Search Results

This chapter examines the alternative, behavioral economic models of evaluation. These models include diagnostic elements (differences in response to risk vs. ambiguity, attention to the chances of a positive or negative event, sensitivity to changes in probability as well as optimism or pessimism), elements related to management (expectancy-related and goal-related utilities), as well as outcome evaluations (disappointment, elation, and regret, as well as the experienced disutility of waiting for outcomes to occur). In addition, these models considered other factors that can change evaluations, such as learning and context. The investigation of the neural correlates of these behavioral economic parameters of choice clarified why some irrational violations of the axioms or reasons may occur or even be justified. The chapter also describes other forms of inconsistency in evaluation, beyond mere inconsistency with the economic axioms. These include conflicts between remembered, experienced, predictive, expectancy-related, and goal-related utility.

This chapter describes a framework for selecting appropriate strategies for evaluating model performance and significance. It begins with a review of key concepts, focusing on how primary occurrence data can be presence-only, presence/background, presence/pseudoabsence, or presence/absence as well as factors that may contribute to apparent commission error. It then considers the availability of two pools of occurrence data: one for model calibration and another for evaluation of model predictions. It also discusses strategies for detecting overfitting or sensitivity to bias in model calibration, with particular emphasis on quantification of performance and tests of significance. Finally, it suggests directions for future research as regards model evaluation, highlighting areas in need of theoretical and/or methodological advances.

This chapter discusses the information that should be included when presenting CFA results, including model specification, input data, model estimation, model evaluation, and substantive conclusions. Longitudinal measurement invariance and equivalent models are briefly shown. Finally, multilevel confirmatory factor analysis models are also mentioned.

This chapter considers the practice of modeling ecological niches and estimating geographic distributions. It first introduces the general principles and definitions underlying ecological niche modeling and species distribution modeling, focusing on model calibration and evaluation, before discussing the principal steps to be followed in building niche models. The first task in building a niche model is to collate, process, error-check, and format the data that are necessary as input. Two types of data are required: primary occurrence data documenting known presences (and sometimes absences) of the species, and environmental predictors in the form of raster-format GIS layers summarizing scenopoetic variables that may (or may not) be involved in delineating the ecological requirements of the species. The next step is to use a modeling algorithm to characterize the species’ ecological niche as a function of the environmental variables, followed by model projection and evaluation and finally, model transferability.

The model class is summarized in terms of the properties of specific linear models, including cointegration and equilibrium (error) correction. Model evaluation is based on the associated information taxonomy, for sequential conditioning, exogeneity, invariance, constancy and recursivity, and encompassing. The theory of reduction provides a basis for general‐to‐specific modelling. Test types, modelling strategies, and system estimation are also briefly discussed.

The topic of this chapter is nonlinear model building. Building non‐parametric models is considered first, followed by building various types of parametric nonlinear models. The latter include smooth transition, switching regression, and artificial neural network models. The three stages of model building: specification, estimation and evaluation, are illustrated by a number of empirical examples involving both economic and non‐economic time series and data sets.

Arguments to support validity of most contributions in the field of human–computer interaction are based on detailed results of empirical studies involving cohorts of tested users confronted with a set of tasks performed on a prototype version of an interactive system. This chapter presents how the Interactive Cooperative Objects (ICO) formal models of the entire interactive system can support predictive and summative performance evaluation activities by exploiting the models. Predictive performance evaluation is supported by ICO formal models of interactive systems enriched with perceptive, cognitive, and motoric information about the users. Summative usability evaluation is addressed at the level of the software system, which is able to exhaustively log all the user actions performed on the interactive system The articulation of these two evaluation approaches is demonstrated on a case study from the avionics domain with a step-by-step tutorial on how to apply the approach.

This chapter first analyzes an approach to a complete evaluation of all aspects of a curriculum. Then, it moves on to examine various types of evaluation which focus on specific components of the curriculum.

Impact assessments increasingly rely on models to project the potential impacts of climate change on species distributions. Ecological niche models have become established as an efficient and widely used method for interpolating (and sometimes extrapolating) species’ distributions. They use statistical and machine-learning approaches to relate species’ observations to environmental predictor variables and identify the main environmental determinants of species’ ranges. Based on this estimated species–environment relationship, the species’ potential distribution can be mapped in space (and time). In this chapter, we explain the concept and underlying assumptions of ecological niche models, describe the basic modelling steps using the silvereye (Zosterops lateralis) as a simple real-world example, identify potential sources of uncertainty in underlying data and in the model, and discuss potential limitations as well as latest developments and future perspectives of ecological niche models in a global change context.

This chapter discusses a number of practical evaluation tools used by qualitative research journals. First, the chapter discusses the American Educational Research Association’s “Standards for Reporting on Empirical Social Science Research,” which emphasizes warrantability and transparency. Second, many ideas on reviewing qualitative research are briefly presented. Third, current qualitative research journals that use and those that do not use specific evaluation tools are discussed. The reasons why some journal editors do not use such specific evaluation tools are identified: trust, freedom, the nature of qualitative research, and “it works.” Other journals that use specific review guides are analyzed. This chapter suggests a holistic way of understanding the evaluation of qualitative research by taking three elements (core values, research processes, and key dimensions) into consideration. The seven most commonly used evaluation criteria are discussed: importance to the field, qualities, writing, data analysis, theoretical framework, participant, and impact/readership.