Scientific issues

Background & Context

This chapter appears in a comprehensive textbook addressing fundamental principles of tests as they apply to polygraphy, with special emphasis on screening, explaining how confidence in polygraph results can be affected by base rates as well as selected decision rules. The work was published at a critical juncture when polygraph practice was transitioning from traditional methods to evidence-based, validated protocols.

Krapohl and Shaw's discussion of the base rate issue represents one of the few attempts to explain to examiners and customers how test accuracy statistics don't directly translate to confidence in individual test outcomes. This educational gap has long plagued polygraph practice, where practitioners and consumers often misunderstand what accuracy percentages actually mean for specific examinees.

The chapter addresses core scientific principles essential for understanding polygraph testing as a probabilistic rather than deterministic tool. The polygraph is described as a probabilistic and non-deterministic test involving both physiological recording and statistical methods, which are needed when neither deterministic observation nor physical measurement are possible.

Research Design & Methodology

This is not an empirical research study but rather a scholarly review chapter synthesizing scientific principles for polygraph practice. The methodology involves explaining theoretical and statistical concepts that govern test interpretation, particularly:

• Base rate analysis: How the prevalence of deception in tested populations affects result interpretation
• Decision rule frameworks: Statistical approaches to determining pass/fail outcomes
• Bayesian inference: Understanding posterior probabilities versus test accuracy
• Screening versus diagnostic contexts: How different application settings alter test performance

The chapter notes that there are decision rules in some polygraph analysis systems that include extra-polygraphic information as part of the decision process, though there is no validated method yet published, and that few published decision scoring procedures allow for consideration of the base rate issue. This highlights a critical gap between statistical theory and actual practice.

Results & Key Findings

The chapter's primary contribution is clarifying the distinction between test accuracy and confidence in individual results. The estimated or assumed accuracy of the test does not indicate the posterior probability of a given result being correct; accuracy figures always relate to the population of examinees as a whole and not to any particular outcome of a concrete examination, meaning one should not assume 90% confidence in a result just because a test has 90% accuracy.

Key accuracy benchmarks presented include:

• Event-specific diagnostic polygraphs provide mean accuracy of .89 with a 95% confidence range from .83 to .95, while multi-issue screening polygraphs provide accuracy rates with a mean of .85 and a 95% confidence range of .77 to .93
• Screening tests show lower accuracy than diagnostic tests, an important consideration for their widespread use
• Because polygraph screening methods are not as powerful as specific-issue testing, it is not appropriate to issue diagnostic decisions of deception indicated (DI) or no deception indicated (NDI) based on a multiple-issue screening test; results of SR (significant response) and NSR (no significant response) are more precise

Discussion & Significance

The chapter's significance lies in bridging the gap between academic statistical theory and field practice. The moves taken to qualify polygraph results as evidence in court proceedings are mostly related to using adapted decision rules in analyzing polygraph records, aimed to achieve equal rates of false positives and false negatives. This represents the field's attempt to meet legal standards while acknowledging inherent limitations.

The base rate problem is particularly crucial for screening applications. When testing populations with low base rates of deception (most applicants are truthful), even tests with high accuracy will produce concerning numbers of false positives. This mathematical reality means decision-makers must understand that a "deceptive" result in a low base-rate population carries less certainty than the test's overall accuracy suggests.

Examiners should discourage decision makers from acting solely on polygraph results without additional supporting information except when the cost of error is so substantial that such decisions can reasonably be justified. This represents a mature, scientifically sound approach to polygraph use that acknowledges both its utility and limitations.

Limitations & Considerations

Few published decision scoring procedures allow for consideration of the base rate issue, and few models publish a sufficient level of detail to allow a formal cost-benefit analysis to identify the appropriate cutting scores for a set of conditions. This represents an ongoing challenge in translating theory to practice.

As a textbook chapter rather than original research, the work synthesizes existing knowledge rather than generating new empirical findings. The practical application of base rate adjustments remains limited in field settings where examiners may lack the statistical sophistication or institutional support to implement these concepts. Additionally, determining accurate base rates for various testing populations is itself challenging, introducing uncertainty into calculations.

Practical Applications

For polygraph examiners, this chapter provides essential guidance on communicating test limitations to clients and decision-makers. Understanding that test accuracy ≠ individual result confidence is crucial for ethical practice. Examiners should adjust their reporting based on the testing context, population base rates, and the decision rules employed.

For consumers of polygraph services—whether law enforcement, employers, or legal professionals—this work underscores the need to view polygraph results as probabilistic evidence requiring corroboration rather than definitive proof. The chapter supports integrated investigative approaches where polygraph serves as one information source among many, particularly in screening contexts where base rate effects are most pronounced.