Description
Return guess and 1-lapse asymptotes and guess+(1-guess-lapse)×latent.
A stimulus model relates a chosen level to a supplied response curve, geometry or adaptive rule. One inverse curve or staircase step can be computed without fitting observations, measuring perception or establishing an individual's threshold.
Return guess and 1-lapse asymptotes and guess+(1-guess-lapse)×latent.
When to use this tool
Use Psychometric Lapse Guess Asymptote Gap when you need the stated stimulus-model or adaptive-step calculation.
How to use the tool and how it works
- Enter guessRate, lapseRate, latentProbability. Use the units and conventions below.
- Run the tool. Correct any format, range, or cross-field input error before interpreting the output.
- Read lowerAsymptote, upperAsymptote, predictedProbability. Use the output convention below.
Require guess, lapse and latent probabilities in [0, 1] and guess+lapse no greater than one. Return guess and 1-lapse asymptotes and guess+(1-guess-lapse)×latent.1
| Input field | Meaning and units | Accepted input |
|---|---|---|
| guessRate | Guess Rate | Required. Finite number; minimum 0; maximum 1. |
| lapseRate | Lapse Rate | Required. Finite number; minimum 0; maximum 1. |
| latentProbability | Latent Probability | Required. Finite number; minimum 0; maximum 1. |
| Output field | Interpretation | Returned shape |
|---|---|---|
| lowerAsymptote | Lower Asymptote | Required. Finite number. |
| upperAsymptote | Upper Asymptote | Required. Finite number. |
| predictedProbability | Predicted Probability | Required. Finite number. |
{
"input": {
"guessRate": 0.5,
"lapseRate": 0.02,
"latentProbability": 0.5
},
"output": {
"lowerAsymptote": 0.5,
"upperAsymptote": 0.98,
"predictedProbability": 0.74
}
}Limitations and assumptions
- Equal asymptotes are allowed and yield a constant curve. Latent probability is supplied rather than calculated from a stimulus model or fitted data.
- Inputs must satisfy both the field types and the cross-field conditions above. Invalid input causes an error; a successful false flag or documented placeholder is a different result.
- Numeric calculations use binary floating point unless exact decimal-integer arithmetic is explicitly stated. No hidden measurement tolerance or decimal rounding is added; nonfinite or out-of-contract results are rejected. Numeric signed-zero results are exported as zero.
Alternative or Complementary methods
Fit and validate the appropriate model on the study data when estimating a threshold. Review lapse/guess assumptions, calibration, convergence, uncertainty and participant context.
References
Similar or alternative tools
- Psychometric Threshold Supplied Curve Inverse
Return location+scale×ln((target-guess)/(1-lapse-target)).
- Signal Detection Dprime One Probit Gap
Subtract falseAlarmProbit from hitProbit for dPrime and return minus half their sum as criterion.