our methods

The Keystone Indicators Project (KIP) is a 50-state comparative index designed to measure livability, competitiveness, resilience, and long-term prosperity across the United States, with Pennsylvania serving as the anchor and benchmark state. The project was developed to provide policymakers, community leaders, researchers, and the public with a transparent, empirically grounded framework for understanding the complex conditions that shape state performance.

The final KIP framework consists of seven domains, 28 subdomains, 88 retained variables, seven domain-level synthesis indices, and one overall KIP Synthesis Index.

The index draws from publicly available federal and nonprofit data systems and emphasizes methodological transparency, reproducibility, and empirical weighting. Unlike many composite ranking systems that rely on subjective weighting schemes or opaque aggregation methods, KIP uses Principal Component Analysis (PCA) to identify coherent statistical structures within the data and derive weights empirically from shared variance among indicators.

The KIP framework measures state performance across seven major domains spanning social well-being, economic vitality, workforce development, environmental systems, government capacity, and long-term competitiveness.

Livability measures whether a state provides the foundational conditions necessary for stable daily life, including material security, social connectedness, access to care systems, and personal safety.

Conservation & Environment measures how environmental systems, outdoor access, natural resources, and ecological resilience shape quality of life and economic opportunity.

Business Climate & Future Readiness measures whether a state economy is dynamic, resilient, innovative, and positioned for future growth through workforce preparedness, infrastructure quality, and capital formation.

Economic Vitality & Jobs measures the overall health, productivity, competitiveness, and renewal capacity of the state economy.

Government Fiscal Health measures whether government systems are financially stable, structurally resilient, and capable of delivering services and absorbing shocks.

Household Well-Being measures whether households and families are prospering through income growth, wealth accumulation, health outcomes, and intergenerational opportunity.

Workforce, Education & Talent measures whether states are effectively developing, retaining, and deploying human capital across educational and labor market systems.

The KIP framework began with 141 candidate variables drawn from federal statistical agencies and established nonprofit data systems. Major sources include the U.S. Census Bureau, Bureau of Labor Statistics, Bureau of Economic Analysis, Environmental Protection Agency, Federal Emergency Management Agency, National Center for Education Statistics, and Centers for Disease Control and Prevention.

All variables were required to be available for all 50 states, use consistent cross-state definitions, remain publicly accessible and reproducible, and demonstrate theoretical relevance to the underlying construct.

Variables were directionally aligned prior to analysis so that higher values consistently represented more favorable outcomes. Variables where higher values represented negative conditions were reverse coded.

Principal Component Analysis was conducted on standardized continuous variables using z-score transformations.

Following PCA and factor-score generation, final dashboard outputs were translated into a standardized 1–5 quintile scale for interpretability and public presentation.

KIP uses a hierarchical Principal Component Analysis (PCA) framework for index construction. PCA was selected because it identifies empirically coherent statistical structures, produces data-driven variable weights, reduces dimensionality, and minimizes arbitrary weighting decisions.

Armor’s Theta was used to evaluate internal consistency and reliability of each subdomain and synthesis index.

The following thresholds were used:

• < 0.60 — Poor / Not Acceptable

• 0.60–0.70 — Minimally Acceptable

• 0.70–0.80 — Acceptable

• 0.80–0.90 — Strong

• 0.90–0.95 — Excellent

• > 0.95 — Potential Redundancy

Importantly, Armor’s Theta measures internal consistency and should not be interpreted as a substantive outcome or performance score.

The final KIP Synthesis Index demonstrated a strong dominant first factor with excellent internal consistency.

A weaker second factor emerged during final synthesis analysis. The Conservation & Environment domain contributed strongly to the primary synthesis factor while also introducing a weaker secondary environmental contrast dimension. While analytically interpretable, the second factor did not demonstrate sufficient reliability to function as a standalone index and was therefore retained for diagnostic interpretation only.

KIP results are presented through an interactive Tableau dashboard allowing users to explore overall synthesis scores, domain indices, subdomain indices, and individual indicators.

Dashboard visualizations include choropleth state maps, ranked comparisons, variable-level tables, and benchmarking tools.

Several methodological limitations should be acknowledged, including mixed-year datasets, proxy measures for certain constructs, quintile compression in dashboard presentation, and the masking of within-state geographic variation through state-level aggregation.

The KIP framework is intended as a comparative diagnostic and strategic planning tool rather than a singular or definitive measure of state performance.

Methodological transparency is a core design principle of KIP. The project emphasizes publicly available data sources, reproducible workflows, empirically derived weights, explicit reliability testing, and transparent documentation of limitations.

No arbitrary or subjective weighting schemes are applied within the index construction process.

Future iterations of KIP will incorporate PA region and PA county-level expansion, PA local level data, and expanded dashboard analytics.

The project framework is intentionally modular and designed to support future expansion and refinement.