In statistical terms, validity is defined as the proportion of true variance that is relevant to the purposes of the test. With the term “relevant” we understand what is attributable to the variable, to the characteristics measured by the research (1). Did you know that there are several types of validity? We will then talk specifically about the validity of the content.
The validity of a test is usually defined by:
- In psychometric terms.
- Validity is a concept that has gone through a long evolutionary process.
- At first.
- Muiz (1996) adopted validity with a specific position.
- He argued that “a test is valid for what it correlates with.
Validity is now understood as a comprehensive evaluative judgment; in this trial, empirical evidence and theoretical hypotheses support the adequacy and adequacy of interpretations not only of the items, but also of how people react, as well as the context of the evaluation.
Therefore, what is validated is not the test, what is specifically validated are the inferences that are extracted from it, this has two consequences:
In this context, the concept of validity refers to the adequacy, meaning and usefulness of the specific inferences made with the test results. Validation of a test is the process of accumulating evidence to support these inferences, so validity is a unitary process. Although evidence can accumulate in several ways, validity still refers to the degree to which this evidence supports inferences made from scores (4).
In 1954, a committee chaired by LJ Cronbach established, at the request of the American Association of Psychology (APA), that validity had four types, these are:
Currently, it is accepted, from a scientific point of view, that the only permissible validity is the validity of built (Messick, 1995).
In the study of validity, the evidence is linked to five aspects
Thus, within this validity, we can understand other types of validity or strategies, as mentioned above, is the validity of the content, predictive validity, competitive validity and conceptual validity.
This type of validity answers the question: are the items that make up the test really a representative sample of the content domain or behavioral domain we are interested in?
For us to understand this, a domain or behavioral field is a hypothetical grouping of all possible elements covering a specific psychological area; for example, a vocabulary test should be an appropriate sample of the possible domain of items in this area.
In this sense, is the validity of the content one? Measure sampling adequacy. Measure? It is enclosed in quotation marks because this type of validity consists of a series of estimates or opinions, these estimates do not provide a quantitative validity index. (1)
This type of validity is primarily associated with performance tests (math test, history?). For determination, the test questions are systematically compared to the behavioral domain of the applied content.
For example, we have a list of 500 words that we expect students in a course to be able to spell correctly, so performance against these words will be of exclusive importance in assessing the student’s ability to spell 500 words correctly. content will only be valid as long as an adequate sample of the 500 words it represents is provided. (1)
If we select only easy or difficult words, or words that represent only certain types of spelling errors, we will probably get very low content validity.
The main aspect of the content validity is the sampling of the elements, that is, the validity of the content determines whether the sample of its items is representative of the universe or the domain of behavior of the item to be represented (1).
Therefore, the validity of the content is the type of validity related to the test itself and what is intended to measure, for example, this will allow us to know if the sample of items in the test is representative of the field of mathematics that we want to measure. Therefore, it is an important concept in both statistics and the use of psychological or performance tests.
In conclusion, the validity study is an analysis of a metric test; in our case, since we are talking about psychology, psychometric, whose conclusions refer to the extent to which this test measures what we want to measure, logically, how much more valid is a test in the absence of a deeper analysis?like reliability, the best.