Psychometrics

The Psychometrics is the field of psychology, the general deals with the theory and method of psychological measurement. Main tasks of the research is primarily the development and improvement of theoretical approaches of psychological measurement, and the development of fundamental methods for the development of measurement instruments and general procedures for psychological measurements, both for basic research and applied fields of psychology. Currently outweigh work on psychological tests, observation instruments, and other methods psychological assessments for more applied fields, especially of traffic psychology, human resources and occupational psychology, clinical neuropsychology, school psychology and legal psychology.

Definitions

The now common declaration defines psychometrics as " every branch of psychology that deals with the psychological measure". According to this view so every field of psychology psychometric shares, or, in other words, ultimately, psychometry is one of the cross-cutting, joining, methodological approaches of psychology; Psychometrics is therefore a " red thread " that runs through all branches of psychology. It thus combines all the psychologists and is an essential element in the education profile of the profession and of psychology as a science.

Other psychologists prefer in their professional practice interpretive (qualitative ) methods of psychology and qualitative research, such as qualitative content analysis, differentiated methods of psychological interviews, psychoanalytic interpretations. Mutual misunderstandings are often due to the ambiguous concept of measurement ( scaling) and on opposite beliefs in fundamental questions of philosophy of science and the psychological anthropology.

Developments

The psychometrics home ultimately a compilation of specific mathematical and statistical models and methods. These have been developed to combine the knowledge obtained of psychological research and empirical data to describe and to draw conclusions from them. Above all, they also serve the psychological models, such as mathematical and statistical psychometric models on various cognitive functional areas and personality areas that are derived from the corresponding basic theories and formalized.

This compilation can be roughly divided into three categories, which in turn have partly interactional each other (thus influencing one another and be fruitful ) are connected, and interactions with other areas, particularly in sociology and economics.

We distinguish three interrelated strands or categories:

  • Approaches to factor analysis
  • Approaches to psychological scaling
  • Aspects of psychological measurement in the narrow sense, namely those of the test psychology

It is important that the psychometrics not directly involved in the development of research methods, but with the general possibilities and problems of psychological measurement or the Measurable making.

The scale has its origin in psychophysics, particularly in the work of Fechner. Of particular note here are the approaches of them influenced by Thurstone, who was also involved in the development of factor analysis and his "Law of comparative judgment" and its further developments. In turn are based on this specific estimation models, as well as the development of the multi-dimensional scaling, which is in turn connected to approaches the factor analysis. Further developments have multiple methods of scaling and those of the non- dimensional scale such as the conjoint measurement. Other normative models have been developed from the psychophysical approaches, which then influenced the development of mathematical psychology. The summary of mathematical psychology and psychometrics is often referred to as quantitative psychology.

Approaches to factor analysis influenced the development of certain statistical estimation extent, the analysis of covariance structures to linear structural equation models. The test psychology has been greatly influenced by both the scaling, as well as the factor analysis. Here evolved over the classical test theory item response theory, influenced by normative models of scaling, which in turn influenced the development of latent class models and structural equation models, this. Among mutual influence of quantitative social research and econometrics The psychometrics is a rich direction for further developments of applied statistics. They therefore fertilized many other quantitative working and busy with problems of measurement science, as in turn affects these psychometry and its developments.

Psychometric approaches, especially the Item Response Theory and the linear structural equation models were further developed in recent years, especially due to their use in the school psychology field in the context of international education comparative studies such as PISA studies. The same applies to their use, eg, in the context of standardized tests in North Rhine -Westphalia or similar quality assurance measures such as school performance studies in Berlin and other German states.

Criticism

Even Immanuel Kant exercised fundamental critique of the idea of an exactly measured psychology, although he attacked only a strictly introspectionist conception of psychology. Herbart, the newly founded in the 19th century, mathematical psychology, and initially also Wilhelm Wundt wanted to contradict Kant, however, overlooked the fact the target of his criticism. Since then, the debate continues and often includes the psychological testing and the entire methodology of psychology. Instead of the flat-rate question " Are psychic phenomena measurable? " To discuss, however, is to distinguish precisely between:

  • The measurements in psychology as a behavioral science based on objective behavioral responses, ie cognitive or motor performance, including their physiological, endocrine, neural bases (see Biological Psychology, Neuropsychology, Psychophysiology );
  • The assessment of sensation strengths in psychophysics as a special case of psychometry, the intensities of the stimuli are physically defined and anchored thereto;
  • Psychometrics of internal states ( emotions, moods ) and of latent behavioral dispositions such as needs, attitudes and personality traits.

Basically psychological test scores and other examination data should reflect the empirical characteristic relationships accurately and clearly, that is expressed in adequate number ratios. Various scale levels can be distinguished, depending on whether only the frequency characteristics are counted, a comparative statement "A is more intelligent than B" or a measurement in a narrow sense is carried out, that is, with gradual differences on a scale that is formed from equal intervals like a thermometer scale. The theoretical assumptions and the permissible or impermissible arithmetic operations are treated in the general scaling theory or theory of measurement and are also fundamental for psychometry.

For the objective intelligence and achievement tests, an interval scale can be assumed in general. For subjective statements about internal states, modes of experience and being, this assumption is highly questionable, because it lacks the equality of intervals and of course the ability to control by other observers or for direct comparison with the well-being of other people. This objection also applies in the psychology widespread personality questionnaire and other questionnaires, when, on its evaluation individual statements are added to test values ​​as if it were to metric levels of scale.

The measured theoretical decisions are not arbitrary, but there are very different viewpoints. " The quality of a measurement scale is thus ultimately of theoretical decisions, ie depending on interpretations ". Some methodologists understand the measurement of psychological variables as a check of structural hypotheses, so make a close relationship between fairs and psychological theory here in the sense of mathematical psychology. Others think that the scale level of the output data need not be justified empirically beforehand or argumentative, it would not matter whether the scale level "true" is, but if the measurement model is useful.

Self-assessments do not provide measurement data in the strict sense, but are subjective estimation method with unknown scale level, with probably different from individual to individual, pseudo- numeric reference systems. The equality of the scale intervals is not given and, consequently, the item scores can be added to a test value not easy. About the consequences of this fact, however, there are major differences of opinion in the literature. Can the measured theoretical assumptions of intelligence tests and the scientific behavioral analysis are transferred to introspection and self-assessments readily?

A not insignificant number of psychologists practicing epistemological critique of their view unreflected measurement and test theory and a pseudo- scientifically oriented psychology. Subjective- mental phenomena and psychological characteristics would be reduced to numbers, without clearly demonstrate the shortcomings of psychometrics. The fundamental criticism of the " measurement of man" and the critique of reductionism often combines with socially critical arguments.

However, the opposite position is critically discussed. The criticism that psychology is not experimentally to explore and certainly not mathematically describe, among other things as a conclusion rejected on the basis of a resting on a präkonzipierten concept of psychic understanding.

664105
de