Reviewers of research reports frequently criticize the choice of statistical methods. While some of these criticisms are well-founded, frequently the use of various parametric methods such as analysis of variance, regression, correlation are faulted because: (a) the sample size is too small, (b) the data may not be normally distributed, or (c) The data are from Likert scales, which are ordinal, so parametric statistics cannot be used. In this paper, I dissect these arguments, and show that many studies, dating back to the 1930s consistently show that parametric statistics are robust with respect to violations of these assumptions. Hence, challenges like those above are unfounded, and parametric methods can be utilized without concern for “getting the wrong answer”.

/pdf/likert-scales-levels-of-measurement-and-the-laws-of-3sz3za9q33.pdf

Likert scales, levels of measurement and the "laws" of statistics.

The current article provides a guideline for conducting factor analysis, a technique used to estimate the population-level factor structure underlying the given sample data. First, the distinction between exploratory and confirmatory factor analyses (EFA and CFA) is briefly discussed; along with this discussion, the notion of principal component analysis and why it does not provide a valid substitute of factor analysis is noted. Second, a step-by-step walk-through of conducting factor analysis is illustrated; through these walk-through instructions, various decisions that need to be made in factor analysis are discussed and recommendations provided. Specifically, suggestions for how to carry out preliminary procedures, EFA, and CFA are provided with SPSS and LISREL syntax examples. Finally, some critical issues concerning the appropriate (and not-so-appropriate) use of factor analysis are discussed along with the discussion of recommended practices.

/pdf/how-to-factor-analyze-your-data-right-do-s-don-ts-and-how-to-1zdh3a9b6b.pdf

How to factor-analyze your data right: do’s, don’ts, and how-to’s.

This article is concerned with the measurement of disclosure in published financial reports. In particular, the use of a disclosure index is examined by reviewing the literature that has made use of this measurement technique. Disclosure indices are extensive lists of selected items which may be disclosed in company reports. Calculating an index score for a particular company can give a measure of the extent of disclosure but not necessarily the quality of the disclosure. Items included in the disclosure index may be weighted in order to take account of the fact that some items are viewed as more important than others. The aim of this article is to bring together and summarise a selection of projects that have employed disclosure indices and to comment on the work carried out to date.

The use of disclosure indices in accounting research: A review article

Although the mere exposure effect has been researched widely, surprisingly little is known about the attitudinal and cognitive effects of message repetition. It was hypothesized that the sequence of topic-relevan t thoughts generated in response to a (repeated) persuasive message would parallel attitude change. To test this prediction, two experiments were conducted. In Experiment 1, individuals heard a communication either zero (control), one, three, or five times in succession, rated their agreement with the advocated position, and listed the message arguments they could recall. In Experiment 2, individuals heard a communication either one, three, or five times, rated their agreement, listed their thoughts, and listed the message arguments they could recall. In both experiments, agreement first increased, then decreased as exposure frequency increased (regardless of the position advocated), but agreement was unrelated to the recall of the message arguments. In Experiment 2, analyses of the listed thoughts revealed that counterargumentation decreased, then increased, whereas topic-irrelevant thinking increased as exposure frequency increased; as expected, only topic-relevant thoughts were related to agreement. These results are interpreted in terms of an attitude-modification model in which repetition and content of a persuasive advocacy affect the type and number of thoughts generated; these thoughts, in turn, affect the attitudinal reaction to the advocacy. In this article, we will consider the atti- using children as well as adults (Heingartner tudinal effects of repeated exposure to per- & Hall, 1974), employing between-subjects suasive communications, an area that has (Moreland & Zajonc, 1976) as well as withingenerated surprisingly little research by social subjects (Crandall, 1972) designs, in field psychologists despite its frequent occurrence (Zajonc & Rajecki, 1969) as well as laborain and importance to everyday life. This area tory (Matlin, 1970) settings, employing picis not well understood (cf. Harrison, 1977), torial magazine advertisements (McCullough in part because most research has focused on & Ostrom, 1974) as well as nonsense syllables

Effects of message repetition and position on cognitive response, recall, and persuasion.

In industrial- and social-psychological research, the variables of interest are often measured by means of Likert-type questionnaires or scales. The internal validity of the conclusions reached in such research directly depends on the reliability (e.g., internal consistency) and the validity of the questionnaires or scales used. Typically, item-analytic procedures have been used to arrive at sets of internally consistent items and subsequently the validity of these scales was investigated by correlating the total scores on them with criteria of interest. In the case of multi-dimensional scales, both the convergent validity of the respective subscales (i.e., the degree to which the items within a particular subscale measure the same uni-dimensional construct), and their discriminant validity (i.e., the degree to which the items in different subscales measure different rather than the same construct) need to be considered. The analyses to investigate internal consistency, convergent validity and discriminant validity cannot proceed in just any order as the analysis of some of these properties presupposes that particular results have been obtained for the other. For example, in the case of multi-dimensional scales it makes little sense to investigate the internal consistency of the total scale by means of Cronbach’s alpha, as this index assumes uni-dimensionality. Green, Lizzits and Mulaik (1977) have shown that items showing

/pdf/an-item-selection-procedure-to-maximise-scale-reliability-4eker7r1hp.pdf

John Gaito

Papers

Measurement scales and statistics: Resurgence of an old misconception.

Unequal intervals and unequal n in trend analyses.