China
Africa
Explore chapters and articles related to this topic
Time Series Analysis for Modeling the Transmission of Dengue Disease
Published in Dinesh C. S. Bisht, Mangey Ram, Recent Advances in Time Series Forecasting, 2021
A.M.C.H. Attanayake, S.S.N. Perera
Different time series approaches have different advantages and disadvantages. The applicability of each technique depends on user requirements as well as the properties of the technique. The ARIMA technique is a widely used technique for time series analysis. The main advantage of this technique is it is a univariate technique; therefore, only the data of an interested variable is sufficient. Furthermore, it adapts with any frequency of data: daily, weekly, monthly or yearly, etc. The main disadvantage of the technique is that reliability of the selected model is highly dependant on the skills and experience of the modeler. Generally, the ARIMA technique is poor in predicting turning points and peaks and not appropriate in long-term forecasting. In addition, it is a challenging task to satisfy all the underlying assumptions. The ARIMA technique outlined in this chapter will provide a benchmark for other analysis.
Evaluation and Incorporation of Uncertainties in Geotechnical Engineering
Published in Chong Tang, Kok-Kwang Phoon, Model Uncertainties in Foundation Design, 2021
Two main statistical methods can be used to analyse the population: descriptive and inferential. Descriptive statistics are summary statistics that quantitatively describe the features of the population. Univariate analysis aims to describe the distribution of a single variable, including its central tendency or location (e.g. mean, median and mode) and variability or dispersion (e.g. range, coefficient of variation (COV), skewness and kurtosis). Unlike descriptive statistics that are solely concerned with properties of the population, inferential statistics make propositions about the population based on a study of a sample taken from the population. There are two main methods of inferential statistics: (1) estimation of the parameters (e.g. mean and COV) that can be done by constructing confidence interval – range of values in which the true population parameters are likely to fall and (2) hypothesis testing (also known as significance testing) that involves determining whether the difference in the means of two samples is statistically significant. Verification of randomness and identification of the probability distribution of a model factor are usually implemented by hypothesis testing. Details on descriptive and inferential statistics can be found in Bernstein and Bernstein (1999a, b).
General introduction
Published in Adedeji B. Badiru, Handbook of Industrial and Systems Engineering, 2013
A multivariate analysis is a step beyond univariate analysis and utilizes more than one variable at the same time to explain and divide the population under study. Variables used as input can be of several forms, and cluster analysis is often that further step from a univariate classification (TargetPro Version 4.5, 2003). Prepackaged approaches to multivariate statistical clustering use a customized version of non-hierarchical cluster analysis, known variously as "iterative centroidal relocation" or "K-means clustering." This approach adjusts in multidimensional space the definition of a fixed number of clusters until a criterion involving "sums of squared distances" is minimized. The computer tests a number of different classifications and searches for a set that maximizes the similarity of the objects assigned to the same cluster, and at the same time, maximizes the statistical distances or differences between individual clusters.
Data Science with Semantic Technologies: Application to Information Systems Development
Published in Journal of Computer Information Systems, 2023
The process makes use of one or several data science techniques. These latter may be classified into the following categories:90Techniques based on mathematics and statistics encompassing those related to regression, dispersion, density estimation, central tendency, discriminant, and time-series analysis.Techniques based on artificial intelligence and machine learning including neural networks, decision trees, evolutionary programming, and fuzzy logic.Techniques based on visualization and graphs are suitable for univariate analysis such as distribution and box plots, for bivariate analysis such as line, bar, and scatter plots and for multivariate analysis such as star plots and pixel-oriented representations.
Time to signal distribution of multivariate bayesian control chart with dual sampling scheme
Published in International Journal of Production Research, 2022
Control charts are typically considered as powerful techniques in the statistical process control (SPC) applied extensively in manufacturing and industries for monitoring a process over time to ensure the process stability; identify occurrence of assignable causes; and reduce the waste in the process, leading to significant reduction in the overall production cost and improvement of the products' quality. Depending on the number of quality characteristics to be monitored, control charts can be classified into the following two main categories: (i) Univariate control charts, which are widely used to monitor a single quality characteristic, and; (ii) Multivariate control charts, which are used to simultaneously monitor several quality characteristics. A major problem with the former category (univariate control charts) is that for monitoring each variable of a typically multivariate output process, implementation of a large number of control charts is required rendering this approach impractical. Furthermore, applying univariate control charts for monitoring highly correlated data leads to inaccurate results. To address the aforementioned problems, multivariate control charts (the focus of this paper) have been introduced into the quality control literature to monitor several quality characteristics simultaneously.
A step-up approach for selecting substitute suppliers under nonlinear profile data
Published in Quality Technology & Quantitative Management, 2021
Supplier selection is one of the key activities in supplier relationship management. Procuring parts from qualified suppliers can increase buyer companies’ competitiveness (Chen et al., 2020; Glock et al., 2017). Many Process Capability Index (PCI) based methods have been developed to select the suppliers with the higher process capability. Most of the studies focused on analyzing quality characteristics that can be represented by univariate or multivariate distributions. For comparing two suppliers, several difference statistics and ratio statistics were proposed to test the superiority of one supplier’s parts over another’s (Pearn et al., 2019; Pearn & Wu, 2013; Wu et al., 2013). For evaluating more than two suppliers, several group selection methods were proposed to select a subset of suppliers containing the best among several suppliers (C.J. Lin & Shen, 2017; Lin & Kuo, 2014; Lin et al., 2018). However, as Pearn et al. (2018) pointed out, the Multiple Comparisons with the Best (MCB) method and the modified Bonferroni method cannot outperform each other in all circumstances, which showed the difficulty of group selection.