For decades, innovation has been discussed as something elusive, creative, and inherently difficult to measure. Many leaders still ask the same question: Can innovation really be measured in a meaningful way? After ten years of systematic data collection, the answer is now unequivocal: yes, it can. Between 2016 and 2025, the InnoSurvey® instrument has been used globally to assess innovation capability across more than 10,000 organisations, spanning all major industries, company sizes, and geographic regions. This has resulted in one of the largest and most reliable innovation data sets in the world. This blog post summarises what we have learned from a decade of innovation data, why we are publishing a full methodological validation now, and how organisations can use this data to move from opinion-based discussions to evidence-based innovation strategy.

Validation of the InnoSurvey® Instrument and Database (2016–2025)

Statistical Significance, Measurement Reliability, Sampling Theory and Practitioner Guidance

Why Innovation Data Matters More Than Ever

Innovation is widely recognised as critical for long-term competitiveness, yet it remains notoriously difficult to drive—especially when it comes to radical or transformative innovation. Research repeatedly shows that the main barrier is not a lack of ideas, but a lack of organisational capability and willingness to act.

Without data, innovation conversations often stall:

Decisions are driven by beliefs rather than evidence
Different stakeholders hold incompatible views of reality
Strategic ambitions are disconnected from operational capability

This is precisely where innovation data becomes essential.

Measurement creates a shared, objective reference point. It allows organisations to:

understand their current innovation capability,
compare themselves to relevant benchmarks,
identify specific capability gaps,
and design credible roadmaps for change.

Why We Are Publishing This Validation Now

We have previously published how the InnoSurvey® question batteries were designed and theoretically grounded. What has been missing until now is long-term empirical proof that the data behaves consistently and reliably over time.

With ten years of data and more than 10,000 organisations assessed, we can now demonstrate that:

innovation capability scores are statistically stable and normally distributed,
the instrument shows very high internal reliability across all domains,
differences between innovators and non-innovators are large and statistically significant,
results hold across industries, regions, languages, and organisational sizes.

In other words, we can now move beyond theory and show—empirically—that innovation capability is measurable, comparable, and actionable.

What the Article Covers (and Why It Matters)

The full article, “Validation of the InnoSurvey® Instrument and Database (2016–2025)”, provides a rigorous methodological foundation for using innovation data in practice.

It includes:

Empirical distribution modelling
Showing that innovation capability data is well-behaved and suitable for statistical analysis.
Reliability analysis (Cronbach’s alpha)
Demonstrating strong internal consistency across all innovation domains.
Sampling theory and confidence intervals
Explaining how many respondents are required to reach confidence levels above 90%, and why we recommend targeting 100 invited respondents per organisational unit.
Comparison of innovators vs non-innovators
Validating that the instrument clearly distinguishes between organisations that innovate successfully and those that do not.
P-value calculus and effect sizes
Showing how statistical significance and practical relevance should be interpreted together.
Validation of company polls vs public polls
Demonstrating that both data sources behave similarly and can be combined for large-scale analysis.

Together, these analyses confirm that the database is robust enough to support benchmarking, correlation analysis, and strategic decision-making.

From Measurement to Strategy

Once innovation capability can be measured reliably, entirely new possibilities open up.

Organisations can:

benchmark themselves against peers and best-in-class performers,
track progress over time,
analyse correlations between strategic intent and operational capabilities,
and design evidence-based innovation roadmaps.

Rather than asking “Can innovation be measured?”, the more relevant question becomes:
“What do we want to do with the insight that innovation data gives us?”

Final Thought

Innovation will always involve uncertainty. But uncertainty does not mean randomness—and creativity does not mean that measurement is impossible.

With ten years of consistent innovation data, we can now state with confidence:
Innovation capability is measurable, comparable, and manageable.

That changes the conversation—from belief to evidence, and from aspiration to action.

Innovation Data: What a Decade of Measurement Tells Us About Innovation Capability