Measurement Models for Reasoned Action Theory (original) (raw)
Related papers
Psychological Methods, 2017
In this issue, Bollen and Diamantopoulos defend causal-formative indicators against several common criticisms leveled by scholars who oppose their use. In doing so, the authors make several convincing assertions: constructs exist independently from their measures; theory determines whether indicators cause or measure latent variables; and reflective and causal-formative indicators are both subject to interpretational confounding. However, despite being a well-reasoned, comprehensive defense of causal-formative indicators, no single article can address all of the issues associated with this debate. Thus, Bollen and Diamantopoulos leave a few fundamental issues unresolved. For example, how can researchers establish the reliability of indicators that may include measurement error? Moreover, how should researchers interpret disturbance terms that capture sources of influence related to both the empirical definition of the latent variable and to the theoretical definition of the construct? Relatedly, how should researchers reconcile the requirement for a census of causal-formative indicators with the knowledge that indicators are likely missing from the empirically estimated latent variable? This commentary develops six related research questions to draw attention to these fundamental issues, and to call for future research that can lead to the development of theory to guide the use of causal-formative indicators.
Individual scores on common factors are required in some applied settings (e.g., business and marketing settings). Common factors are based on reflective indicators, but their scores cannot unambiguously be determined. Therefore, factor score estimates and unit-weighted scales are used in order to provide individual scores. It is shown that these scores are based on treating the reflective indicators as if they were causal-formative indicators. This modification of the causal status of the indicators should be justified. Therefore, the fit of the models implied by factor score estimates and unit-weighted scales should be investigated in order to ascertain the validity of the scores.
IDENTIFYING THE DIRECTIONS OF THE RELATIONSHIPS OF ASSOCIATION BETWEEN THE CONSTRUCTS AND THEIR INDICATORS: AN EMPIRICAL CASE (Atena Editora), 2021
There are two types of models for measuring a construct. A construct is a latent variable when the measurement indicators are influenced by it. In this case, the indicators are called reflected or effect indicators. On the other hand, a construct can be called a composite variable when it is the indicators that condition its behavior. These indicators are called formative or causal. There is disagreement in the literature about the nature of indicators for measuring various constructs. Furthermore, in most empirical work, indicators are assumed to be reflective. The direction of the linear relationship between indicators and their constructs influences the parameter estimates of structural models. An empirical study with categorical data is used to assess the direction of linear relationships. Although the theoretical framework of some constructs used advocates the use of causal indicators, tests of statistical significance pointed out that all indicators in the model are reflected.
Differentiating Between Precursor and Control Variables When Analyzing Reasoned Action Theories
Aids and Behavior, 2010
This paper highlights the distinction between precursor and control variables in the context of reasoned action theory. Here the theory is combined with structural equation modeling to demonstrate how age and past sexual behavior should be situated in a reasoned action analysis. A two wave longitudinal survey sample of African-American adolescents is analyzed where the target behavior is having vaginal sex. Results differ when age and past behavior are used as control variables and when they are correctly used as precursors. Because control variables do not appear in any form of reasoned action theory, this approach to including background variables is not correct when analyzing data sets based on the theoretical axioms of the Theory of Reasoned Action, the Theory of Planned Behavior, or the Integrative Model.
2011
In the social sciences, latent constructs play an important role. They appear as explanatory elements in structural theories, or they are of interest as the outcome of an intervention, for example a support or a preventive programme, a therapy, or a marketing activity. These constructs are typically considered to imply a quantitative latent variable that exists independently of measurement. As a matter of routine, measures of latent variables in the social sciences are treated in the same way as natural scientists handle and utilize their measures. However, in terms of what the concept of measurement is actually about, the social sciences have veered away from the rigorous concept adhered to in the natural sciences. An arbitrary definition of measurement and a multitude of procedures which are deemed appropriate for quantification have resulted in a speculative approach to measurement. Based on a return to the standard definition of measurement and a new conceptualisation of content and construct validity, the social sciences could advance their quantitative research substantially. The Rasch model for measurement plays an important role in this process.
Analyzing Individual and Average Causal Effects via Structural Equation Models
Methodology, 2005
Although both individual and average causal effects are defined in Rubin's approach to causality, in this tradition almost all papers center around learning about the average causal effects. Almost no efforts deal with developing designs and models to learn about individual effects. This paper takes a first step in this direction. In the first and general part, Rubin's concepts of individual and average causal effects are extended replacing Rubin's deterministic potential-outcome variables by the stochastic expected-outcome variables. Based on this extension, in the second and main part specific designs, assumptions and models are introduced which allow identification of (1) the variance of the individual causal effects, (2) the regression of the individual causal effects on the true scores of the pretests, (3) the regression of the individual causal effects on other explanatory variables, and (4) the individual causal effects themselves. Although random assignment of the observational unit to one of the treatment conditions is useful and yields stronger results, much can be achieved with a nonequivalent control group. The simplest design requires two pretests measuring a pretest latent trait that can be interpreted as the expected outcome under control, and two posttests measuring a posttest latent trait: The expected outcome under treatment. The difference between these two latent trait variables is the individual-causal-effect variable, provided some assumptions can be made. These assumptions -which rule out alternative explanations in the Campbellian tradition -imply a single-trait model (a one-factor model) for the untreated control condition in which no treatment takes place, except for change due to measurement error. These assumptions define a testable model. More complex designs and models require four occasions of measurement, two pretest occasions and two posttest occasions. The no-change model for the untreated control condition is then a single-trait-multistate model allowing for measurement error and occasion-specific effects.
Variables that moderate the attitude-behavior relation: Results of a longitudinal survey
Journal of Personality and Social Psychology, 1979
The following factors were hypothesized to moderate the attitude-behavior relation: (a) the behavioral sequence that must be successfully completed prior to the occurrence of the behavior, (b) the time interval between the measurement of attitudes and behavior, (c) attitude change, (d) the respondent's educational level, and (e) the degree of correspondence between attitudinal and behavioral variables. The behaviors investigated were having a child and using oral contraceptives. A stratified random sample of 244 married women in a midwestern urban area was studied during a three-wave, 2-year longitudinal study. Selection of attitudinal and belief measures was guided by the Fishbein model of behavioral intentions. Consistent with the hypotheses, the relations between behavior and both intention and the model's attitudinal and normative components were substantially attenuated by (a) events in the behavioral sequence not under the volitional control of the actor, (b) an increase in the time interval between the measurement of attitudes and behavior from 1 to 2 years, and (c) changes in the model's attitudinal and normative components during the first year. The respondent's educational level did not affect attitudebehavior consistency. Finally, the attitude-behavior correlation increased significantly as the degree of correspondence between the two variables increased. Wicker (1969) concluded his comprehen-and behavioral measures. By assessing both sive review of the attitude-behavior relation variables at corresponding levels of specificity, with the suggestion, "It is considerably more that is, measuring attitude toward the act for likely that attitudes will be unrelated or only the prediction of a specific behavior or measlightly related to overt behaviors than that suring a global attitude toward an object for attitudes will be closely related to actions" the prediction of a multiple-act behavioral (p. 76). Rather than signaling a decrease in criterion, a reasonable degree of predictive research on this topic, pessimistic reviews by accuracy can be obtained (Ajzen & Fishbein,