Standardized Descriptive Index for Measuring Deviation and Uncertainty in Psychometric Indicators

The use of descriptive statistics in pilot testing procedures requires objective, standard diagnostic tools that are feasible for small sample sizes. While current psychometric practices report item-level statistics, they often report these raw descriptives separately rather than consolidating both mean and standard deviation into a single diagnostic tool to directly measure item quality. By leveraging the analytical properties of Cohen’s d, this article repurposes its use in scale development as a standardized item deviation index. This measures the extent of an item’s raw deviation relative to its scale midpoint while accounting for its own uncertainty. Analytical properties such as boundedness, scale invariance, and bias are explored to further understand how the index values behave, which will aid future efforts to establish empirical thresholds that characterize redundancy among formative indicators and consistency among reflective indicators.

💡 Research Summary

The manuscript introduces a novel metric called the Standardized Descriptive Index (SDI) designed for pilot‑scale psychometric testing where sample sizes are typically small and conventional factor‑analytic or multicollinearity diagnostics are unreliable. SDI is derived by adapting Cohen’s d to the context of single‑item analysis: it quantifies how far an item’s observed mean deviates from the theoretical midpoint of its response scale, expressed in units of the item’s own standard deviation. Formally, SDI_i = ( \bar{x}_i – M ) / s_i, where \bar{x}_i is the item mean, M is the scale midpoint (e.g., 3 on a 5‑point Likert), and s_i is the item’s sample standard deviation. This formulation makes SDI an unscaled t‑statistic that converges to a standard normal z‑score as the sample size grows, a property demonstrated through the Lindeberg‑Levy Central Limit Theorem and Slutsky’s theorem.

Three core analytical properties are examined. First, boundedness: although SDI is theoretically unbounded, the finite range of Likert scales imposes a practical ceiling. Using Popoviciu’s inequality, the authors show that |SDI| ≤ R / (2 s_i), where R is the observed range, thereby preventing extreme values in limited‑range instruments. Second, scale invariance: SDI remains unchanged under any linear transformation of the response scale (x′ = a x + b), because both the numerator and denominator are affected proportionally. This makes the index comparable across instruments that use different numeric codings (e.g., 1‑7 versus 0‑100). Third, bias adjustment: as with Cohen’s d, SDI overestimates true effect size in small samples. The authors adopt Hedges’ correction factor J(df) = Γ(df/2) /