Scaling Methods - General Psychological Workshop

Scaling Methods

Depending on how the scaling procedures are implemented, indirect and direct scaling methods are distinguished.

The methodology of indirect, indirect scaling was developed by G. Fechner. It is based on methods for determining thresholds of sensations. In order to measure any sensation, it is necessary to express it in terms of the threshold. Having determined the magnitude of the stimulus, below which the sensation does not arise, we determine the zero point of the measuring psychophysical scale, thus ensuring the possibility of constructing a scale of relations.

You can choose another stimulus, which is higher than the threshold value, as the starting point of the scale, but in this case we can get only an interval scale. Next, it is necessary to find an incentive that causes a sensation of a barely noticeable difference from the zero sensation that occurs when the sensory stimulus is affected by the minimal stimulus that sets the beginning of the scale. Thus, it is possible to construct a mathematical function that describes the dependence of sensations on the physical quantities of the stimulus. The problem turns out to be simpler if we take into account the law of Weber who showed that the increment of the stimulus AS, causing a sensation of a barely noticeable difference, is proportional to the magnitude of the stimulus itself, i.e. AS = kS. It should, however, be borne in mind that this relationship is valid not for the entire continuum of sensations, but only for its middle part.

The main problem of such a measurement procedure, however, is how to treat the relationship between the values ​​of barely noticeable differences. Since an indirect scaling procedure does not imply any way of comparing them, it is necessary to make an arbitrary assumption on this score. Thus, Fechner suggested that these values ​​do not depend on the magnitude of the stimulus. This assumption was called the postulate of the equality of barely noticeable differences. The introduction of this postulate made it possible to establish the character of psychophysical dependence by means of a logarithmic function.

Other examples of indirect scaling are the already mentioned Thurston pairwise comparison method, based on the law of comparative judgments formulated by him, and the analogous method of the comparative categories of Thorgerson. These methods can be defined as psychometric, in contrast to Fechner's psychophysical method, since they do not require a correlation of sensation with any physical sign of the objects being scaled.

Finally, we note some more methods of indirect scaling, which have become quite widespread in various branches of psychology. These are different variations of the scoring method, ranking method , and sequential category method. These methods can also be considered as methods of direct scaling, if the experimenter's task is limited to constructing only a weak, ordinal scale. The construction of an interval scale based on the application of these methods involves the study of the frequency distribution of the estimates of different experts or the set of repeated assessments of the same expert and the further translation of the obtained data into probability values. Then, the distribution probabilities are transformed into the values ​​of the standard normal distribution-2-units. These methods will be considered in more detail in the chapter "Methods of indirect scaling".

By methods of direct scaling, it is customary to call methods that in their very procedure ensure the construction of at least an interval scale. This is achieved due to the fact that the quantitative characteristics of the measured qualities are initially assigned to the subject, and the subject himself is instructed to conduct a quantitative comparison of the objects of evaluation, and not qualitative, as in the method of scoring, whose procedure is very similar to the procedure of direct evaluation.

For example, the experimenter may ask the subject to evaluate his taste sensations as follows: I want you to tell me how much sweet this sample seems to you, compared to the standard & quot ;. Methods of direct scaling suggest that the subject is indeed able to carry out such an assessment. Therefore, no special procedures for transforming the original data, characteristic of indirect methods, do not imply these methods. The path from the raw data provided by the subjects to the scale itself is extremely simple and short.

An important difference between the methods of direct scaling from the already mentioned methods of scoring, ranking, sequential categories or pair comparisons, also allowing to construct an interval scale, is the fact that the equality of intervals in the case of using direct scaling procedures is established directly by the examinees during the evaluation of the assigned to him objects, whereas indirect methods assume the allocation of equivalent intervals only on the basis of the analysis of the frequency distribution of the answers of the subjects.

Depending on which scale the direct scaling methods allow, they are divided into interval methods and methods of magnitude.

Interval methods allow you to set the interval equality. Thus, they can be used to obtain a scale of equal intervals. The methods of magnitude are based on comparing the relationships and establishing their equivalence. Thus, they give a relationship scale.

In turn, both methods can be divided into productive and evaluation methods.

Productive methods suggest that subjects perform some actions with the evaluated objects. For example, the experimenter may ask the subject to determine the value of one stimulus so that it is twice as large as the value of another stimulus used as a reference. In the case of evaluation methods , all manipulations with stimuli are performed by the experimenter, and the subject only evaluates his feelings. For example, he can report that the new stimulus is twice as large (brighter, colder) than the reference one, or one and a half times as paler as the reference one.

So, the psychological dimension involves the expression of psychological characteristics in the form of a measure that represents a value on the scale. In psychology, there are only four types of scales that differ in the number of relationships into which objects measured by a scale can enter, but also the number of operations that can be performed with these objects. The procedures for constructing scales (scaling procedures) assume a certain set of rules, according to which a scale is constructed. Knowledge of the features of the scales and the rules for their construction is crucially important in psychological research, since without this, neither the evaluation of the influence of psychological factors, nor their change, nor the relationship with each other is possible. If the measurement is performed in violation of these rules, this will lead to distortions in the results of the study.

thematic pictures

Also We Can Offer!

Other services that we offer

If you don’t see the necessary subject, paper type, or topic in our list of available services and examples, don’t worry! We have a number of other academic disciplines to suit the needs of anyone who visits this website looking for help.

How to ...

We made your life easier with putting together a big number of articles and guidelines on how to plan and write different types of assignments (Essay, Research Paper, Dissertation etc)