• Corpus ID: 220280168

Causal inference and constructed measures: towards a new model of measurement for psychosocial constructs.

@article{VanderWeele2020CausalIA,
  title={Causal inference and constructed measures: towards a new model of measurement for psychosocial constructs.},
  author={Tyler J. VanderWeele},
  journal={arXiv: Methodology},
  year={2020}
}
Psychosocial constructs can only be assessed indirectly, and measures are typically formed by a combination of indicators that are thought to relate to the construct. Reflective and formative measurement models offer different conceptualizations of the relation between the indicators and what is often a univariate latent variable supposed to correspond in some way to the construct. In this paper, a causal interpretation is proposed of associations between constructed measures and various… 

Figures from this paper

A statistical test to reject the structural interpretation of a latent factor model

TLDR
A statistical test to potentially reject the structural interpretation of a latent factor model is developed and applied to empirical data concerning associations between the Satisfaction with Life Scale and subsequent all-cause mortality, which provides strong evidence against a structural interpretation for a univariate latent underlying the scale.

Limited Functional Form, Misspecification, and Unreliable Interpretations in Psychology and Social Science

The replicability crisis has drawn attention to numerous weaknesses in psychology and social science research practice. In this work we focus on three issues that deserve more attention: The use of

Misspecification and unreliable interpretations in psychology and social science.

TLDR
This work focuses on three issues that cannot be addressed with replication alone, and which deserve more attention: Functional misspecification, structural misspecifying, and unreliable interpretation of results.

Psychometric properties of the EQ-5D-5L for aboriginal Australians: a multi-method study

TLDR
The EQ-5D-5L is a suitable instrument to measure five specific aspects of Aboriginal and Torres Strait Islander HRQoL and potential expansions to the instrument are investigated.

References

SHOWING 1-10 OF 47 REFERENCES

A statistical test to reject the structural interpretation of a latent factor model

TLDR
A statistical test to potentially reject the structural interpretation of a latent factor model is developed and applied to empirical data concerning associations between the Satisfaction with Life Scale and subsequent all-cause mortality, which provides strong evidence against a structural interpretation for a univariate latent underlying the scale.

Constructs, inferences, and mental measurement

Causal inference and longitudinal data: a case study of religion and mental health

TLDR
An introduction to causal inference with longitudinal data is provided and the complexities of analysis and interpretation when exposures can vary over time are discussed, to strengthen research on mental health, religion and health, and in the biomedical and social sciences generally.

On the nature and direction of relationships between constructs and measures.

Theory development typically focuses on relationships among theoretical constructs, placing little emphasis on relationships between constructs and measures. In most cases, constructs are treated as

On Well-defined Hypothetical Interventions in the Potential Outcomes Framework.

TLDR
A hypothetical intervention to set X to x is simply the specification, possibly contrary to fact, of the event or state X=x, such that a hypothetical intervention is well-defined with respect to outcome Y, exposure X, setting X =x, and population P, if for each individual i in populationP, there is a unique value Yx(i) (or distribution of values Yx in the context of stochastic counterfactuals).

Measurement Validity is Fundamentally a Matter of Definition, Not Correlation

Correlations between sets of measurements produced by several measures can be determinative of the validity of these measures only insofar as theories about how these measurements relate in

Measurement as a Normative Practice

Recently, a number of prominent measurement specialists (e.g. Cliff, 1992; Schonemann, 1994) have pondered the lack of progress in the development of convincing solutions to the measurement problems

Outcome-Wide Longitudinal Designs for Causal Inference: A New Template for Empirical Studies

TLDR
It is argued that the outcome-wide longitudinal design has numerous advantages over more traditional studies of single exposure-outcome relationships including results that are less subject to investigator bias, greater potential to report null effects, greater capacity to compare effect sizes, a tremendous gain in the efficiency for the research community, a greater policy relevance, and a more rapid advancement of knowledge.