Thoughts on the Inconclusive Zone in Comparison Question Test (CQT)

This theoretical paper examines the inconclusive zone in CQT polygraph examinations, arguing that inconclusive results reflect method or execution failure rather than the subject's truthfulness state. Ginton applies psychometric theory and decision theory concepts to analyze both internal and external aspects affecting the inconclusive zone's size and interpretation.

Theoretical and conceptual analysis applying true score theory from psychometrics and pay-off matrix concepts from decision theory to polygraph practice, integrating insights from previous research on CQT scoring and accuracy.

This theoretical analysis by Avital Ginton addresses the overlooked but fundamental role of the inconclusive zone in CQT polygraph examinations. Using psychometric measurement theory and decision analysis frameworks, the paper examines how inconclusive results reflect methodological limitations rather than subject truthfulness states. The analysis reveals that inconclusive zones create a negative correlation between zone size and definite decisions, reducing both correct and incorrect outcomes. Ginton demonstrates that optimal inconclusive zone parameters are context-dependent and should be determined through pay-off matrix analysis rather than rigid standardization. The work emphasizes that conservative inconclusive zones can mitigate prior information bias and reduce potential errors in polygraph decision-making.

This work provides essential theoretical framework for examiners to better understand and optimize inconclusive zone parameters based on situational consequences and decision-making contexts. The analysis supports more flexible, context-appropriate approaches to inconclusive zone configuration rather than rigid standardization across all polygraph applications.

Background & Context

The inconclusive zone represents one of the most overlooked yet fundamentally important aspects of Comparison Question Test (CQT) polygraph examinations. Despite being an integral part of almost any CQT data analysis method and representing the existence of built-in uncertainties in the test, most examiners tend not to spend much time wondering about its meaning. This 2022 theoretical paper by Avital Ginton, a leading polygraph researcher and former head of the Israel Police Polygraph Section, addresses this critical gap in examiner understanding.

An inconclusive result does not reflect the subject's state of mind regarding the truthfulness of their answers to relevant questions, but rather reflects the CQT method or its execution failure to identify the subjects' state of mind—more precisely, it is a failure to reach a definite conclusion about that, whether true or false. Understanding this fundamental distinction is essential for proper interpretation of polygraph results and appropriate decision-making in both investigative and evidentiary contexts.

Research Design & Methodology

This is a theoretical and conceptual analysis paper rather than an empirical study. Ginton draws on true score theory from psychometric measurement and applies pay-off matrix concepts from decision theory to polygraph practice. The analysis integrates insights from his previous research on consistency factors, field accuracy studies, and confirmation bias effects in CQT scoring.

The paper examines both internal and external aspects of the inconclusive zone. Internal aspects include the relation between the extent of using multiple comparison points between relevant and comparison questions and the optimal inconclusive zone size, while external aspects affecting the zone's size and shape are examined when looking at the CQT through a prism of aiding decision-making rather than a mere means to sort truth from lies. The framework draws on Lord, Novick, and Birnbaum's statistical theories of mental test scores to explain measurement error in polygraph testing.

Key conceptual elements analyzed include:

• The relationship between random measurement error and inconclusive outcomes
• Symmetrical versus asymmetrical inconclusive zones
• The trade-off between error reduction and conclusive decision rates
• Context-dependent optimization of inconclusive zone parameters

Results & Key Findings

The primary insight is that the inconclusive zone serves a dual function: preventing wrong decisions while simultaneously carrying an inherent cost of reducing the number of correct decisions. There is a negative correlation between the size of the inconclusive zone and the number of definite calls made by the test—the number of both wrong and correct decisions decreased whenever the range of the inconclusive zone increased.

Ginton's analysis reveals several critical considerations about inconclusive zone configuration:

• A wise approach is to think through a pay-off matrix and look for the optimal zone breadth, but the optimum is not a fixed value—what might be regarded as optimal in one circumstance might not suit a different situation, as sticking to a rigid size of an inconclusive zone is like saying that all decisions have similar importance and consequences
• Using the conservative inconclusive zone of +/-5 in numerical scoring might mitigate the prior information impact by reducing the possibility that it may change results from Deception Indicated to No Deception Indicated and vice versa—with such cut scores, at most, the effect would be shown in entering or leaving the inconclusive zone, which is less problematic in terms of increasing the number of potential errors
• By definition, random fluctuations do not take sides or incline to one side, thus using an asymmetrical inconclusive zone cannot be a remedy to cope with its potentially adverse effect on decisions; yet it was demonstrated that using an asymmetrical inconclusive zone in some circumstances may improve accuracy by reducing the rate of errors, probably as a way to compensate for some weaknesses or deficiencies in the neat rationale underlying the CQT

Physiological responses to psychological stimuli are influenced by the individual's psychological state at the moment when the stimulus is presented, and even if the same stimulus is objectively thrown at the subject twice, they may experience them differently and react with different physiological responses, creating a high probability that two objectively equal stimuli create different reactions. This inherent variability underscores why an inconclusive zone is necessary.

Discussion & Significance

Ginton's analysis reframes the inconclusive zone from a mere statistical artifact to a sophisticated decision-making tool that must be calibrated to specific contexts. Ideally, it should be left to the clients who use the polygraph as a means to aid their decision-making to decide how big the inconclusive zone should be—the case of homeland security is quite different from catching a thief, and so is the difference between sexual harassment and cheating on a school examination, representing a matter of social and institutional preferences based on economic, moral, and ethical considerations.

The paper's integration of true score theory provides a robust psychometric foundation for understanding inconclusive results. The variable in question is the difference between reactions to relevant and comparison questions, which can take various values that are the combination of true score (reflecting the amount of concern) plus error—there are two kinds of errors, random and systematic, and striving for consistency deals with the effort to reduce random error but cannot remedy the effect of possible systematic error. This distinction is crucial for examiners to understand what inconclusive results actually represent.

The paper bridges theoretical psychometrics with practical polygraph applications, challenging the field's reliance on one-size-fits-all decision rules. By advocating for context-specific calibration of the inconclusive zone, Ginton pushes the profession toward more nuanced, defensible decision frameworks that acknowledge the inherent measurement uncertainty in psychophysiological detection of deception.

Limitations & Considerations

As a theoretical and conceptual paper, this work does not present new empirical data. An evidence-based approach is essential to enable reasonable assessments of the proper range of the inconclusive zone, but due to the lack of data, it is inconceivable to expect evidence to support such a differential approach. The recommendations for context-specific inconclusive zones, while theoretically sound, lack the empirical foundation that would guide practitioners in specific applications.

The paper's call for client-driven determination of inconclusive zone parameters raises practical and ethical questions about standardization versus flexibility. While acknowledging that different contexts may warrant different decision thresholds, implementing such variability in practice could complicate quality control, training, and legal admissibility. The tension between optimal decision-making for specific contexts and the profession's need for standardized practices remains unresolved.

Practical Applications

This paper provides examiners with a conceptual framework for understanding what inconclusive results truly represent—not failures of the subject or examiner, but acknowledgments of inherent measurement uncertainty. Practitioners should recognize that the inconclusive zone functions as a quality control mechanism, preventing errors at the cost of reduced decisiveness. The recommendation to use conservative cut scores (±5) may help mitigate confirmation bias effects while maintaining reasonable conclusive rates.

For polygraph consumers and administrators, the key takeaway is that inconclusive zone parameters should be thoughtfully selected based on the consequences of errors in specific contexts. High-stakes security screening may warrant different thresholds than criminal investigations, and these decisions should reflect careful analysis of the relative costs of false positives versus false negatives rather than reflexive adherence to standard cut scores. Examiners should be transparent with clients about these trade-offs when establishing testing protocols.