Experimental and Quasi-Experimental Designs for Generalized Causal Inference

Shadish, W. R., Cook, T. D., & Campbell, D. T. (2002). Experimental and Quasi-Experimental Designs for Generalized Causal Inference. Houghton Mifflin.

Type

Book

Intellectual base

Review or monograph

Year

2002

ISBN

9780395615560

Link

https://discover.library.unt.edu/catalog/b2480456

Cited from

philosophy, statistics_experimental_design

Cited by

24 citations across 24 artifacts.

Each citation links to the sentence it supports in the citing article.

Primes

• Evidence
  • In science, data are evidence for or against hypotheses, with strength depending on study design (the trace-producing mechanism), replication (independent corroboration), and freedom from confounders (defeaters).

    This sourceTreats the strength of causal evidence as governed by study design and the systematic ruling-out of threats to validity (confounders) — the trace-producing-mechanism and defeater roles in science.

• Experimental Design
  • A design may be internally valid but fail to answer the right question or generalize to the target population, as Shadish, Cook, and Campbell (2002) systematize across the four validity types.

    This sourceSystematizes the four validity types (internal, external, construct, statistical conclusion) and develops design principles for navigating their trade-offs in real-world research.

• Washout Failure
  • In education research, testing a curriculum immediately after a prior intervention conflates the new pedagogy with carryover learning.

    This sourceTreats carryover, testing/practice effects, and period effects as threats to validity in repeated-measures and quasi-experimental designs.

Domain-specific

• Dependent and independent variables
  • Dependent and independent variables is a paired modeling-role distinction between an outcome variable whose variation is explained and an input variable treated as controlled, assigned, or explanatory within a stated scope.
• Statistical Conclusion Validity
  • Shadish, Cook, and Campbell distinguish this from internal validity, which asks whether observed covariation reflects a causal relationship, and from construct and external validity.

Mechanisms

• Before/After Analysis
  • Its central failure is the post hoc trap: because the change and the outcome are separated only by time

    This sourceShows that a one-group pretest–posttest difference can arise from maturation or history rather than the intervention.

• Before/After Constraint Monitoring
  • Its central failure mode is misattribution — crediting the relief for an improvement that was really regression to the mean
• Boundary Case Probe
  • Its strength is converting a vague "well, it depends" into named, defensible scope conditions

    This sourceTreats explicit scope conditions as distinguishing where a model applies and preventing quiet overreach.

• Control Group Design
  • The discipline is to pre-specify the control and confirm comparability on the key confounders before any outcome is known — protecting against the internal-validity threats a single-arm before/after study cannot rule out.

    This sourceProspectively designed comparison groups help rule out history, maturation, regression, and other internal-validity threats that single-group before/after designs cannot exclude.

• Controlled Overlap Pilot
  • Its central hazard is external validity — a pilot in a sheltered subzone can succeed for reasons that will not survive full deployment (a hand-picked cohort, extra attention, a scale at which harms stay dilute).

    This sourceExplains that effects can differ between small-scale experiments and full-scale implementation, and that selecting especially ready participants can inflate effects relative to the broader population.

• Cross-Scale Transfer Review
  • Its classic failure is assuming external validity by default — transferring a result because it is convenient and treating a bounded finding as a universal law.

    This sourceDefines external validity as whether a causal relationship holds across variations in persons, settings, treatments, and measurements rather than automatically beyond the sampled instances.

• External Validity Check
  • The discipline it formalizes is the classical worry about external validity — whether a result generalizes beyond the exact conditions that produced it.

    This sourceDefines external validity as whether a causal relationship holds across variations in persons, settings, treatments, and outcomes.

• Limited Cohort Rollout
  • Its central failure mode is selection bias

    This sourceExplains that nonrepresentative selection and differences between study participants and target populations can limit generalization of an observed result.

• Network Perturbation or Ablation Test
  • Measure the predicted behavior. Run the outcome the interpretation forecasts — cascade reach, signal fidelity, flow, information spread — before and after

    This sourceExplains before-and-after outcome comparison through experimental and pretest–posttest designs.

• Persistence Stress and Shadow Test
  • It misleads when the scenarios are unrepresentative: a test tuned to failures that never occur, while missing the one that does, gives false assurance — the map is not the territory

    This sourceExplains that external-validity claims depend on whether causal relationships hold across relevant variations in persons, settings, treatments, and outcomes.

• Pilot-to-Scale Design Probe
  • Its failure mode is the external-validity trap:

    This sourceFrames external validity as whether a causal relationship generalizes across persons, settings, treatments, and outcomes beyond the study context.

• Pilotable Solution
  • Its central failure mode is a threat to external validity: a pilot in one hand-picked, well-staffed, unusually motivated site can succeed for reasons that will not travel, so the clean pilot result does not survive the full rollout.

    This sourceDefines external validity in terms of whether a causal relationship generalizes across persons, settings, treatments, and outcomes.

• Policy Pilot Cycle
  • Its failure mode is external validity — a pilot that succeeds in three motivated neighborhoods but fails at scale because the pilot conditions did not represent the whole.

    This sourceDefines external validity as whether a causal result generalizes across populations, settings, times, and implementation conditions.

• Progressive Policy Pilot
  • Its central discipline is guarding external validity

    This sourceDefines external validity as whether causal relationships hold across variation in persons, settings, treatments, and measurements.

• Service Pilot
  • Its central hazard is external validity — a pilot often enjoys extra attention, motivated staff, and hand-holding that will not survive full rollout, so a pilot can succeed for reasons that won't scale.

    This sourceTreats external validity as the problem of whether a causal result generalizes beyond the units, treatments, outcomes, and settings actually studied.

• Tension-Curve Rehearsal
  • Its central failure mode is that the sandbox is not the world: rehearsal participants are primed, self-selected, or already know the reveal, and a curve tuned to them can miss on a real, naïve audience — the results may simply not generalize

    This sourceExplains why results from selected participants and settings may not generalize to a different real-world audience.

• Test Market
  • The honest failure mode is weak external validity

    This sourceFrames external validity as whether a result generalizes beyond the study’s sampled population and setting.

• Transfer Assumption Review
  • The review converted a vague sense that the model "should generalize" into named, falsifiable premises — the discipline external-validity failures usually punish for being skipped.

    This sourceFrames generalization as an inference whose assumptions across people, settings, times, treatments, and outcomes must be identified and critically assessed.

• Transfer Prototype Experiment
  • Its central threat is weak external validity

    This sourceDefines external validity as whether a pilot result generalizes to other populations or settings.

Verification

Does it exist? Confirmed. This work's ISBN resolves to a registered record, which fixes its identity. That is all it fixes.

Does it back the claim? Not recorded. Neither this nor any other of the 24 citations of this work carries a recorded support check.

Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.

See how references were verified.

Links previously used in the corpus

Before the registry existed this work was also linked 11 other ways.

• https://books.google.com/books?id=o7jaAAAAMAAJ ×7
• https://books.google.com/books/about/Experimental_and_quasi_experimental_desi.html?id=o7jaAAAAMAAJ ×3
• https://books.google.com/books/about/Experimental_and_Quasi_experimental_Desi.html?id=bhLLmgEACAAJ ×2
• https://books.google.com/books/about/Experimental_and_Quasi_experimental_Desi.html?id=o7jaAAAAMAAJ ×2
• https://search.worldcat.org/title/experimental-and-quasi-experimental-designs-for-generalized-causal-inference/oclc/48116417 ×2
• https://search.worldcat.org/es/title/experimental-and-quasi-experimental-designs-for-generalized-causal-inference/oclc/606894072 ×1
• https://search.worldcat.org/title/10006500 ×1
• https://search.worldcat.org/title/Experimental-and-quasi-experimental-designs-for-generalized-causal-inference/oclc/606894072 ×1
• https://search.worldcat.org/title/Experimental-and-quasi-experimental-designs-for-generalized-causal-inference/oclc/700293827 ×1
• https://search.worldcat.org/title/experimental-and-quasi-experimental-designs-for-generalized-causal-inference/oclc/47644326 ×1
• https://www.worldcat.org/oclc/47702762 ×1

Registry ID ref:08aed4ca7552 · see in the full table