Skip to main content

CRP 2026: Sensitivity Analysis

Published: April 2026

Sensitivity analysis tests whether findings are robust to the choice of inclusion criteria. Every key metric - means, standard deviations, inter-construct correlations, and reliability coefficients - is computed independently across three CRP sample definitions. If a finding holds across Conservative Clean (N=79) and Prolific Accepted (N=200), it is robust to inclusion criteria.

Sample Definitions

The three primary result groups below are used throughout this analysis. They are nested from most restrictive to least restrictive.

KeyLabelDescriptionN
conservative_cleanConservative CleanProlific APPROVED + all quality checks (IRI, duration >= 540s, reCAPTCHA, straightlining, auth)79
flexible_cleanFlexible CleanProlific APPROVED + basic quality (all 3 IRIs + duration >= 480s)116
prolific_acceptedProlific AcceptedAll deduplicated V2 rows with Prolific APPROVED status200

Constraints: Conservative Clean ⊆ Flexible Clean ⊆ Prolific Accepted.

Full Sensitivity Table

The table below shows every metric computed across all three sample definitions. Values are formatted to four decimal places. Means, standard deviations, correlations, and Cronbach’s alpha coefficients are all included.

MetricConservative Clean
N=79
Flexible Clean
N=116
Prolific Accepted
N=200
Barrier Grand Mean2.81392.78912.7644
Barrier SD0.63090.66100.6893
Readiness Grand Mean3.04833.07653.1361
Readiness SD0.58290.62390.6674
Maturity Grand Mean3.03183.06163.1533
Maturity SD0.70870.75010.7855
B-R Correlation-0.5016-0.5172-0.3814
B-M Correlation-0.2451-0.3653-0.3156
R-M Correlation0.58770.68210.7194
Alpha Barriers0.85720.86910.8728
Alpha Readiness0.87620.90520.9171
Alpha Maturity0.83680.87610.8847

Dataset Comparison

The table below shows how each metric changes as inclusion criteria are relaxed. The Δ columns show the difference from Conservative Clean (the primary analysis dataset) to each progressively less restrictive dataset. Small deltas confirm that findings are not artifacts of a particular data cleaning strategy.

MetricConservative
N=79
Δ Flexible Clean
N=116
Δ Prolific Accepted
N=200
Barrier Grand Mean2.8139-0.0248-0.0495
Barrier SD0.6309+0.0301+0.0584
Readiness Grand Mean3.0483+0.0282+0.0878
Readiness SD0.5829+0.0410+0.0845
Maturity Grand Mean3.0318+0.0298+0.1215
Maturity SD0.7087+0.0414+0.0768
B-R Correlation-0.5016-0.0156+0.1202
B-M Correlation-0.2451-0.1202-0.0705
R-M Correlation0.5877+0.0944+0.1317
Alpha Barriers0.8572+0.0119+0.0156
Alpha Readiness0.8762+0.0290+0.0409
Alpha Maturity0.8368+0.0393+0.0479

Deltas highlighted in amber exceed 0.05 scale points. Correlation and reliability differences of this magnitude are expected when adding noisier data but do not change substantive conclusions.

Interpretation

The sensitivity analysis reveals remarkable stability across inclusion criteria. Key observations:

  • Construct means are highly stable, with differences of less than 0.10 scale points between the most and least restrictive samples.
  • Standard deviations increase slightly with less restrictive samples, as expected when including noisier data.
  • Correlations between constructs are directionally consistent across all samples (Barriers negatively correlated with Readiness and Maturity; Readiness and Maturity positively correlated).
  • Cronbach’s alphavalues remain excellent (> 0.84) across all samples, indicating robust internal consistency regardless of inclusion criteria.

These findings demonstrate that the core results of the Technology Adoption Barriers Survey are not artifacts of a particular data cleaning strategy. Whether using the strictest quality filters (Conservative Clean, N=79) or the broadest CRP dataset (Prolific Accepted, N=200), the same substantive conclusions hold.

Related Pages

Open Data & Reproducibility - download the dataset and reproduce these results yourself. ← Back to CRP 2026 Results