Signal Detection Theory (SDT) is a psychological theory that aims to describe and explain the process of decision-making in the presence of uncertainty or noise. It provides a quantitative framework for understanding how individuals distinguish between a signal (e.g., a meaningful stimulus) and noise (e.g., irrelevant or random data) in perception or other cognitive tasks.
SDT assumes that whenever a stimulus is presented, it is embedded in a background noise, making it difficult to perceive or discriminate. According to SDT, the decision-making process involves two components: sensitivity to the presence of a signal (sensitivity or d') and decision criterion (c).
Sensitivity, often referred to as d’, measures an individual's ability to discriminate between signal and noise accurately. High d' values indicate high sensitivity and accurate discrimination, while low values indicate low sensitivity and poor discrimination.
The decision criterion, c, refers to an individual's personal standard or threshold for deciding whether a stimulus is a signal or noise. This criterion is influenced by factors such as motivation, previous experience, and the cost of making errors.
SDT proposes that individuals make a decision by comparing the internal evidence for a stimulus being a signal with the internal evidence for it being noise. The outcome of this comparison determines whether the individual responds with a "yes" or "no" to the presence of a signal.
Signal Detection Theory has important applications in various fields, including psychology, medicine, and engineering. It provides a framework for understanding perceptual processes, diagnostic decision-making, and the design of reliable systems that minimize errors in the presence of noise.
