Global Evaluation in Polygraph: Expert Guide (2026)

Definition and Purpose

In polygraph testing, global evaluation refers to the holistic, integrative assessment process through which a trained examiner arrives at a final diagnostic opinion about an examinee's truthfulness. Rather than relying exclusively on the numerical scores derived from physiological chart analysis, the examiner weighs every available data point gathered during the entire examination — from the pre-test interview through chart collection and into any post-test discussion.

As Slowik (1982) established in his foundational work, global evaluation is essentially "inductive case analysis in which one goes from the particular to the general" — an analysis of separate variables to reach an overall conclusion [1]Verified Global Evaluation: An Inductive Approach to Case Resolution
Foundational work defining global evaluation as inductive case analysis integrating fact analysis, behavioral observation, chart interpretation, and post-test interrogation. Its components include fact analysis, behavioral observation and analysis, chart interpretation, and post-test interrogation [1]Verified Global Evaluation: An Inductive Approach to Case Resolution
Foundational work defining global evaluation as inductive case analysis integrating fact analysis, behavioral observation, chart interpretation, and post-test interrogation. Importantly, global evaluation does not permit an examiner to allow investigative experience or intuition to supersede or ignore the physiological recordings on a set of polygraph charts [1]Verified Global Evaluation: An Inductive Approach to Case Resolution
Foundational work defining global evaluation as inductive case analysis integrating fact analysis, behavioral observation, chart interpretation, and post-test interrogation.

Think of numerical scoring as the backbone of the analysis. It provides a structured, quantifiable assessment of the physiological data recorded during the relevant, comparison, and irrelevant questions. But physiological data exists within a broader context. The examinee's demeanor, their verbal responses during the pre-test, the clarity of test questions, any spontaneous admissions, the presence or absence of artifacts, and the circumstances of the case — all feed into global evaluation.

The concept is analogous to how a physician makes a diagnosis. A doctor does not rely solely on a blood test number. They consider the patient's symptoms, medical history, physical examination findings, and clinical experience before rendering a diagnosis. Similarly, a polygraph examiner uses numerical scoring as a critical input but then integrates all other available information to arrive at a well-reasoned professional opinion. For more on how the body responds during testing, see our guide on what happens to your body when you lie on a polygraph.

What Numerical Scoring Provides

Numerical scoring is the quantitative backbone of modern polygraph analysis. The examiner evaluates each physiological channel — pneumograph/respiration, electrodermal activity (EDA), cardiovascular, and sometimes movement sensors — for each relevant question. Responses are compared to comparison questions using a standardized scale, typically a 3-position or 7-position scale [2]Verified Fundamentals of Polygraph Practice
Comprehensive textbook covering polygraph scoring systems, analysis techniques, and evidence-based practices published by Academic Press (Elsevier). Each chart run generates scores that are tallied across all charts.

If the cumulative score exceeds a positive threshold, the result is called Non-Deceptive Indicated (NDI). If it falls below a negative threshold, the result is Deceptive Indicated (DI). If the score falls in a middle range, the result may be classified as Inconclusive (INC).

This system is powerful. It provides reproducibility, inter-rater reliability, and a clear audit trail. Research on the Empirical Scoring System (ESS) demonstrated a bootstrap mean accuracy rate of 87.9%, with inexperienced examiners achieving decision accuracy comparable to experienced scorers [2]Verified Fundamentals of Polygraph Practice
Comprehensive textbook covering polygraph scoring systems, analysis techniques, and evidence-based practices published by Academic Press (Elsevier). However, numerical scoring has inherent limitations.

Where Numbers Fall Short

Numerical scores only measure physiological tracings. They cannot capture what the examinee said during the pre-test, whether they appeared confused by a question, or whether they made a partial admission. Artifacts from movement, coughing, or medical conditions can distort scores, potentially misleading the numerical total.

Borderline cases are common — many examinations produce scores near the inconclusive zone. Context is absent from numbers alone: a score tells you nothing about question formulation quality, the examinee's comprehension, or whether testing conditions met standards.

Global evaluation fills these gaps. It is the examiner's professional responsibility to consider the totality of the data before rendering a final opinion. The numerical score informs the opinion but does not automatically dictate it. Research by Shurany and Gordon (2018) found that individual physiological response patterns vary significantly, with EDA contributing 55% of reactions, cardiovascular 26%, and pneumograph 19% — underscoring why a holistic approach to data interpretation is essential [3]Verified Idiosyncrasies in Chart Evaluation
Found individual physiological response patterns vary significantly with EDA contributing 55% of reactions, cardiovascular 26%, and pneumograph 19%.

Quantitative Data

Quantitative data includes numerical chart scores using 3-position or 7-position scales, automated algorithm outputs from systems like PolyScore, OSS-3, and CPS, spot analysis results per question per chart, channel-specific reaction patterns, and cumulative totals across all chart runs. These form the measurable foundation upon which the examiner builds their analysis.

Qualitative Data

Qualitative data encompasses behavioral observations from the pre-test interview, verbal responses and spontaneous admissions, examinee demeanor and cooperativeness, question comprehension issues, and artifact identification and management. The examiner catalogues these observations systematically throughout the examination for integration during global evaluation.

The Four Primary Channels

The physiological data collected by the polygraph instrument forms the primary evidentiary basis for any diagnostic opinion. During a standard examination, the instrument simultaneously records data from multiple channels, each measuring a different autonomic nervous system response [4]Verified Beyond the Polygraph: Deception Detection and the Autonomic Nervous System
Review of deception detection methods including polygraph, confirming physiological measurement principles underlying autonomic nervous system responses.

Pneumograph (Respiration): Two pneumatic tubes placed around the chest and abdomen record breathing rate, depth, amplitude, and regularity. Changes such as suppression, apnea, or altered cycle length can indicate autonomic arousal.

Electrodermal Activity (EDA): Sensors attached to the fingertips measure changes in sweat gland activity. The EDA channel is highly sensitive to emotional arousal and is often one of the first channels to show a reaction. Handler, Nelson, Krapohl, and Honts (2010) confirmed that the electrodermal response is "the most robust and informative" of all signals collected during polygraph testing [5]Verified An EDA Primer for Polygraph Examiners
Confirms electrodermal response is the most robust and informative signal in polygraph testing, published in Polygraph 39(2), 68-108. Multiple studies indicate the electrodermal component provides the greatest contribution to diagnostic accuracy [5]Verified An EDA Primer for Polygraph Examiners
Confirms electrodermal response is the most robust and informative signal in polygraph testing, published in Polygraph 39(2), 68-108.

Cardiovascular Measures: A blood pressure cuff measures relative changes in blood pressure, heart rate, and pulse amplitude, providing data on cardiac reactivity.

Motion Sensors: Activity sensors detect gross body movements, helping examiners identify artifacts and detect potential countermeasure attempts.

Pattern Analysis Across Charts

During global evaluation, the examiner does not simply tally numbers. They examine the overall pattern of responding across all channels and chart runs. Are reactions to relevant questions consistent across charts? Does the same channel show the strongest response each time? Is there habituation (decreasing response) or sensitization (increasing response)? These patterns provide richer diagnostic information than any single numerical score.

Research by Saldžiūnas, Kovalenko, and Knyazev (2012) demonstrated that cognitive processing alone can generate physiological reactions detectable by polygraph instrumentation, confirming that EDA responses increase systematically with cognitive load [6]Verified Tests with Numbers
Demonstrated that cognitive processing produces observable EDA responses increasing with task difficulty, confirming physiological reactivity detectable by polygraph. This finding reinforces why examiners must assess the totality of physiological patterns rather than isolated data points.

What Examiners Observe

While physiological data is the primary evidence, behavioral observations provide essential contextual information. During the pretest interview, the examiner establishes rapport, reviews test questions, and assesses examinee suitability. This phase can reveal critical information:

Response to question review — whether the examinee becomes visibly anxious when certain relevant questions are discussed, or attempts to minimize, rationalize, or redirect the conversation.

Spontaneous admissions — whether the examinee volunteers information about the target issue that was not previously known. Partial admissions during the pre-test often correlate with chart data showing significant reactions.

Comprehension difficulties — whether language barriers, cognitive limitations, or hearing impairments affect understanding. The examiner must factor these into global evaluation.

Emotional state and cooperativeness — context for interpreting physiological reactions, including whether a person's emotional state may produce artifacts affecting data quality.

The Limits of Behavioral Assessment

It is essential to understand that behavioral observations alone cannot determine truthfulness or deception. Widacki (2010) documented that throughout history, practitioners recognized that deception produces observable physiological changes [7]Verified The Attempts at Detecting Deception Through Evaluation of Non-verbal Symptoms
Documents that ancient practitioners recognized deception produces observable physiological changes, establishing foundational principles for modern psychophysiological detection, but modern research consistently shows that even trained professionals cannot reliably detect deception from behavioral cues alone — unaided human deception detection accuracy averages only around 54% [8]Verified A review of the polygraph: history, methodology and current status
Confirms human deception detection accuracy averages 54% and reviews CQT accuracy estimates ranging from 74-89% for guilty examinees.

In global evaluation, behavioral observations serve as supplementary context, not primary evidence. The examiner uses them to qualify, clarify, or contextualize the physiological data — never to override it without documented justification. This distinction is what separates responsible global evaluation from subjective guesswork. For more on how the brain processes deception, see the cognitive process behind lying.

Pre-Test, In-Test, and Post-Test Verbal Data

What an examinee says throughout the polygraph examination carries significant weight in global evaluation. During the pre-test interview, the examiner asks targeted questions to refine question formulation, identify potential outside issues that might cause physiological arousal, and assess whether the examinee has a clear understanding of what will be asked.

Occasionally during breaks between chart runs or after the examiner provides feedback, examinees make admissions. These can range from minor clarifications to full confessions. In-test admissions are directly relevant because they confirm or contradict the physiological data.

After chart collection, the examiner may conduct a post-test interview. The content and timing of any post-test admissions are documented and weighed in the global evaluation.

The examiner tracks verbal consistency throughout — significant changes in the narrative, adding details, retracting earlier statements, or suddenly remembering undisclosed information are evaluated in context with the physiological data. Research in UK sex offender supervision found that polygraph-tested supervisees were nearly six times more likely to make at least one risk-relevant disclosure [9]Verified An Evaluation of Polygraph Testing by Police to Manage Individuals Convicted or Suspected of Sexual Offending
Found polygraph-tested supervisees were nearly 6 times more likely to make risk-relevant disclosures across nine UK police areas involving 800+ individuals, demonstrating how the polygraph examination environment itself — including the verbal components — promotes truthful communication.

How Context Shapes Interpretation

Every polygraph examination occurs within a specific context. Whether it is a private lie detector test, a pre-employment screening, or a post-conviction sex offender examination, the purpose and circumstances influence data interpretation. Understanding the different types of polygraph examinations is essential for proper contextual evaluation.

Case context includes the purpose of the examination (diagnostic vs. screening exams have different base rates and interpretive frameworks), known facts about the case, the examinee's medical and psychological history (medications affecting the autonomic nervous system require careful interpretation), and testing conditions including room configuration, interruptions, and temperature. Conditions such as menopause and hormonal changes can also affect physiological responding and must be considered during global evaluation.

The APA's 2011 meta-analysis demonstrated that examination type matters significantly: single-issue diagnostic testing produced an aggregated decision accuracy of 89% (confidence interval 83%–95%), while multi-issue examinations achieved 85% accuracy (confidence interval 77%–93%) [10]Verified Meta-Analytic Survey of Criterion Accuracy of Validated Polygraph Techniques
Confirms 89% aggregated decision accuracy for single-issue diagnostic testing with 83-95% confidence interval based on 38 studies and 11,737 scored results. Examiners must account for these differences when contextualizing their findings.

Major Algorithms in Use

Modern polygraph systems include automated scoring algorithms that analyze physiological data mathematically and produce probability estimates. The most widely used algorithms include:

PolyScore: Developed by the Johns Hopkins University Applied Physics Laboratory (JHU-APL) [11]Verified The Polygraph and Lie Detection (Appendix F: Computerized Scoring)
Confirms PolyScore was developed by JHU-APL and used with Axciton and Lafayette instruments; CPS developed from University of Utah research, PolyScore uses statistical models to evaluate multi-channel physiological data and produces a probability of deception based on logistic regression or neural network models [11]Verified The Polygraph and Lie Detection (Appendix F: Computerized Scoring)
Confirms PolyScore was developed by JHU-APL and used with Axciton and Lafayette instruments; CPS developed from University of Utah research. It is integrated into both Axciton and Lafayette polygraph instruments [12]Verified PolyScore: Computerized Polygraph Scoring Algorithm
Confirms PolyScore algorithm developed at Johns Hopkins University Applied Physics Laboratory for evaluating zone comparison polygraph examinations. PolyScore was developed on real criminal cases provided by the Department of Defense Polygraph Institute [11]Verified The Polygraph and Lie Detection (Appendix F: Computerized Scoring)
Confirms PolyScore was developed by JHU-APL and used with Axciton and Lafayette instruments; CPS developed from University of Utah research.

OSS-3 (Objective Scoring System, Version 3): Developed by Raymond Nelson, Donald Krapohl, and Mark Handler (2008) [13]Verified Brute-Force Comparison: A Monte Carlo Study of OSS-3 and Human Polygraph Scorers
Describes development and validation of OSS-3 by Nelson, Krapohl and Handler; confirms algorithm has demonstrable validity with multiple validation samples, OSS-3 is a powerful computer algorithm that calculates a probabilistic classifier for both diagnostic and screening polygraphs [14]Verified Tech Talk: Introduction to the Lafayette OSS-3 Test of Proportions
Confirms OSS-3 is a probabilistic classifier for both diagnostic and screening polygraphs with artifact marking capabilities in Lafayette LXSoftware. It is a form of 7-position scoring derived from measurements of "Kircher features," eliminating subjectivity in chart interpretation [13]Verified Brute-Force Comparison: A Monte Carlo Study of OSS-3 and Human Polygraph Scorers
Describes development and validation of OSS-3 by Nelson, Krapohl and Handler; confirms algorithm has demonstrable validity with multiple validation samples. OSS-3 is integrated into Lafayette LXSoftware [15]Verified Lafayette LXSoftware User Manual
Confirms Lafayette LXSoftware includes PolyScore, OSS, Identifi, QuESt, and ASIT algorithms with OSS provided as standard and has been automated by multiple computer polygraph manufacturers.

CPS (Computerized Polygraph System): Originally developed by Scientific Assessment Technologies based on research at the University of Utah by John Kircher and David Raskin (1988) [16]Verified Human Versus Computerized Evaluations of Polygraph Data in a Laboratory Setting
Found computerized evaluations achieved accuracy of at least 90%, equaling or exceeding human scorers in polygraph interpretation. CPS is associated with Stoelting instruments. The current iteration, CPS Elite, is Stoelting's fourth-generation computerized polygraph system, integrating the Fusion software platform [17]Verified CPS Elite Polygraph Systems
Confirms Stoelting CPS Elite is the fourth-generation Computerized Polygraph System with Fusion software platform.

For a full overview of APA-validated techniques and their scoring methods, see our complete guide.

Algorithms as Decision Support, Not Decision Makers

These algorithms are valuable tools that enhance consistency, reduce certain forms of examiner bias, and provide a mathematical cross-check against hand-scored evaluations. OSS-3 and PolyScore have demonstrated accuracy rates between 85–92% under laboratory conditions [18]Verified Modern Algorithms in Polygraph Data Analysis
Confirms OSS-3 and PolyScore demonstrated accuracy rates between 85-92% under laboratory conditions; describes hybrid computer-assisted, examiner-driven analysis as modern standard. Kircher and Raskin (1988) found that computerized evaluations achieved accuracy of at least 90%, equaling or exceeding human scorers [16]Verified Human Versus Computerized Evaluations of Polygraph Data in a Laboratory Setting
Found computerized evaluations achieved accuracy of at least 90%, equaling or exceeding human scorers in polygraph interpretation.

However, algorithms have significant limitations that make global evaluation indispensable. They process only physiological data channels and cannot assess behavioral observations, verbal content, or case context. They may be affected by artifacts that a human examiner would identify and exclude. They provide probability estimates, not certainties.

In best practice, the automated algorithm result is one input into global evaluation — an important one, but not the sole determinant. The examiner reviews the algorithm output alongside their hand-scored analysis, behavioral notes, and contextual information. This hybrid approach — computer-assisted, examiner-driven analysis — represents the modern standard of forensic psychophysiology [18]Verified Modern Algorithms in Polygraph Data Analysis
Confirms OSS-3 and PolyScore demonstrated accuracy rates between 85-92% under laboratory conditions; describes hybrid computer-assisted, examiner-driven analysis as modern standard. For more on the digital workflow from test to report, see our examiner guide.

The Seven-Stage Process

Stage 1 — Complete Numerical Scoring: The examiner hand-scores each chart run using the validated scoring technique (3-position or 7-position scale) for every relevant question across all physiological channels. Cumulative totals are calculated.

Stage 2 — Run Automated Algorithms: The examiner processes collected data through the system's automated algorithm (PolyScore, OSS-3, or CPS). The algorithm's probability output and quality indicators are compared against hand-scored results for consistency.

Stage 3 — Review Behavioral and Verbal Notes: The examiner reviews contemporaneous notes from the pretest interview, in-test observations, and any post-test discussion. Admissions, comprehension issues, and cooperation levels are catalogued.

Stage 4 — Assess Data Quality and Artifact Impact: The examiner evaluates whether artifacts (coughing, movement, medical events, equipment issues) may have compromised data quality. If artifacts affected key questions, the examiner determines whether sufficient clean data remains for a valid opinion.

Stage 5 — Consider Case Context: The examination's purpose, the testing environment, the examinee's medical and psychological history, and any known case facts are weighed against collected data.

Stage 6 — Integrate All Data and Form Opinion: The examiner synthesizes all quantitative and qualitative data. If all data sources align, the opinion is straightforward. Discrepancies require documented reasoning and may result in an inconclusive call.

Stage 7 — Document and Report: The final opinion (NDI, DI, or INC) is documented in a formal examination report with supporting data, scoring results, algorithm outputs, and relevant notes. This documentation enables quality review and peer assessment. For details on what a diagnostic impression looks like in a polygraph report, see our legal guide.

Professional Standards Framework

The American Polygraph Association (APA) sets the professional standards governing polygraph practice. While the APA Standards of Practice do not use the exact phrase "global evaluation" as a standalone defined term, the principles underlying it are embedded throughout the standards. The APA believes that scientific evidence supports the validity of polygraph examinations conducted in compliance with documented and validated procedures [10]Verified Meta-Analytic Survey of Criterion Accuracy of Validated Polygraph Techniques
Confirms 89% aggregated decision accuracy for single-issue diagnostic testing with 83-95% confidence interval based on 38 studies and 11,737 scored results.

Key requirements include: use of validated techniques with established scoring rules; rendering a professional diagnostic opinion rather than merely reporting a number; documentation, record-keeping, and peer review processes requiring examiners to justify opinions based on data; pretest requirements for informed consent, question review, and suitability assessment; and artifact identification and management.

ASTM International also provides standards relevant to polygraph practice. Standard E2062, the Standard Guide for PDD Examination Standards of Practice, establishes essential and recommended elements in the procedures for conducting a psychophysiological detection of deception examination [19]Verified ASTM E2062-11(2017) Standard Guide for PDD Examination Standards of Practice
Confirms ASTM Standard E2062 establishes essential and recommended elements for PDD examination procedures. Additional ASTM standards cover interpretation (E2229), calibration (E2063), and screening examinations (E2386) [19]Verified ASTM E2062-11(2017) Standard Guide for PDD Examination Standards of Practice
Confirms ASTM Standard E2062 establishes essential and recommended elements for PDD examination procedures.

The APA's 2011 meta-analysis — which reviewed 38 qualifying studies involving 295 scorers who provided 11,737 scored results of 3,723 examinations — provides the most comprehensive validation of polygraph techniques used within these standards [10]Verified Meta-Analytic Survey of Criterion Accuracy of Validated Polygraph Techniques
Confirms 89% aggregated decision accuracy for single-issue diagnostic testing with 83-95% confidence interval based on 38 studies and 11,737 scored results. For a complete list of APA-validated techniques, see our guide.

What Research Shows About Bias

Research on examiner bias in polygraph testing has demonstrated that contextual information can influence scoring decisions. The landmark study by Elaad, Ginton, and Ben-Shakhar (1994) found that prior expectations affected examiners' judgments when polygraph charts did not include clear indications of guilt or innocence — but when objective physiological evidence contained strong contradictory indications, judgments were not affected by expectations [20]Verified The effects of prior expectations and outcome knowledge on polygraph examiners' decisions
Landmark study showing prior expectations affected examiners' judgments with ambiguous charts but not when strong physiological evidence contradicted expectations. This finding highlights both the vulnerability and resilience of the scoring process.

A subsequent study by Krapohl and Dutton (2018) found that, on average, polygraph scores and decisions were shifted in the direction of biasing information for both clear and ambiguous data, though not all scorers were affected [21]Verified Examiner Expectation Effects in Polygraph Scoring
Found polygraph scores and decisions were shifted in the direction of biasing information; partially replicated Elaad et al. (1994) findings. However, a re-evaluation by Ginton (2019) concluded that the real-world impact of prior expectations on field polygraph decisions was substantially smaller than critics suggested, adversely affecting approximately 3% of total examinations [22]Verified Basic vs. Applied Psychology perspectives: reevaluating the impact of prior expectations on polygraph outcomes
Re-evaluated Elaad 1994 data and concluded prior expectations adversely impact only about 3% of total polygraph examinations in practice.

Gołaszewski (2022) advocated for mandatory blind evaluation procedures in evidentiary examinations, arguing that blind scoring enhances objectivity by removing the potential for confirmation bias [23]Verified Should Blind Evaluation of Polygraph Charts Be a Mandatory Procedure in Evidentiary Examinations?
Advocates for mandatory blind evaluation procedures in evidentiary examinations to enhance objectivity and mitigate confirmation bias. This represents a growing consensus that procedural safeguards — combined with computerized algorithms that provide perfect reliability — offer meaningful protection against bias effects.

Resolving Ambiguous Data

The true value of global evaluation becomes most apparent when data is ambiguous. A significant percentage of polygraph examinations produce numerical scores in or near the inconclusive range. These are the cases where integrative judgment is most critical.

Consider a scenario where the cumulative score falls near the inconclusive threshold. The number alone suggests "inconclusive." But during global evaluation, the examiner might note that a persistent cough on one chart created artifacts in the respiration channel, reducing that chart's diagnostic value. After excluding compromised data, the remaining channels across other charts may consistently point toward a clear conclusion.

The examiner might also consider that the examinee made a significant partial admission during the pre-test that aligns with physiological reactions to a specific relevant question. Or that automated scoring algorithms — which process data differently from human evaluators — produced a clear result despite the borderline hand-scored total.

This integrative reasoning is precisely what global evaluation provides. It allows the trained professional to resolve ambiguities that no single metric can address. The process is governed by APA standards and must be documented — it is structured professional judgment, not intuition. For more on common mistakes novice examiners make during this process, see our examiner training guide.

Your Examination in Context

If you are scheduled for a polygraph examination, understanding global evaluation can help you feel more confident about the process. Your examiner is not simply running data through a formula — they are conducting a comprehensive, multi-source analysis designed to reach the most accurate conclusion possible.

Your honesty during the pre-test interview matters. The information you provide helps the examiner formulate clear questions and identify any factors that might affect the physiological data. If you have medical conditions, take medications, or are experiencing unusual stress, disclosing this information helps the examiner account for these factors during global evaluation.

The examiner will use validated scoring techniques that have been demonstrated to achieve 89% accuracy for single-issue diagnostic tests according to the APA's comprehensive meta-analysis [10]Verified Meta-Analytic Survey of Criterion Accuracy of Validated Polygraph Techniques
Confirms 89% aggregated decision accuracy for single-issue diagnostic testing with 83-95% confidence interval based on 38 studies and 11,737 scored results. Automated algorithms provide an additional mathematical cross-check. Your final result — NDI, DI, or INC — reflects the examiner's professional integration of all available evidence.

You have the right to understand the process. You can request a specific polygraph technique if appropriate for your situation, and the examiner should be willing to explain how they reached their conclusion. If you are interested in polygraph training programs, many accredited schools offer comprehensive education on these methods.