ANCOVA Versus CHANGE From Baseline in Nonrandomized Studies: The Difference

The pretest-posttest control group design can be analyzed with the posttest as dependent variable and the pretest as covariate (ANCOVA) or with the difference between posttest and pretest as dependent variable (CHANGE). These 2 methods can give contradictory results if groups differ at pretest, a phenomenon that is known as Lord's paradox. Literature claims that ANCOVA is preferable if treatment assignment is based on randomization or on the pretest and questionable for preexisting groups. Some literature suggests that Lord's paradox has to do with measurement error in the pretest. This article shows two new things: First, the claims are confirmed by proving the mathematical equivalence of ANCOVA to a repeated measures model without group effect at pretest. Second, correction for measurement error in the pretest is shown to lead back to ANCOVA or to CHANGE, depending on the assumed absence or presence of a true group difference at pretest. These two new theoretical results are illustrated with multilevel (mixed) regression and structural equation modeling of data from two studies.     

A comparison of subset selection and analysis of covariance for the adjustment of confounders

Two common methods for adjusting group comparisons for differences in the distribution of confounders, namely analysis of covariance (ANCOVA) and subset selection, are compared using real examples from neuropsychology, theory, and simulations. ANCOVA has potential pitfalls, but the blanket rejection of the method in some areas of empirical psychology is not justified. Assumptions of the methods are reviewed, with issues of selection bias, nonlinearity, and interaction emphasized. Advantages of ANCOVA include better power, improved ability to detect and estimate interactions, and the availability of extensions to deal with measurement error in the covariates. Forms of ANCOVA are advocated that relax the standard assumption of linearity between the outcome and covariates. Specifically, a version of ANCOVA that models the relationship between the covariate and the outcome through cubic spline with fixed knots outperforms other methods in simulations.     

Common Misconceptions Concerning The Analysis Of Covariance

Four misconceptions about the requirements for proper use of analysis of covariance (ANCOVA) are examined by means of Monte Carlo simulation. Conclusions are that ANCOVA does not require covariates to be measured without error, that ANCOVA can be used effectively to adjust for initial group differences that result from nonrandom assignment which is dependent on observed covariate scores, that ANCOVA does not provide unbiased estimates of true treatment effects where initial group differences are due to nonrandom assignment which is dependent on the true latent covariable if the covariate contains measurement error, and that ANCOVA requires no assumption concerning the equality of within-groups and between-groups regression. Where treatments actually influence covariate scores, the hypothesis tested by ANCOVA concerns a weighted combination of effects on covariate and dependent variables.     

Biblical authority and the not-so strange silence of Scripture about abortion.

Biblical authority is definitive for many Protestants in matters of faith and practice. The question this essay addresses is the deafening silence of this Scriptural authority on the controversial issue of abortion, especially because Christian scholars have argued vehemently against this practice. In particular, Michael Gorman's recent article 'Why is the New Testament silent about abortion?' raises many substantive issues with implications for the very meaning of authority, faith, and the life of the community. It is contended that elective abortion poses significant substantive issues with which a woman, or couple, must struggle, and that it is inappropriate (perhaps unfaithful) to make such a profound decision according to unfeeling or out-modeled patriarchal rules.     

Editor's Note

Based on experiences since the launching of this journal in 2001, the editorial board structure of Identity has being modified to represent the various substantive areas in which identity research and theory is currently being undertaken. Associate Area Editors have been allocated to ten specifically designated substantive areas that are especially active in the identity field. Associate Area Editors will participate in the review process, by recommending potential reviewers to the Chief Editor (from the Board-at-Large, or from scholars in that area), and by providing a recommendation to the Chief Editor regarding publication of a submission on the basis of reviews. As specified in the front matter of this issue, the Editorial Board will now comprise: a Chief Editor, three Regional Associate Editors, an Associate Area Editor for each substantive area, and a Board at Large. The substantive areas are: ?Applied identity issues ?Gender identity & sexuality ?Identity politics and social construction ?Identity and emerging adulthood (including "youth" and the transition to adulthood) ?Identity development in adulthood ?Psychological perspectives on racial & ethnic identity ?Psychosocial, personal, & ego identity ?Self & social identity ?Sociological perspectives on racial & ethnic identity ?Vocational identity The Editors of Identity welcome submissions of research and theory relevant to, but not limited by, these substantive areas.     

Attention and Executive Function Deficits in Adolescent Sex Offenders

Thirty male adolescent sex offenders and 20 age-matched male adolescents completed an extensive battery of attention and executive function tests. Controls were obtained from adolescents from a socially and economically deprived background, typical of the offending group. The attention battery was based on Mirksy, Anthony, Duncan, Ahearn, and Kellam (1991) and the executive function battery on Kelly (2000a). Successful matching for IQ was not achieved and therefore ANCOVA comparisons were made between the groups, with IQ as the covariate. In attention a highly significant difference was found on the focus-execute factor and a significant difference on the shift factor. In executive function there was a highly significant difference only on the response speed factor. In all cases better abilities were demonstrated by the control group. The importance of thorough neuropsychological investigation in the clinical assessment of this forensic group is supported. The clinical implications of neuropsychological deficits in terms of risk assessment and clinical management are discussed.     

Attention and executive function deficits in adolescent sex offenders.

Thirty male adolescent sex offenders and 20 age-matched male adolescents completed an extensive battery of attention and executive function tests. Controls were obtained from adolescents from a socially and economically deprived background, typical of the offending group. The attention battery was based on Mirksy, Anthony, Duncan, Ahearn, and Kellam (1991) and the executive function battery on Kelly (2000a). Successful matching for IQ was not achieved and therefore ANCOVA comparisons were made between the groups, with IQ as the covariate. In attention a highly significant difference was found on the focus-execute factor and a significant difference on the shift factor. In executive function there was a highly significant difference only on the response speed factor. In all cases better abilities were demonstrated by the control group. The importance of thorough neuropsychological investigation in the clinical assessment of this forensic group is supported. The clinical implications of neuropsychological deficits in terms of risk assessment and clinical management are discussed.     

Quine on Quantification and Existence

Quine's justly famous paper "On What There Is" introduced a criterion of ontological commitment which has been almost universally accepted by analytic philosophers ever since.In this paper I try to unpack some of the substantive and controversial philosophical commitments that are presupposed by this criterion.The aim is not to show that the criterion is incorrect,but merely that it is not as obvious as it is taken to be by many,and that we might have reasons to explore alternative ways of thinking about ontological commitments.     

Specificity of operations in sentence recognition

When we read a sentence do we abstract out its semantic core and discard the surface representation, or is the surface representation an integral part of the encoded sentence? This question was studied by measurement of transfer to a second reading of a sentence of skill acquired in a first encounter with the sentence. The transfer relation was studied when the typography, language, or modality of the first and second embodiments were varied. The results favor a theory that emphasizes recognition in terms of the pattern analyzing operations that are directed at surface lexical representations. A distinction is brought out between operational or procedural memory and substantive or semantic memory. In many cases memory of procedures may be sufficient to recover the information encoded. Stage-wise processing theories do not seem to have place for such notions.     

Online Module for Carrier Screening in Ashkenazi Jewish Individuals Compared with In-Person Genetics Education: A Randomized Controlled Trial

To increase accessibility to genetics services for low-urgency patients seeking Ashkenazi Jewish (AJ) carrier screening, we designed an interactive computer (IC) module that provides pre-test genetics education and allows genetics professionals to order the test without meeting the patients beforehand. We compared this module with in-person genetic counseling (GC) using a randomized trial. AJ individuals were randomized to undergo genetics education via the IC module (n = 26) or GC (n = 28). We compared post-interventional genetics knowledge, perceived genetic risk, and anxiety between the two groups, after accounting for pre-interventional scores, using ANCOVA. Wilcoxon Rank-Sum test was used to compare post-interventional satisfaction. Post-interventional genetics knowledge, risk perception, or anxiety were not significantly different between the two groups after accounting for baseline scores (p = 0.50–0.54), although the data are inconclusive regarding the module’s non-inferiority at a 5% margin. Post-intervention satisfaction scores were generally higher in the GC group than the IC module group. Our IC module has the potential to improve access to clinical genetics services for patients and staff, but it is not suitable for all AJ patients and cannot completely replace the benefits of in-person consultations.     

Burhoe's Second-Hand Influence

Many of us not part of the "old Burhoe gang" are nonetheless deeply influenced by the ideas of Ralph Wendell Burhoe, albeit in indirect ways. This remembrance summarizes six such ways: Three are "procedural" influences, namely (1) that dialogue is most valuable, especially in the science/religion interface, when carried on among those who may not agree; (2) that scholarship is necessary to refine and improve preliminary opinions; and (3) that organizations are crucial to accomplishing the first two tasks. The three "substantive" influences are (4) Burhoe's focus on human values; (5) his work in defining God; and (6) his contribution to defining what it means to be human. As is well known, his emphasis in all three substantive cases was on the power and nuances of biological and social evolution, especially on the dynamics of natural selection.     

What if there were no psychometrics?: constructs, complexity, and measurement

McGrath (2005/this issue) has published a very significant article; it is significant because it examines the substantive issue of construct validity in a simple and informative way, noting the confusions apparent in how constructs and their variables are defined, used, and interpreted within the domain of personality and individual differences. This is a careful, thoughtful, article that quietly proceeds to outline the problems with current thinking and approaches to defining and using constructs in psychology. McGrath also suggests how some of these problems might be addressed. I note that McGrath appears to miss what might be considered an obvious rejoinder to some of his arguments, that is, the use of latent variable and item response theory. Some consideration is given to these arguments. However, a cursory examination shows that although these new methodologies offer many opportunities for new stochastic questionnaire data modeling and the construction of "instant" latent variables, the same problems caused by lack of attention to measurement and meaning remain. I find I am in agreement with many of the author's views and arguments, but I also find myself wondering whether modern psychometrics and individual differences research methods is now so dominated by psychological statisticians that any thought of substantive scientific innovation in this area that deals more properly with measurement and meaning is long gone. I think the answers to the question "What if there was no psychometrics?" would be most illuminating.     

Unity versus multiplicity: a conceptual analysis of the term "self" and its use in personality theories

There is no single answer to the unity-multiplicity problem regarding the self for the simple reason that the term "self" is used by too many different theorists in too many different ways. In fact, there are several important substantive topic areas that need to be distinguished and studied scientifically. The topic areas I examine in this article are reflexivity, unit coherence, agency, and subjectivity. Each of these areas will be evaluated in terms of what it contributes to, and can be interpreted in terms of, the unity-multiplicity issue. It is proposed that we need a more differentiated technical vocabulary if we are to better understand the phenomena we are examining. Matching our technical vocabulary to this empirical detail sharpens the questions being asked and places the empirical facts in better focus. A more elaborate framework of conceptual differentiation provides a better basis for developing an integrated theory.     

"Facilitated consensus," "ethics facilitation," and unsettled cases

In "Consensus, Clinical Decision Making, and Unsettled Cases:' David M. Adams and William J.Winslade' make multiple references to both editions of the American Society of Bioethics and Humanities (ASBH) Core Competencies for Healthcare Ethics Consultation in their discussion of two assumptions that are supposed to be at the heart of the facilitated consensus model's inability to handle unsettled cases; that is, that: 1. Consultants "should maintain a kind of moral impartiality or neutrality throughout the process," "explicitly condemn[ing] anything resembling a substantive 'ethics' recommendation, and 2. "What counts as the proper set of allowable options among which the parties are to deliberate will itself always be clearly discernible' Herein, I argue that neither of these assumptions is required by ASBH's ethics facilitation approach. I then conclude by suggesting that, despite their fundamentally mistaken interpretation of the ASBH approach-perhaps even because of it-Adams and Winslade have made two important contributions to the ethics consultation literature.     

Patients with chronic fatigue syndrome do not score higher on the autism‐spectrum quotient than healthy controls: Comparison with autism spectrum disorder

Clinically, there is an overlap of several symptoms of chronic fatigue syndrome (CFS ) and autism spectrum disorder (ASD ), including fatigue; brain “fog”; cognitive impairments; increased sensitivity to sound, light, and odour; increased pain and tenderness; and impaired emotional contact. Adults with CFS (n = 59) or ASD (n = 50) and healthy controls (HC ; n = 53) were assessed with the Autism‐Spectrum Quotient (AQ ) in a cross‐sectional study. Non‐parametric analysis was used to compare AQ scores among the groups. Univariate analysis of variance (ANCOVA ) was used to identify if age, sex, or diagnostic group influenced the differences in scores. Patients with ASD scored significantly higher on the AQ than the CFS group and the HC group. No differences in AQ scores were found between the CFS and HC groups. AQ results were influenced by the diagnostic group but not by age or sex, according to ANCOVA . Despite clinical observations of symptom overlap between ASD and CFS , adult patients with CFS report few autistic traits in the self‐report instrument, the AQ . The choice of instrument to assess autistic traits may influence the results.     

When does measurement error in covariates impact causal effect estimates? Analytic derivations of different scenarios and an empirical illustration

The average causal treatment effect (ATE) can be estimated from observational data based on covariate adjustment. Even if all confounding covariates are observed, they might not necessarily be reliably measured and may fail to obtain an unbiased ATE estimate. Instead of fallible covariates, the respective latent covariates can be used for covariate adjustment. But is it always necessary to use latent covariates? How well do analysis of covariance (ANCOVA) or propensity score (PS) methods estimate the ATE when latent covariates are used? We first analytically delineate the conditions under which latent instead of fallible covariates are necessary to obtain the ATE. Then we empirically examine the difference between ATE estimates when adjusting for fallible or latent covariates in an applied example. We discuss the issue of fallible covariates within a stochastic theory of causal effects and analyse data of a within-study comparison with recently developed ANCOVA and PS procedures that allow for latent covariates. We show that fallible covariates do not necessarily bias ATE estimates, but point out different scenarios in which adjusting for latent covariates is required. In our empirical application, we demonstrate how latent covariates can be incorporated for ATE estimation in ANCOVA and in PS analysis.     

On specifying the null model for incremental fit indices in structural equation modeling

In structural equation modeling, incremental fit indices are based on the comparison of the fit of a substantive model to that of a null model. The standard null model yields unconstrained estimates of the variance (and mean, if included) of each manifest variable. For many models, however, the standard null model is an improper comparison model. In these cases, incremental fit index values reported automatically by structural modeling software have no interpretation and should be disregarded. The authors explain how to formulate an acceptable, modified null model, predict changes in fit index values accompanying its use, provide examples illustrating effects on fit index values when using such a model, and discuss implications for theory and practice of structural equation modeling.     

Can substantive theorizing really save us from ourselves? A skeptical commentary on Wicker's proposal

This commentary concurs in Wicker's call for more attention to substantive theorizing, but attempts to place that strategic approach within a broader conceptual and methodological context. It presents a perspective that is somewhat more skeptical than Wicker's as to the ultimate potential of research in our field. Specifically, the commentary discusses five themes that Wicker raises in support of the importance and potential value of substantive theorizing, looking at the dark side of each of them as well as at the potential gains. The commentary thus tries to give an appropriate balance of attention to both the limitations and the advantages of substantive theorizing.     

Methodological variables in Web-based research that may affect results: Sample type, monetary incentives, and personal information

There are many methodological differences between Web-based studies, differences that could substantially affect the results. The present study investigated whether sample type, offering payment through a lottery, and requiring participants to enter personal information would affect dropout rates and/or the substantive results in a study of jury decision making in capital cases. Asking participants to enter their e-mail addresses increased dropout rates, and offering payment through a lottery tended to do so as well. Participants offered payment tended to be less likely to give death sentences, and sample type moderated the influence of attitudes toward the death penalty on verdicts.