FIRE: an SPSS program for variable selection in multiple linear regression analysis via the relative importance of predictors

We provide an SPSS program that implements currently recommended techniques and recent developments for selecting variables in multiple linear regression analysis via the relative importance of predictors. The approach consists of: (1) optimally splitting the data for cross-validation, (2) selecting the final set of predictors to be retained in the equation regression, and (3) assessing the behavior of the chosen model using standard indices and procedures. The SPSS syntax, a short manual, and data files related to this article are available as supplemental materials from brm.psychonomic-journals.org/content/supplemental.     

Social interactions as predictors of children's likability and friendship patterns: A multiple regression analysis

The concurrent and predictive validity of four qualitative behavioral classes of social interaction (initiating and receiving positive and negative social interaction) was investigated using sociometric measures of peer acceptance (ratings) and friendship (nominations). Correlational analyses showed significant relationships between behavioral and sociometric measures supporting previous work with preschool populations. Stepwise multiple regression analyses suggested that receiving social interaction from peers best predicted overall acceptance, whereas initiating social interactions best predicted children's friendship patterns. Tentative implications for the behavioral assessment of children's social skills were discussed.The current data were gathered as part of a larger research project concerning social skills assessment and training in children.     

Sample size and multiple regression analysis

Despite the development of procedures for calculating sample size as a function of relevant effect size parameters, rules of thumb tend to persist in designs of multiple regression studies. One explanation for their persistence may be the difficulty in formulating a reasonable a priori value of an effect size to be detected. This article presents methods for calculating effect sizes in multiple regression from a variety of perspectives and also introduces a new method based on an exchangeability structure among predictor variables. No single method is deemed superior, but rather examples show that a combination of methods is likely to be most valuable in many situations. A simulation provides a 2nd explanation for why rules of thumb for choosing sample size have persisted but also shows that the outcome of such underpowered studies will be a literature consisting of seemingly contradictory results.     

Bootstrap methods for comparing independent regression slopes

In this study, we explore the effects of non-normality and heteroscedasticity when testing the hypothesis that the regression lines associated with multiple independent groups have the same slopes. The conventional approach involving the F-test and the t-test (F/t approach) is examined. In addition, we introduce two robust methods which allow simultaneous testing of regression slopes. Our results suggest that the F/t approach is extremely sensitive to violations of assumptions and tends to yield misleading conclusions. The new robust alternatives are recommended for general use.     

Equivalence tests for comparing correlation and regression coefficients

Equivalence tests are an alternative to traditional difference‐based tests for demonstrating a lack of association between two variables. While there are several recent studies investigating equivalence tests for comparing means, little research has been conducted on equivalence methods for evaluating the equivalence or similarity of two correlation coefficients or two regression coefficients. The current project proposes novel tests for evaluating the equivalence of two regression or correlation coefficients derived from the two one‐sided tests (TOST) method (Schuirmann, 1987, J. Pharmacokinet. Biopharm, 15, 657) and an equivalence test by Anderson and Hauck (1983, Stat. Commun., 12, 2663). A simulation study was used to evaluate the performance of these tests and compare them with the common, yet inappropriate, method of assessing equivalence using non‐rejection of the null hypothesis in difference‐based tests. Results demonstrate that equivalence tests have more accurate probabilities of declaring equivalence than difference‐based tests. However, equivalence tests require large sample sizes to ensure adequate power. We recommend the Anderson–Hauck equivalence test over the TOST method for comparing correlation or regression coefficients.     

Hand laterality and cognitive ability: a multiple regression approach

Several different associations between hand laterality and cognitive ability have been proposed. Studies reporting different conclusions vary in their procedures for defining laterality, and several of them rely on measures which are statistically problematic. Previous methods for measuring relative hand skill have not satisfactorily separated the overall level of hand skill, which is a known correlate of cognitive ability, from the asymmetry of its distribution. This paper uses a multiple regression paradigm that separates these two components. Support is found for Leask and Crow's [Trends in Cognitive Sciences, 5 (2001) 513] proposal that average cognitive ability increases monotonically with increasing strength of laterality, regardless of its direction. The small average advantage to dextrals stems from them being more strongly lateralised than sinistrals. The paucity of strong dextrals amongst the very gifted is due to a smaller variance in cognitive ability in this group.     

Dissociating conflict adaptation from feature integration: a multiple regression approach

Congruency effects are typically smaller after incongruent than after congruent trials. One explanation is in terms of higher levels of cognitive control after detection of conflict (conflict adaptation; e.g., M. M. Botvinick, T. S. Braver, D. M. Barch, C. S. Carter, & J. D. Cohen, 2001). An alternative explanation for these results is based on feature repetition and/or integration effects (e.g., B. Hommel, R. W. Proctor, & K.-P. Vu, 2004; U. Mayr, E. Awh, & P. Laurey, 2003). Previous attempts to dissociate feature integration from conflict adaptation focused on a particular subset of the data in which feature transitions were held constant (J. G. Kerns et al., 2004) or in which congruency transitions were held constant (C. Akcay & E. Hazeltine, in press), but this has a number of disadvantages. In this article, the authors present a multiple regression solution for this problem and discuss its possibilities and pitfalls.     

Identifying significant predictors of student evaluations of faculty through hierarchical regression analysis

College teachers' ages and personalities, and students' course grades, gender, enrollment status, academic abilities, and ages were investigated as predictors of student evaluations of faculty. An evaluation form containing 7 items reflecting the personality trait of extraversion and 8 items reflecting teaching effectiveness was used to collect data from 351 undergraduates. Teachers' extraversion (.79) and teachers' ages (-.08) were correlated highest, and students' gender was correlated lowest (.08) with teaching effectiveness. Hierarchical regression revealed that teachers' extraversion was the only significant predictor of student evaluations (beta = .76, p < .001) after controlling for enrollment status, course grades, and student ages.     

A multiple regression analysis of family factors affecting the potential for alcoholism in college students

This study explored the effects of the family system on the potential for alcoholism in college students. Analysis of the data indicated that students' gender, race, and how often they consumed alcohol were unrelated to the potential for alcoholism. However, perceived conflict in the students' family of origin appeared to increase the potential for alcoholism. This finding is consistent with family systems theory, used by many human service professionals as a basis for assessing and treating chemical dependency.     

An individual differences model for multiple regression

A model for multiple regression was developed which allows individual differences to emerge empirically. The model encompasses as special cases several of the previous attempts to improve psychological prediction by deviating from the usual linear multiple regression model. The model is tested with both artificial and real data. The results indicate that the model effectively reduces the variance of the error of prediction, and that the weights obtained are stable over different samples, and, to some extent, over different sets of predictors.This article is based upon a thesis submitted in partial fulfillment of the requirements for the doctoral degree at the University of Illinois. The author thanks Professor Ledyard R Tucker who served as committee chairman and offered considerable support and assistance.     

Computing aspects of power for multiple regression

Rules of thumb for power in multiple regression research abound. Most such rules dictate the necessary sample size, but they are based only upon the number of predictor variables, usually ignoring other critical factors necessary to compute power accurately. Other guides to power in multiple regression typically use approximate rather than precise equations for the underlying distribution; entail complex preparatory computations; require interpolation with tabular presentation formats; run only under software such as Mathmatica or SAS that may not be immediately available to the user; or are sold to the user as parts of power computation packages. In contrast, the program we offer herein is immediately downloadable at no charge, runs under Windows, is interactive, self-explanatory, flexible to fit the user’s own regression problems, and is as accurate as single precision computation ordinarily permits.     

An elicitation method for multiple linear regression models

This paper describes a method of quantifying subjective opinion about a normal linear regression model. Opinion about the regression coefficients and experimental error is elicited and modeled by a multivariate probability distribution (a Bayesian conjugate prior distribution). The distribution model is richly parameterized and various assessment tasks are used to estimate its parameters. These tasks include the revision of opinion in the light of hypothetical data, the assessment of credible intervals, and a task commonly performed in cue-weighting experiments. A new assessment task is also introduced. In addition, implementation of the method in an interactive computer program is described and the method is illustrated with a practical example.     

A simplified method for approximating multiple regression coefficients

A method of exhaustion has been described for calculating regression coefficients. This method dispenses with the solution of simultaneous equations but utilizes a process of successive extraction in obtaining's, where each successive is maximized. This procedure permits the worker to discard as he goes along those weights which are deemed unsatisfactory for purposes of prediction. The coefficients and theR in a problem involving a criterion and six independent variables were calculated in sixty minutes. TheR's obtained by this method are smaller than those yielded by the Doolittle technique, but in problems which have been considered this discrepancy has not exceeded .05.     

Computing aspects of power for multiple regression.

Rules of thumb for power in multiple regression research abound. Most such rules dictate the necessary sample size, but they are based only upon the number of predictor variables, usually ignoring other critical factors necessary to compute power accurately. Other guides to power in multiple regression typically use approximate rather than precise equations for the underlying distribution; entail complex preparatory computations; require interpolation with tabular presentation formats; run only under software such as Mathmatica or SAS that may not be immediately available to the user; or are sold to the user as parts of power computation packages. In contrast, the program we offer herein is immediately downloadable at no charge, runs under Windows, is interactive, self-explanatory, flexible to fit the user's own regression problems, and is as accurate as single precision computation ordinarily permits.     

Two SPSS programs for interpreting multiple regression results

When multiple regression is used in explanation-oriented designs, it is very important to determine both the usefulness of the predictor variables and their relative importance. Standardized regression coefficients are routinely provided by commercial programs. However, they generally function rather poorly as indicators of relative importance, especially in the presence of substantially correlated predictors. We provide two user-friendly SPSS programs that implement currently recommended techniques and recent developments for assessing the relevance of the predictors. The programs also allow the user to take into account the effects of measurement error. The first program, MIMR-Corr.sps, uses a correlation matrix as input, whereas the second program, MIMR-Raw.sps, uses the raw data and computes bootstrap confidence intervals of different statistics. The SPSS syntax, a short manual, and data files related to this article are available as supplemental materials from http:// brm.psychonomic-journals.org/content/supplemental.     

SPSS and SAS programs for comparing Pearson correlations and OLS regression coefficients

Several procedures that use summary data to test hypotheses about Pearson correlations and ordinary least squares regression coefficients have been described in various books and articles. To our knowledge, however, no single resource describes all of the most common tests. Furthermore, many of these tests have not yet been implemented in popular statistical software packages such as SPSS and SAS. In this article, we describe all of the most common tests and provide SPSS and SAS programs to perform them. When they are applicable, our code also computes 100 × (1 ? α)% confidence intervals corresponding to the tests. For testing hypotheses about independent regression coefficients, we demonstrate one method that uses summary data and another that uses raw data (i.e., Potthoff analysis). When the raw data are available, the latter method is preferred, because use of summary data entails some loss of precision due to rounding.     

Modelling monotonic effects of ordinal predictors in Bayesian regression models

Ordinal predictors are commonly used in regression models. They are often incorrectly treated as either nominal or metric, thus under- or overestimating the information contained. Such practices may lead to worse inference and predictions compared to methods which are specifically designed for this purpose. We propose a new method for modelling ordinal predictors that applies in situations in which it is reasonable to assume their effects to be monotonic. The parameterization of such monotonic effects is realized in terms of a scale parameter b representing the direction and size of the effect and a simplex parameter modelling the normalized differences between categories. This ensures that predictions increase or decrease monotonically, while changes between adjacent categories may vary across categories. This formulation generalizes to interaction terms as well as multilevel structures. Monotonic effects may be applied not only to ordinal predictors, but also to other discrete variables for which a monotonic relationship is plausible. In simulation studies we show that the model is well calibrated and, if there is monotonicity present, exhibits predictive performance similar to or even better than other approaches designed to handle ordinal predictors. Using Stan, we developed a Bayesian estimation method for monotonic effects which allows us to incorporate prior information and to check the assumption of monotonicity. We have implemented this method in the R package brms, so that fitting monotonic effects in a fully Bayesian framework is now straightforward.