders
26.3.3.2 Trade Specialization
26.3.3.3 Age and Education of Traders
26.3.3.4 Initial Investments
26.3.3.5 Investment and Assets
26.3.3.6 Source of Investment
26.3.4 Structure of Traditional Potato Retail
26.3.5 Technical Efficiency Measurement
26.3.5.1 Human Labor
26.3.5.2 N Fertilizer
26.3.5.3 K Fertilizer
26.3.5.4 P Fertilizer
26.3.5.5 Pesticide
26.3.5.6 Irrigation
26.3.5.7 Seed
26.3.5.8 Family Size
26.3.5.9 Age
26.3.5.10 Education
26.3.5.11 Occupation
26.3.5.12 Farm Size
26.3.6 Frequency Distribution of Technical Efficiency
26.3.7 Potato Value Chain
26.4 Discussion
26.5 Conclusion
References
27 Modelling and Analysis of Computer Experiments Using a Simple Pendulum Model
27.1 Introduction
27.2 Materials and Methods
27.3 Implementation
27.4 Results and Discussion
27.5 Conclusion
References