Reliability and Validity has been applied commonly in qualitative research and has been with time considered the point of shift in the research. Consequently, for them to be used in a naturalistic manner they have to be redefined; in view of the fact that they are based on positivism. This paper critically tackles Reliability and Validity in explaining what it is all about.
Alternate-form reliability refers to the degree of relatedness of different forms of the same test. Example of the alternate form reliability is the psychological test in which questions are altered. The Internal-consistency reliability is used in reference to the overall degree of relatedness of all the items in a test or the raters in a judgment study. Internal-consistency reliability: The overall degree of relatedness of all items in a test or all raters in a judgment study (Schmitt & Landy, 1993)
Internal-consistency is achieved by measuring the reliability between different items using the same test. For example, in the case where a respondent expresses agreement with two different statements and disagreement with the statements that tend to oppose the first statements then there is good internal consistency of the test. Item-to-item reliability: The reliability of any single item on average (analogous to judge-to-judge reliability, which is the reliability of any single judge on average). The Item-to-item reliability is a type of reliability of any single item on average. The example would be the reliability of the two items such as the coins that are seen to be identical.
Test-retest reliability: The degree of temporal stability (relatedness) of a measuring instrument or test, or the characteristic it is designed to evaluate, from one administration to another; also called retest reliability.
Test-retest reliability is used to show the degree of temporal stability in the measuring instrument or test, or the characteristic, this type of reliability is designed with the purpose of evaluation, from one administration to the next. An example is when a group of respondents is exposed to the tests for IQ scores: in this case each respondent is tested twice with the two tests being staged a month apart. Then, the correlation coefficient obtained between the two sets of IQ-scores is the required measure for the test-retest reliability of the test.
Construct validity: This shows how a practical test which is developed from the theory can exactly measure what the theory postulates. The degree to which the conceptualization of what is being measured or experimentally manipulated is what is claimed, such as the constructs that are measured by psychological tests or that serve as a link between independent and dependent variables.
Content validity: The adequate sampling of the relevant material or content that a test purports to measure. This is a non-statistical validity and it involves a kind of systematic examination of the test's content in order to determine its coverage of the representative sample. An example is the psychological test uses a questionnaire to collect data, the content of the question are is measured to establish whether it covers all the items concerning intelligence. A given test has the content validity developed it by carefully selecting the items so as to comply with the test specifications that are drawn up by thoroughly examining the subject domain. Examples include the use of statistical means to find out from the participants if the construct was useful.
Convergent and discriminate validity: convergent validity is used in reference to the extent to which the measurement correlates with other types of measurement which are relevant while discriminate validity shows the lack of correlation between the operationalizations that are not correlated.
Criterion validity: The degree to which a test or questionnaire is correlated with outcome criteria in the present (its concurrent validity) or the future (its predictive validity).According to Hambleton & Novick (1973) Criterion related validity has two types, concurrent and predictive validity, which are both based on correlation. Concurrent validity reflects a standard of the test results from students.
External validity: This refers to the relevance of the internal validity of the results in a test to the other cases in general. It is also the generalizability of an inferred causal relationship over different people, settings, manipulations and research outcomes.
Face validity: The degree to which a test or other instrument "looks as if" it is measuring something relevant. This type of validity requires personal views, example include asking the participants as to whether they think the construct was relevant or useful. It does not refer to what the test exactly measures instead it refers to what the test appears to superficially measure. Face validity refers to whether the test is seen as valid to those who are being examined, those who are involved in decision making on the use of the test, and other observers.
Internal validity: This is the inductive estimation of the degree on which the conclusions on the causal relationships are made in relation to the measures used. The higher degree of the internal validity is achieved with use of the experimental techniques under controlled conditions and the analyzing of the effects of independent variables on the dependent variables.
Statistical-conclusion validity: This is the measure of the extent to which the conclusion reached on the variables can be justified .The accuracy of drawing certain statistical conclusions, such as an estimation of the magnitude of the relationship between an independent and a dependent variable (the effect size) or an estimation of the degree of statistical significance of a particular statistical test. (Rosnow & Rosenthal, 2008) In statistics it ensures that the sampling procedures are carried out adequately and there is measurements that are procedurally reliable with appropriate tests.
Data collection methods in human research
Administering written questionnaires
- The Focus group discussions
- The Projective techniques mapping
Instruments in human research
- Mechanical instruments such tape recorders.
Skilful use of this methods and instrument reduces the chance of biased information and gives a more comprehensive understanding of the topic that is under study.
Data collection method in human managerial
- Structured observations of meetings and events
Instruments in human research
- Mail and telephone surveys
This ensures that the research apply the primary data thereby increasing reliability and validity. In conclusion, reliability and validity have been identified as a very vital aspect since they reflect trustworthiness, quality and rigor in the field of qualitative research. Thus it eliminates bias, and makes sure the researcher is truthful and honest on every issue researched.