This chapter introduces the basic principles of hypothesis testing. We explain the ideas of the null and alternative hypothesis, and the role of the test statistic in quantifying the discrepancy between the null hypothesis and the observed data sample. The value of the test statistic is used to estimate the probability of incorrectly rejecting the null hypothesis (i.e. the test significance). We also discuss the Type II error probability and the related concept of test power. The process of statistical decision-making for formulated hypotheses is illustrated with the help of simple categorical data, assessed by the goodness-of-fit test. We also touch on the issues of sampling bias, suitable sample sizes, and briefly outline a different approach to exploring our hypotheses using Bayesian statistics. Finally, we discuss the limitations and failures of hypothesis testing in statistical practice and outline improvements to this approach. The methods described in this chapter are accompanied by a carefully-explained guide to the R code needed for their use.

Chapter 8 provides correlations that can be used to solve external flow forced convection problems where an external flow is defined as one where the boundary layer can grow without bound. For flow over a flat plate located sufficiently far from any other surface, the boundary layer is never confined by the presence of another object and therefore continues to grow from the leading edge to the trailing edge. An internal flow is defined as a flow situation where the growth of the boundary layer is confined; that is, the boundary layers can only grow to a certain thickness before being constrained. Internal flows are often encountered in engineering applications (e.g., the flow through tubes or ducts).

This chapter provides a brief introduction to the structural equation model (SEM), which typically postulates more complex relationships between variables than that of linear regression. In SEM, a variable can serve both as a predictor for one or multiple other variables, and also as a response variable, affected by other predictors. The suitability of the SEM can be tested by comparing it with the observed data, and further evaluated by a range of fit indices. We demonstrate the use of the simplest form of SEM, which is equivalent to the formerly used method of path analysis. Finally, we discuss the extent to which we can use structural equation models to identify causal relationships in study systems. The methods described in this chapter are accompanied by a carefully-explained guide to the R code needed for their use, in this case employing the sem package.

In this chapter, we discuss the finite element analysis of several special types of structures: trusses, beams, frames, and plates. These types of structures are defined based on their geometric characteristics and mechanical behavior. From a geometric point of view, these structures can be viewed as objects with lower dimensions: line/curve segments and thin surfaces in the 3-D space. In finite element analysis, special types of elements were created to model the low-dimensional structures on both geometric and mechanics aspects. In this regard, these structural elements can be considered as reduced-order 3-D elasticity elements. The mathematical models and finite element formulations are derived based on such model reductions or simplifications. In this chapter, we demonstrate the finite element analysis procedures for these types of structures by solving three example problems. MATLAB codes for solving the example problems are also presented.

As a process of text-meaning construction, reading entails retrieving the meaning of a word from its graphic form. To do so, the reader must identify the word based on its phonological and morphological information that are encoded in a sequence of graphic symbols that encodes the word. As such, a reader must constantly connect text information with his/her knowledge – be it linguistic or conceptual – stored in memory. In second language (L2) reading, text meanings are constructed by connecting text information in the L2 with stored knowledge of the learner in the first language (L1). Text-meaning construction in L2 reading involves two languages and is jointly constrained by L2 linguistic knowledge and an assortment of L1 resources available to the learner at a given point in time.