Tableplot
A New Tool for Assessing Precise Predictions
Ernest Kwan
1
, Irene R.R. Lu
1
, and Michael Friendly
2
1
Carleton University, Ottawa, Canada,
2
York University, Toronto, Canada
DOI 10.1027/0044-3409.217.1.38
Abstract. In the debate over null hypothesis significance testing, Paul Meehl strongly advocated appraising theories through the gener-
ation and evaluation of precise predictions (e.g., Meehl, 1978). The study of personality structure through the five-factor model (FFM;
McCrae & John, 1992) is an important area of research where one encounters many precise predictions. Extant methods of assessing
such predictions, however, do not allow researchers to examine the outcome of the predictions in great detail. That is, it may be difficult
to determine how estimates fail to match predicted values. As Meehl argued, one must examine how a theory fails to predict in order to
refine and improve the theory. To promote better theory appraisal in FFM research, we present a powerful new tool, called a tableplot
(Kwan, 2008a), that can summarize and clarify factor-analytic results. Specifically, we illustrate how the tableplot enables detailed
appraisal of precise predictions in the FFM.
Keywords: precise predictions, theory appraisal, five-factor model, graphical display, tableplot
In the debate over null hypothesis significance testing
(NHST) Paul Meehl strongly criticized psychology’s use of
NHST for theory testing (e.g., Meehl, 1967, 1978, 1986,
1990, 1997). Meehl’s main concern is that NHST does not
require researchers to carefully generate or examine precise
predictions derived from a substantive theory of interest.
Meehl argued that unless one examines how empirical es-
timates fail to match a theory’s precise predictions, one can
do little to refine or improve the theory.
Despite Meehl’s emphasis on precise predictions, he also
noted that substantive theories in many areas of psychology
cannot generate very precise predictions (e.g., Meehl,
1978). We consider an important exception: personality re-
search through the use of factor-analytic techniques. Par-
ticularly, we refer to the study of personality structure
through the five-factor model (FFM; McCrae & John,
1992) and the associated five-factor theory (FFT; McCrae
& Costa, 1996, 1999). In the FFM there are many parame-
ters with corresponding predicted values (e.g., Rolland,
2002). However, researchers do not adequately examine the
extent to which these estimates match their predicted values
(e.g., McCrae, Zonderman, Costa, Bond, & Paunonen,
1996). According to Meehl, this neglect is detrimental be-
cause it limits the advancement and refinement of FFT.
One clear reason behind the unsatisfactory assessment
of precise predictions in FFM research is the large number
of parameter estimates involved. The FFM has 150 param-
eters (e.g., Costa & McCrae, 1992). Extant methods of as-
sessment include summary indices of fit and significance
tests of such indices (e.g., McCrae et al., 1996; also see the
next section of this paper). If one wishes to examine how
parameter estimates deviate from predicted values, one
must rely on a table of predicted and estimated values (see
Table 1). As one can verify from Table 1, using a table to
compare 300 values can be a challenge, even when supple-
mented by summary statistics. Indeed, several researchers
have discussed the inadequacies of employing tables to in-
terpret quantitative information (e.g., Friendly & Kwan,
2003; Wainer, 1997). Thus, even if one intends to carefully
examine the outcome of precise predictions in the FFM,
one may still find it difficult to do so.
The goal of this paper is to promote better assessment of
precise predictions in FFM research. Recently Kwan
(2008a) proposed a new graphical display, called a table-
plot, for presenting factor analysis results. We illustratehow
the tableplot can be used to help assess precise predictions.
First we examine research on the FFM: We discuss the role
of precise predictions, extant methods for assessing such
predictions, and the limitations of these methods. We then
introduce the tableplot and illustrate how the tableplot fa-
cilitates better assessment of precise predictions in the
FFM. We provide a discussion and conclusion in the last
section.
Precise Predictions in Studies of
Personality
The FFM is commonly operationalized by the Revised
NEO Personality Inventory (NEO PI-R; Costa & McCrae,
1992). The NEO PI-R comprises 240 items that measure
30 facets. These facets relate to five domains (factors) of
personality: Neuroticism, Extraversion, Openness, Agree-
ableness, and Conscientiousness. Factor analysis (FA) esti-
mates the relationship between a facet and a domain; these
Zeitschrift für Psychologie / Journal of Psychology 2009; Vol. 217(1):38–48 © 2009 Hogrefe & Huber Publishers