2018. 5. 30. 16:12ㆍPsychology/통계
이미지 출처: http://gru.stanford.edu/doku.php/tutorials/sdt
One of the early goals of psychologists was to measure the sensitivity of our sensory systems. This activity led to the development of the idea of a threshold, the least intense amount of stimulation needed for a person to be able to see, hear, feel, or detect with stimulus. Unfortunately, one of the problems with this concept was that even though the level of stimulation remained constant, people were inconsistent in detecting the stimulus. Factors other than the sensitivity of sense receptors influence the signal detection process. There is no single, fixed value below which a person never detects the stimulus and above which the person always detects it.
In general, psychologists typically define threshold as that intensity of stimulation that a person can detect some percentage of the time, for example, 50 percent of the time. An approach to resolving this dilemma is provided by signal detection theory. This approach abandons the idea of a threshold. Instead, the theory involves treating detection of the stimulus as a decision-making process, part of which is determined by the nature of the stimulus, by how sensitive a person is to the stimulus, and by cognitive factors.
일반적으로 심리학자들은 전형적으로 개인의 일정비율의 자극 강도 탐지로 절대역을 정의하였는데 회기에 50% 비율의 자극을 탐지하는 수준이 절대역이 되는것이 실례이다. 이러한 접근법의 딜레마를 해결하기 위해서 제공된것이 신호탐지이론이다. 이 접근법은 절대역이라는 아이디어를 버렸다. 대신에 이 이론은 선택적 주의 과정으로서 자극의 탐지를 다루고 있는데 이러한 선택 과정에는 중성의 성격과 개인의 자극 탐지 민감도에 의해서 결정되고 뿐만아니라 인지적 요소들을 포함한다.
In other words, a person will be able to detect more intense sounds or lights more easily than less intense stimuli. Further, a more sensitive person requires less stimulus intensity than a less sensitive person would. Finally, when a person is quite uncertain as to whether the stimulus was present, the individual will decide based on what kind of mistake in judgment is worse: to say that no stimulus was present when there actually was one or to say that there was a stimulus when, in reality, there was none.
In a typical sensory experiment that involves a large number of trials, an observer must try to detect a very faint sound or light that varies in intensity from clearly below normal detection levels to clearly above. The person responds positively (i.e., there is a stimulus) or negatively (i.e., there is no stimulus). There are two possible responses, "Yes" and "No." There are also two different possibilities for the stimulus, either present or absent. The accompanying table describes the combination of an observer's response and whether the stimulus is actually there. The table refers to a task with an auditory stimulus, but it could be modified to involve stimuli for any sense.
Psychologists have used mathematical approaches to determine the sensitivity of an individual for any given pattern of Hits and False Alarms; this index of sensitivity is called d' (called d-prime). A large value of d' reflects greater sensitivity.
심리학자들은 False-alarms과 Hit 의 패턴으로 개인의 민감도를 결정하기 위해 수학적으로 접근하였다. 이 민감도의 지표가 d-prime이라고 불리운다. 큰 수치의 d-prime은 높은 민감도를 의미한다.
Calculation of d-prime.
D-prime (sensitivity) increases with the distance between the two distribution peaks. In signal detection theory terminology, 'sensitivity' refers to an observer's ability to discriminate between two different stimuli (signal or noise) and incorporates both 'false-alarm' and 'hit' rates. Medical parlance differs in that 'sensitivity' refers just to the 'hit rate'. The term 'specificity' is not commonly used in signal detection theory, but in medical parlance it refers to the 'correct-rejection' rate (which is the inverse of the false-alarm rate).
D-prime(민감도)는 두 분포의 꼭짓점 사이의 거리의 증가를 말한다. 신호탐지이론에서 민감도는 관찰자가 상반되는 두 자극(신호 또는 그 외의 자극)을 구분짓는 능력으로 추론되며 false-alarm과 hit 비율 둘다가 상호 독립적임을 의미한다. 의학적인 용어로서의 민감도는 hit rate로 추론한다. specificity는 보통 신호탐지이론에서 사용되지 않는 용어이지만 의학적인 용어에서는 이것을 correct-rejection 비율을 의미한다. (이것은 false-alarm rate과 반대 되는 개념이다.)