Classification and regression trees are machine-learning methods for constructing prediction models from data. The models are obtained by recursively partitioning the data space and fitting a simple prediction model within each partition. As a result, the partitioning can be represented graphically as a decision tree. Classification trees are designed for dependent variables that take a finite number of unordered values, with prediction error measured in terms of misclassification cost. Regression trees are for dependent variables that take continuous or ordered discrete values, with prediction error typically measured by the squared difference between the observed and predicted values. This article gives an introduction to the subject by reviewing some widely available algorithms and comparing their capabilities, strengths, and weakness in two examples. © 2011 John Wiley & Sons, Inc. WIREs Data Mining Knowl Discov 2011 1 14-23 DOI: 10.1002/widm.8

This article is categorized under: 

Technologies > Classification
Technologies > Machine Learning
Technologies > Prediction
Technologies > Statistical Fundamentals

/pdf/classification-and-regression-trees-1td8f8b4ru.pdf

Classification and regression trees

The metafor package provides functions for conducting meta-analyses in R. The package includes functions for fitting the meta-analytic fixed- and random-effects models and allows for the inclusion of moderators variables (study-level covariates) in these models. Meta-regression analyses with continuous and categorical moderators can be conducted in this way. Functions for the Mantel-Haenszel and Peto's one-step method for meta-analyses of 2 x 2 table data are also available. Finally, the package provides various plot functions (for example, for forest, funnel, and radial plots) and functions for assessing the model fit, for obtaining case diagnostics, and for tests of publication bias.

Conducting Meta-Analyses in R with the metafor Package

In this book, Andrew Harvey sets out to provide a unified and comprehensive theory of structural time series models. Unlike the traditional ARIMA models, structural time series models consist explicitly of unobserved components, such as trends and seasonals, which have a direct interpretation. As a result the model selection methodology associated with structural models is much closer to econometric methodology. The link with econometrics is made even closer by the natural way in which the models can be extended to include explanatory variables and to cope with multivariate time series. From the technical point of view, state space models and the Kalman filter play a key role in the statistical treatment of structural time series models. The book includes a detailed treatment of the Kalman filter. This technique was originally developed in control engineering, but is becoming increasingly important in fields such as economics and operations research. This book is concerned primarily with modelling economic and social time series, and with addressing the special problems which the treatment of such series poses. The properties of the models and the methodological techniques used to select them are illustrated with various applications. These range from the modellling of trends and cycles in US macroeconomic time series to to an evaluation of the effects of seat belt legislation in the UK.

Forecasting, Structural Time Series Models and the Kalman Filter

Statistical Analysis with Missing Data

Past behavior guides future responses through 2 processes. Well-practiced behaviors in constant contexts recur because the processing that initiates and controls their performance becomes automatic. Frequency of past behavior then reflects habit strength and has a direct effect on future performance. Alternately, when behaviors are not well learned or when they are performed in unstable or difficult contexts, conscious decision making is likely to be necessary to initiate and carry out the behavior. Under these conditions, past behavior (along with attitudes and subjective norms) may contribute to intentions, and behavior is guided by intentions. These relations between past behavior and future behavior are substantiated in a meta-analytic synthesis of prior research on behavior prediction and in a primary research investigation. In everyday explanations of behavior, habits denote one's customary ways of behaving. Claiming that one performed a behavior because of habit provides an understandable explanation for an act that otherwise might seem irrational or even harmful. Habits also are featured in the popular psychology literature in the form of self-help books designed to identify readers' existing habits, evaluate habits' effectiveness in meeting goals, and establish more desirable habits. Habits are not, however, important constructs in most contemporary social psychological models of human behavior. Early in their careers, most psychology graduate students learn that frequency of past behavior, a standard indicator of habit strength (Triandis, 1977, 1980), is the best predictor of

/pdf/habit-and-intention-in-everyday-life-the-multiple-processes-1xuobe1ggh.pdf

Habit and intention in everyday life: The multiple processes by which past behavior predicts future behavior.

Although relapse prevention (RP) has become a widely adopted cognitive-behavioral treatment intervention for alcohol, smoking, and other substance use, outcome studies have yielded an inconsistent picture of the efficacy of this approach or conditions for maximal effectiveness. A meta-analysis was performed to evaluate the overall effectiveness of RP and the extent to which certain variables may relate to treatment outcome. Twenty-six published and unpublished studies with 70 hypothesis tests representing a sample of 9,504 participants were included in the analysis. Results indicated that RP was generally effective, particularly for alcohol problems. Additionally, outcome was moderated by several variables. Specifically, RP was most effective when applied to alcohol or polysubstance use disorders, combined with the adjunctive use of medication, and when evaluated immediately following treatment using uncontrolled pre-post tests.

Efficacy of relapse prevention: a meta-analytic review

In a meta-analysis, graphical displays can be used to check statistical assumptions for numerical procedures and they can be used to discover important patterns in the data. The authors propose the normal quantile plot as a preferred alternative to the funnel plot for such purposes. The normal quantile plot, like the funnel plot, can be used to investigate whether all studies come from a single population and to search for publication bias. However, the normal quantile plot is easier to interpret than the funnel plot, especially when it includes 95% confidence bands. In addition, the normal quantile plot can be used to check the normality assumption for numerical procedures. The funnel plot cannot be used for this latter purpose. Most people have heard the phrase, "A picture is worth a thousand words." This phrase seems especially applicable to producers and consumers of metaanalytic reviews. In a meta-analysis, graphical displays (figures, plots) can be used to enhance numerical analyses in at least two ways. First, graphical displays can be used to discover patterns and relations among variables in a meta-analysis. Second, graphical displays can be used to check statistical assumptions on which numerical analyses are based. One of the most popular graphical displays for exploring meta-analytic data sets is the funnel plot (Light & Pillemer, 1984). In this article, we begin by describing the funnel plot and its uses. We then propose the normal quantile plot as a preferred alternative to the funnel plot.

Using the normal quantile plot to explore meta-analytic data sets.

Vote-counting procedures in meta-analysis.

The application of a nonlinear time series model to the prediction of traffic parameters on a freeway network is investigated. The nonlinear time series approach is a statistical technique that has strong potential for on-line implementation. A new approach for predicting corridor travel times is developed and tested with travel-time data. The travel-time data are derived from observed speed data, which are collected from an 18-km (11.2-mi) freeway section in Orlando, Florida. The westbound Interstate-4 morning peak period (6:00 to 10:00 a.m.) for 20 incident-free days is tested with the goal of predicting recurrent congestion. The problem is addressed from the perspectives of single-variable and multiple-variable prediction of corridor travel times. In single-variable prediction, speed time-series data are used to forecast travel times along the freeway corridor. A calibrated single-variable prediction model is developed through the application of decay factors to smooth out the input data and the establ...

Travel-Time Prediction for Freeway Corridors

This paper presents a survey of data mining techniques for malware detection using file features. The techniques are categorized based upon a three tier hierarchy that includes file features, analysis type and detection type. File features are the features extracted from binary programs, analysis type is either static or dynamic, and the detection type is borrowed from intrusion detection as either misuse or anomaly detection. It provides the reader with the major advancement in the malware research using data mining on file features and categorizes the surveyed work based upon the above stated hierarchy. This served as the major contribution of this paper.

Morgan C. Wang

Papers

Efficacy of relapse prevention: a meta-analytic review

Using the normal quantile plot to explore meta-analytic data sets.

Vote-counting procedures in meta-analysis.

Travel-Time Prediction for Freeway Corridors

A survey of data mining techniques for malware detection using file features