Baron and Kenny’s procedure for determining if an independent variable affects a dependent variable through some mediator is so well known that it is used by authors and requested by reviewers almost reflexively. Many research projects have been terminated early in a research program or later in the review process because the data did not conform to Baron and Kenny’s criteria, impeding theoretical development. While the technical literature has disputed some of Baron and Kenny’s tests, this literature has not diffused to practicing researchers. We present a nontechnical summary of the flaws in the Baron and Kenny logic, some of which have not been previously noted. We provide a decision tree and a step-by-step procedure for testing mediation, classifying its type, and interpreting the implications of findings for theory building and future research.

/pdf/reconsidering-baron-and-kenny-myths-and-truths-about-2nucg9g9ev.pdf

Reconsidering Baron and Kenny: Myths and Truths about Mediation Analysis

Purpose – Partial least squares (PLS) path modeling is a variance-based structural equation modeling (SEM) technique that is widely applied in business and social sciences. Its ability to model composites and factors makes it a formidable statistical tool for new technology research. Recent reviews, discussions, and developments have led to substantial changes in the understanding and use of PLS. The paper aims to discuss these issues. Design/methodology/approach – This paper aggregates new insights and offers a fresh look at PLS path modeling. It presents new developments, such as consistent PLS, confirmatory composite analysis, and the heterotrait-monotrait ratio of correlations. Findings – PLS path modeling is the method of choice if a SEM contains both factors and composites. Novel tests of exact fit make a confirmatory use of PLS path modeling possible. Originality/value – This paper provides updated guidelines of how to use PLS and how to report and interpret its results.

/pdf/using-pls-path-modeling-in-new-technology-research-updated-4mwzhyqaye.pdf

Using PLS path modeling in new technology research: updated guidelines

I describe a test of linear moderated mediation in path analysis based on an interval estimate of the parameter of a function linking the indirect effect to values of a moderator-a parameter that I call the index of moderated mediation. This test can be used for models that integrate moderation and mediation in which the relationship between the indirect effect and the moderator is estimated as linear, including many of the models described by Edwards and Lambert ( 2007 ) and Preacher, Rucker, and Hayes ( 2007 ) as well as extensions of these models to processes involving multiple mediators operating in parallel or in serial. Generalization of the method to latent variable models is straightforward. Three empirical examples describe the computation of the index and the test, and its implementation is illustrated using Mplus and the PROCESS macro for SPSS and SAS.

An Index and Test of Linear Moderated Mediation.

A key aim of social psychology is to understand the psychological processes through which independent variables affect dependent variables in the social domain. This objective has given rise to statistical methods for mediation analysis. In mediation analysis, the significance of the relationship between the independent and dependent variables has been integral in theory testing, being used as a basis to determine (1) whether to proceed with analyses of mediation and (2) whether one or several proposed mediator(s) fully or partially accounts for an effect. Synthesizing past research and offering new arguments, we suggest that the collective evidence raises considerable concern that the focus on the significance between the independent and dependent variables, both before and after mediation tests, is unjustified and can impair theory development and testing. To expand theory involving social psychological processes, we argue that attention in mediation analysis should be shifted towards assessing the magnitude and significance of indirect effects.

http://quantpsy.org/pubs/rucker_preacher_tormala_petty_2011.pdf

Mediation Analysis in Social Psychology: Current Practices and New Recommendations

Consumer Brand Engagement in Social Media: Conceptualization, Scale Development and Validation

Effects of various mass media on political learning during the 1992 presidential campaign are examined via analyses of two voter surveys conducted in different states. Three indicators of political knowledge are compared: differences on issues between parties (Republican vs. Democratic), differences on issues among candidates (Bush vs. Clinton vs. Perot), and personal knowledge about the candidates (Bush, Clinton, and Perot). Campaign media, including both news coverage and special events (conventions, debates), added significantly to the prediction of both kinds of knowledge about the candidates, even after controlling for major demographic variables and for habitual uses of news media. Of the new forms of media campaigning that became prominent in 1992, at least the interview / talk show format apparently added to voter learning about candidates. Television sources of various types tended to contribute more to learning about the candidates, whereas the newspaper was the medium more associated with knowl...

Political Knowledge and the Campaign Media of 1992

Relative contributions of television news and campaign advertising to U.S. voters' knowledge about candidate issue differences are compared. Empirical comparisons are based on interview data from six campaign surveys of voters, in various election settings from 1984 to 1992. In hierarchical regression analyses, after controls for demographic and political interest variables, measures of attention to television news consistently account for a significant increment of slightly more than 2 percent of variance in issue knowledge. Parallel measures representing attention to candidates' televised advertisements produce a much more variable pattern in terms of variance explained in knowledge. Usually the effects of advertisements are less than those of news, and sometimes they are nonsignificant; but in one hotly contested ideological race the informative effect attributable to advertisements exceeds that of TV news. These patterns hold up after further controls for other media use variables, including newspaper reading. A commonly repeated generalization in the political communication literature is Patterson and McClure's (1976) conclusion that voters learn issue information from television advertisements but not from television news. The two assertions are often paired in syntheses of the literature (e.g., Diamond 1978; Diamond and Bates 1984; Graber 1989; Jamieson 1993; Kaid 1981; Kraus and Davis 1981; Nimmo 1978; O'Keefe and Atwood 1981). The study has been cited at least 150 times in academic journals (Social Sciences Citation Index 1976-93), including recent publications by political scientists (Bartels 1993; FinXINSHU ZHAO is assistant professor of journalism and mass communication at the University of North Carolina at Chapel Hill, and STEVEN H. CHAFFEE iS Janet M. Peck Professor of international communication at Stanford University. Public Opinion Quarterly Volume 59:41-65 ? 1995 by the American Association for Public Opinion Research All rights reserved. 0033-362X/95/5901-0006$02.50 This content downloaded from 157.55.39.104 on Sat, 18 Jun 2016 07:11:55 UTC All use subject to http://about.jstor.org/terms 42 Xinshu Zhao and Steven H. Chaffee kel 1993); some mass communication researchers consider it a "classic" of the political campaign literature (Weaver and Drew 1993). Often overlooked when citing Patterson and McClure's conclusions is the limited scope of their study, conducted during a single campaign (Nixon-McGovern, 1972 election) in a single county (Onondaga County, New York). Subsequent voter surveys have sometimes found little correlation between knowledge and attention to political commercials (see, e.g., Drew and Weaver 1991), and others attribute clear learning effects to television news (see, e.g., Bartels 1993; Drew and Reeves 1980; Lasorsa 1986; McLeod and McDonald 1985; Neuman, Just, and Crigler 1992; Sears and Chaffee 1979). Patterson and McClure's result remains prominent in the literature more because it was the first to make an explicit contrast between learning from TV news and ads than because it is consistent with most subsequent studies. The "rule" that ads are important to issue learning while news is not affects both research and practice. Just, Crigler, and Wallach (1990), as one instance, decided in their campaign research not to study television news at all. They concentrated instead on commercials (and on televised debates), citing Patterson and McClure as justification for their design. Diamond and Bates (1984) reported that political campaign managers' beliefs regarding television news and ads are also affected by the Patterson-McClure conclusion, guiding daily decisions in field campaigns. The proposition that ads are more informative than news is not grounded in any general theory (Kraus and Davis 1981, p. 278). Indeed, it runs counter to many people's intuition-a feature that has probably helped attract attention to it. The more common view of political commercials is probably that of the prominent practitioner who called them "the most deceptive, misleading, unfair and untruthful of all advertising" (Ogilvy 1985, pp. 210-13). Broadcast journalists, while criticized on many sides, are generally conscientious reporters who strive to be informative (Halberstam 1979). While local news programs may emphasize trivial events, political campaigns do get considerable TV coverage-partly, perhaps, in response to criticisms of television news following the PattersonMcClure report. To infer that voters do not benefit from following the news on television implies that this extensive professional effort goes for naught. Uncontrolled correlational studies suggest that TV news is less informative about politics than are newspapers, but this result does not hold up with controls for measurement error (Bartels 1993), prior knowledge (Chaffee and Schleuder 1986; Chaffee, Ward, and Tipton 1970), or questioning about "attention" to TV news rather than mere frequency of exposure (Chaffee and Schleuder 1986; McLeod and McDonald 1985). Still, empirical comparisons of ads versus news This content downloaded from 157.55.39.104 on Sat, 18 Jun 2016 07:11:55 UTC All use subject to http://about.jstor.org/terms Campaign Ads vs. TV News as Information Sources 43 effects have been outnumbered in the literature by repetition of Patterson and McClure's conclusions, such as their assertion (1976, p. 54) that network TV news is "simply not informative." Few surveys have asked parallel questions about TV news and ads, so that any doubt a given study might cast on one part of the contrast does not extend to the other.' Almost all relevant comparisons have been one-campaign (and usually one-locale) studies, potentially as limited in generalizability as was the original. In this article we report a series of surveys intended to test the generalization with data from a variety of election settings, using measures designed to provide a clearer comparison of news versus ads as agencies of voter learning about political issues. Our general method is correlational, and we include here an extensive set of control variables. Individual differences in knowledge might be associated with differential attention to either news or ads for reasons quite apart from the effects of the latter on the former. Knowledgeable people do, it is well established, seek further information in areas where they are already expert (Sears and Freedman 1967). So do well-educated people, and years of schooling is one of several controls that we routinely enter before our tests of specific effects of TV news and ads. We also enter stringent behavioral controls where available, including other kinds of political knowledge (apart from issue positions of candidates) and use of newspapers.

Campaign advertisements versus television news as sources of political issue information

This study examined the moderating effects of product involvement on the effects of humour on memory and attitude towards the advertisement by using multi-year survey (1992 to 1997) of responses to...

Humour effect on memory and attitude: moderating role of product involvement

The main purpose of this study is to explore theoretically and empirically the effects of consumers' different surfing behaviors in terms of advertising effectiveness in the new media context. This study attempts to answer two primary questions: (1) What effect does interactivity have on attitude and memory? (2) What is the role of individual motivation on clicking behavior on the Web site?

In this study, perceived interactivity was also found to influence consumers' attitudes toward the ad and memory for its contents. This finding is consistent with literature about the effects of interaction on attitude and memory. Results of this study showed a positive impact of perceived interactivity on both attitude and memory.

Xinshu Zhao

Papers

Reconsidering Baron and Kenny: Myths and Truths about Mediation Analysis

Political Knowledge and the Campaign Media of 1992

Campaign advertisements versus television news as sources of political issue information

Humour effect on memory and attitude: moderating role of product involvement

Effects of Perceived Interactivity on Web Site Preference and Memory: Role of Personal Motivation