Measurement can be an independent research method, but it can also act as a component of the integrated procedure of an experiment.

As an independent method, it serves to identify individual differences in the behavior of a subject and in his reflection of the surrounding world, as well as to investigate the adequacy of reflection (the traditional task of psychophysics) and the structure of individual experience.

Measurement is incorporated into the context of an experiment as a method of registering the state of the object of study and, accordingly, the change in this state in response to the experimental intervention. In psychology, three basic procedures of psychological measurement are distinguished. The basis for the distinction is the object of measurement. First, a psychologist may measure features of people's behavior in order to determine how one person differs from another in terms of the expression of one or another property, the presence of one or another mental state, or in order to assign him to a particular personality type. By measuring features of behavior, the psychologist determines the similarities or differences among people. Psychological measurement becomes the measurement of subjects.

Second, a researcher may use measurement as a task for the subject, in the course of performing which the subject measures (classifies, ranks, evaluates, etc.) external objects: other people, stimuli, or objects of the external world, or his own states. Often this procedure turns out to be the measurement of stimuli. The concept of «stimulus» is used in a broad sense, and not in a narrowly psychophysical or behavioral one. By a stimulus is meant any object that can be scaled. Third, there exists the procedure of so-called joint measurement (or joint scaling) of stimuli and people. In this it is assumed that «stimuli» and «subjects» can be located on one axis. The behavior of the subject is regarded as a manifestation of the interaction of personality and situation.

Outwardly, the procedure of psychological measurement in no way differs from the procedure of a psychological experiment. Moreover, in psychological research practice, «measurement» and «experiment» are often used as synonyms. However, in conducting a psychological experiment we are interested in the causal relationships between variables, whereas the result of a psychological measurement is merely the assignment of the subject, or of the object he is evaluating, to one or another class, point on a scale, or space of attributes. The procedure of psychological measurement consists of a number of stages analogous to the stages of experimental research.

The foundation of psychological measurements is the mathematical theory of measurement — a branch of psychology developing intensively in parallel with, and in close interaction with, the development of the procedures of psychological measurement. Today it is the largest branch of mathematical psychology.

The measurement scale is the basic concept introduced into psychology in 1950 by S. S. Stevens; his interpretation of the scale is still used in the scientific literature today. A scale – in the literal sense is a measuring instrument.

The type of scale determines the set of statistical methods that can be applied for processing the measurement data.

Several types of scales are distinguished:

• The nominal scale - is obtained by assigning «names» to objects. Objects are compared with one another, and their equivalence – nonequivalence is determined.

• The ordinal scale - the ordering of objects by the degree of expression of some attribute.

• The interval scale.

• The ratio scale.

Types of psychological measurements

In the natural sciences, as S. S. Papovyan proposes, three types of measurement should be distinguished:

1. Fundamental measurement is based on fundamental empirical regularities that make it possible to derive a system of numerical relations directly from an empirical system.

2. Derived measurement is the measurement of variables on the basis of regularities connecting these variables with others. Derived measurement requires the establishment of laws describing the connections between individual parameters of reality, making it possible to derive «hidden» variables on the basis of directly measured variables.

3. Measurement «by definition» is carried out when we arbitrarily assume that a system of observed attributes characterizes precisely this, and not some other, property or state of the object.

The methods of psychological measurements can be classified on various grounds:

1) the procedure for collecting the «raw» data;

2) the subject of measurement;

3) the type of scale used;

4) the type of material being scaled;

5) the scaling models;

6) the number of dimensions (unidimensional and multidimensional);

7) the power of the data-collection method (powerful or weak);

8) the type of the individual's response;

9) what they are: deterministic or probabilistic.

For the experimental psychologist, the main grounds are the procedure for collecting data and the subject of measurement.

The following procedures of subjective scaling are most often applied:

The method of ranking. All the objects are presented to the subject simultaneously; he must order them by the magnitude of the measured attribute.

The method of paired comparisons. The objects are presented to the subject in pairs. The subject evaluates the similarities — differences between the members of the pairs.

The method of absolute judgment. The stimuli are presented one at a time. The subject gives an evaluation of the stimulus in the units of the offered scale.

The method of choice. The individual is offered several objects (stimuli, statements, etc.), from which he must select those that meet a given criterion.

By the subject of measurement, all techniques are divided into a) techniques for scaling objects; b) techniques for scaling individuals; and c) techniques for the joint scaling of objects and individuals.

Techniques for scaling objects (stimuli, statements, etc.) are built into the context of an experimental or measurement procedure. In essence, they are not the task of the researcher but represent an experimental task for the subject. The researcher uses this task to elicit the behavior of the subject (in this case — reactions, actions, verbal evaluations, etc.) in order to learn the features of his psyche.

In subjective scaling, the subject performs the functions of a measuring instrument, while the experimenter takes little interest in the features of the objects being «measured» by the subject and instead investigates the «measuring instrument» itself.