This text covers R program coding for the implementation of two essential data analytics for practical construction problems. The first part of this book explains time series basics, models, and forecasting approaches in the context of the construction industry, accompanied by practical examples in construction. The second part describes the concept of investment valuation for construction projects and provides both deterministic and probabilistic techniques to conduct investment valuation on construction projects. R code scripts are provided in this book for solving practical problems in the construction industry. This book is also equipped with an R Package entitled “cdar” to provide the necessary functions for performing investment valuation. The book maximizes students’ understanding of the necessary theoretical background of data analytics, and explains the implementation of data analytics techniques to solve the actual problems in the construction industry.
Author(s): Mohsen Shahandashti, Bahram Abediniangerabi, Ehsan Zahed, Sooin Kim
Publisher: Springer
Year: 2023
Language: English
Pages: 178
City: Cham
Contents
Chapter 1: Introduction to Construction Analytics
1.1 The Impacts and Challenges of the Construction Industry
1.2 Construction Analytics for Solving Construction Industry Challenges
1.3 Construction Analytics Techniques: Forecasting and Investment Valuation
1.4 R Language for Implementing Construction Analytics
1.5 Summary
1.6 Exercise Problems
References
Chapter 2: Construction Time Series Forecasting Using Univariate Time Series Models
2.1 Introduction
2.2 Construction Cost Time Series
2.2.1 Example 1: Highway Construction Spending (HCS)
2.2.2 Example 2: National Highway Construction Cost Index (NHCCI)
2.2.3 Example 3: Composite Index of Iowa Highway Construction (IHC)
2.2.4 Example 4: California Construction Cost Index (CCCI)
2.3 Characteristics of Time Series
2.3.1 Stationarity
2.3.2 Seasonality
2.3.3 Trend
2.4 Univariate Time Series Forecasting
2.4.1 Moving Average (MA)
2.4.2 Autoregressive (AR)
2.4.3 Exponential Smoothing (ES)
2.4.4 Autoregressive Moving Average (ARMA)
2.4.5 Autoregressive Integrated Moving Average (ARIMA)
2.4.6 Seasonal Autoregressive Integrated Moving Average (SARIMA)
2.5 Diagnostic Tests for Time Series Models
2.5.1 Diagnostic Tests for No Autocorrelation
2.5.1.1 Ljung-Box Test
2.5.1.2 Autocorrelation Function
2.5.2 Diagnostic Tests for Homoscedasticity
2.5.2.1 ARCH-LM (Autoregressive Conditional Heteroscedasticity-Lagrange Multiplier) Test
2.5.2.2 ACF and Time Plots of Squared Residuals
2.5.3 Diagnostic Tests for Normality
2.5.3.1 Shapiro-Wilk Test
2.5.3.2 Normal Q-Q (Quantile-Quantile) Plot
2.6 Summary
2.7 Problems
References
Chapter 3: Construction Forecasting Using Time Series Volatility Models
3.1 Introduction
3.2 Time Series Volatility Models
3.2.1 Autoregressive Conditional Heteroscedasticity (ARCH)
3.2.2 Generalized Autoregressive Conditional Heteroscedasticity (GARCH)
3.3 Diagnostic Tests for Time Series Volatility Models
3.3.1 Results of Diagnostic Tests for No Autocorrelation
3.3.2 Results of Diagnostic Tests for Homoscedasticity
3.4 Estimating Volatility Using ARCH and GARCH Models
3.5 Forecasting the TFC Time Series Using ARIMA-ARCH and ARIMA-GARCH Models
3.6 Summary
3.7 Exercise Problems
References
Chapter 4: Construction Time Series Forecasting Using Multivariate Time Series Models
4.1 Introduction
4.2 Potential Explanatory Time Series
4.2.1 Stationarity
4.2.2 Granger Causality
4.2.3 Cointegration Test
4.3 Multivariate Forecasting Models
4.3.1 Vector Autoregressive (VAR)
4.3.2 Vector Error Correction (VEC)
4.3.3 Forecasting Errors of VEC Models
4.4 Summary
4.5 Exercise Problems
References
Chapter 5: Construction Forecasting Using Recurrent Neural Networks
5.1 Introduction
5.2 Recurrent Neural Networks
5.3 Model Development Process
5.3.1 Data Preparation
5.3.2 Train and Test Datasets
5.3.3 Data Rescaling
5.3.4 RNN Parameters
5.4 Simple RNNs
5.5 Long Short-Term Memory (LSTM)
5.6 Gated Recurrent Unit (GRU)
5.7 Forecasting Errors of Time Series Models
5.8 Summary
5.9 Exercise Problems
References
Chapter 6: Investment Valuation of Construction Projects Under Uncertainty
6.1 Stochastic Life-Cycle Cost Analysis of Construction Projects
6.2 Life-Cycle Cost Comparison of Alternative Construction Projects
6.3 Real Options Analysis of Construction Projects
6.4 Binomial Tree Model
6.5 Summary
6.6 Exercise Problems
References
Appendix A: Conventional Investment Valuation Techniques for Evaluating Construction Projects
A.1 Cash Flow Analysis
A.1.1 Project Cash Flows
A.1.2 Net Present Value
A.1.3 Future Value
A.1.4 Equivalent Uniform Values
A.2 Life-Cycle Cost Analysis
A.3 Life-Cycle Benefit-Cost Analysis
A.3.1 Benefit-Cost Ratio (BCR)
A.3.2 Net Present Value (NPV)
A.3.3 Internal Rate of Return (IRR)
A.3.4 Breakeven Analysis
A.4 Sensitivity Analysis and Cost Contingencies
A.5 Summary
A.6 Exercise Problems
Appendix B: R and R Package Installation and Helpful Communities
Appendix C
Appendix D
Appendix E
Appendix F
Appendix G
Appendix H
Appendix I
Appendix J
Appendix K
Appendix L
Appendix M
Appendix N
Appendix O
References
Index
