Negative Consequences of Dichotomizing Continuous Predictor Variables

Irwin, Julie R.; McClelland, Gary H.

doi:10.1509/jmkr.40.3.366.19237

Cited by 359 publications

(263 citation statements)

References 8 publications

Supporting

Mentioning

250

Contrasting

Unclassified

Order By: Relevance

“…Nevertheless, based on the coefficients of determination, the weekly exercise-volume shared 9.1% and 4.3% of variance with these measures that warranted the further investigation via high-and low exercise-volume grouping. While dichotomization is often criticized in the literature (e.g., Irwin & McClelland, 2003), recent re-evaluations show that the practice proves to be robust and reliable (Iacobucci, Posavac, Kardes, Schneider, & Popovich, 2015a, 2015b. Further, we used the method suggested by Gelman and Park (2008), that may be the most reliable means of dichotomization.…”

Section: Discussionmentioning

confidence: 99%

Is there a link between the volume of physical exercise and emotional intelligence (EQ)?

Gáspár¹,

Soós²,

Szabó³

2017

Polish Psychological Bulletin

View full text Add to dashboard Cite

Abstract:Emotional intelligence (EQ) was linked to sport participation. We report two studies in which we tested the link between exercise volume, defined as weekly hours of exercise, and EQ. Volunteers (n = 64 and n = 84) completed the Wong and Law Emotional Intelligence Scale. In Study I, significant correlations between exercise volume and use-and regulation-of-emotions prompted us to use a posteriori grouping into high-and low exercise-volume groups. The former exhibited better use-of-emotions than the latter (p = .007, d = .87). In Study II, using a priori grouping, we replicated the finding from Study I (p = .001, d = .78), and the groups also differed in "self-emotions appraisal" (p = .05, d = .44) and total EQ (p = .017, d = .54). Since the items measuring the use-of-emotions involve motivational aspects of the EQ, we posit that this dimension is "naturally" linked to exercise volume. Our findings also suggest that self-emotions appraisal and the overall EQ are linked to greater volumes of exercise. These results should provide an incentive for longitudinal studies in this area.

show abstract

Section: Discussionmentioning

confidence: 99%

Is there a link between the volume of physical exercise and emotional intelligence (EQ)?

Gáspár¹,

Soós²,

Szabó³

2017

Polish Psychological Bulletin

View full text Add to dashboard Cite

show abstract

“…For additional problems associated with dichotomization of continuous scores see studies by J. Cohen (1983), Irwin andMcClelland (2003), andMacCallum, Zhang, Preacher, andRucker (2002).…”

Section: Ega and Group Assignmentmentioning

confidence: 99%

Use of the Extreme Groups Approach: A Critical Reexamination and New Recommendations.

Preacher¹,

Rucker²,

MacCallum³

et al. 2005

Psychological Methods

602

491

View full text Add to dashboard Cite

Analysis of continuous variables sometimes proceeds by selecting individuals on the basis of extreme scores of a sample distribution and submitting only those extreme scores to further analysis. This sampling method is known as the extreme groups approach (EGA). EGA is often used to achieve greater statistical power in subsequent hypothesis tests. However, there are several largely unrecognized costs associated with EGA that must be considered. The authors illustrate the effects EGA can have on power, standardized effect size, reliability, model specification, and the interpretability of results. Finally, the authors discuss alternative procedures, as well as possible legitimate uses of EGA. The authors urge researchers, editors, reviewers, and consumers to carefully assess the extent to which EGA is an appropriate tool in their own research and in that of others.

show abstract

“…We thank Peter Vorderer for his collaboration in Study 1 (see also Hartmann & Vorderer, 2010) Cohen, 1983;Irwin & McClelland, 2003), we favored a moderated regression over an ANOVA in order to avoid dichotomization of the empathy variable based on a median split. In the moderated regression, we examined simple slopes by applying the SPSS macro offered by O'Connor (1998).…”

Section: Author Notesmentioning

confidence: 99%

Just a Game? Unjustified Virtual Violence Produces Guilt in Empathetic Players

Hartmann¹,

Toz²,

Brandon³

2010

Media Psychology

109

View full text Add to dashboard Cite

Many avid gamers discount violent conduct in video games as morally insignificant as "it is just a game". However, recent debates among users, regarding video games featuring inappropriate forms of virtual violence, suggest a more complex truth. Two experiments (N 1 = 49, N 2 = 80) examined users' guilt responses in order to explore the moral significance of virtual violence. In both studies, justification of virtual violence and users' trait empathy determined guilt in a structurally similar way to real-world scenarios: people felt guiltier if they engaged in unjustified virtual violence, especially if they were empathetic players. These results show that video games are capable of inducing affective moral responses in users. Accordingly, virtual violence may be considered morally significant action.Keywords: violence, video games, guilt, empathy, justification, morality (Bartle, 2008).Virtual violence may be defined as any behavior intended to do harm to another video game character, who is motivated to avoid the harm-doing (Anderson et al., 2008;Baron & Richardson, 1994). Shooting virtual characters for example, in first-person shooter video games, provides a typical example of virtual violence. While many studies have shown that virtual violence depicted in video games increases aggression in users (Anderson et al., 2010), surprisingly little is known about how users perceive and experience virtual violence themselves (e.g., Scharrer & Leone, 2006, Young & Whitty, 2010.Violent video games are designed for entertainment purposes. Consequently, regular violent game players do not typically feel as though they are doing something wrong when they shoot virtual characters. A frequent argument put forward by avid gamers is that they are well aware that the violence depicted in video games "is not real" (Ladas, 2002). For example, Klimmt, Schmid, Nosper, Vorderer, and Hartmann (2006, see also Whitty, Young, & Goodings, in press) asked avid gamers how they experience virtual violence personally. The majority of players replied that they enjoyed virtual violence as they believe that shooting virtual characters is "just a game" (comparable to chess) and has "nothing to do with killing". This suggests that players maintain a psychologically detached and unaffected stance when playing violent games and that virtual violence is too artificial to be considered morally significant and thus trigger any moral response in the user.RUNNING HEAD: Virtual Violence and Guilt 2 However, Klimmt et al.'s (2006) study suggests that users may also perceive and judge virtual violence in a moral way. In their study, a number of players indicated that they would find it disturbing if they accidentally shot a child, for example, or if painful injuries were depicted in the video game. Related discussion of "inappropriate" virtual violence also exists in the video game community. Many video game-related online blogs and forums recently featured heated debate regarding a mission included in the popular online-role-playing game "...

show abstract

Negative Consequences of Dichotomizing Continuous Predictor Variables

Cited by 359 publications

References 8 publications

Is there a link between the volume of physical exercise and emotional intelligence (EQ)?

Is there a link between the volume of physical exercise and emotional intelligence (EQ)?

Use of the Extreme Groups Approach: A Critical Reexamination and New Recommendations.

Just a Game? Unjustified Virtual Violence Produces Guilt in Empathetic Players

Contact Info

Product

Resources

About