Evaluating Structural Equation Models with Unobservable Variables and Measurement Error

The paper

Fornell & Larcker (1981). Evaluating Structural Equation Models with Unobservable Variables and Measurement Error. Journal of Marketing Research. https://doi.org/10.1177/002224378101800104

The statistical tests used in the analysis of structural equation models with unobservable variables and measurement error are examined. A drawback of the commonly applied chi square test, in addition to the known problems related to sample size and power, is that it may indicate an increasing correspondence between the hypothesized model and the observed data as both the measurement properties and the relationship between constructs decline. Further, and contrary to common assertion, the risk of making a Type II error can be substantial even when the sample size is large. Moreover, the present testing methods are unable to assess a model's explanatory power. To overcome these problems, the authors develop and apply a testing system based on measures of shared variance within the structural model, measurement model, and overall model.

Contribution

validation

Data basis

none

Document

full article

Review stage

peer reviewed

Disciplines

marketing, structural equation modelling

Access

closed

Existing implementations

Code the authors or the community already shipped. This is what decides how far up the ladder a work can climb — no implementation, no tools.

• cransemToolsGPL-2.0-or-laterby Terrence D. Jorgensen, Sunthud Pornprasertmanit, Alexander M. Schoemann, Yves Rosseelruns here

What it can do

• Discriminant validitydiscriminant_validity

  Apply the Fornell-Larcker criterion to every pair of constructs.

• Reliabilityreliability

  Compute average variance extracted and composite reliability per construct.

• Versionsversions

  Report the R and package versions this agent runs, and the paper it implements.

Provenance

Each check stands on its own. There is no single “verified” state: whether an agent faithfully implements its paper is a curation judgement, not something this registry can mechanically prove.

Machine-readable: paper.jsonld · server.json · agent-card.json

Agent: org.agenticjournal/paper-fornell-larcker-1981-validity · v0.2.0