Assess Validity of Data IV

Data Validity Assessment Triangulation

Assessment of qualitative data and their Interpretation

Validity Assessment of qualitative data and their interpretation, Credible data collection ,Denzin, 1989, Method Triangulation,Whittemore, Chase, and Mandle (2001).

    The criteria and methods of assessment described thus far apply to quantitative data collection instruments. The procedures cannot be meaningfully applied to such qualitative materials as narrative interview data or descriptions from a participant observer's field notes, but qualitative researchers are also concerned with data quality. 

    The central question underlying the concepts of reliability and validity is: Do the data reflect the truth? Qualitative researchers are as eager as quantitative researchers to have data reflecting the true state of human experience. 

    Nevertheless, there has been considerable controversy about the criteria to use for assessing the "truth value" of qualitative research. Whittemore, Chase, and Mandle (2001), who listed different criteria recommended by 10 influential authorities, noted that the difficulty in achieving universally accepted criteria (or even universally accepted labels for those criteria) stems in part from various tensions, such as the tension between the desire for rigor and the desire for creativity. 

    The criteria currently thought of as the gold standard for qualitative researchers are those outlined by Lincoln and Guba (1985). These researchers have suggested four criteria for establishing the trustworthiness of qualitative data: credibility, dependability, confirmability, and transferability. 

    These criteria go beyond an assessment of qualitative data alone, but rather are concerned with evaluations of interpretations and conclusions as well. These standards are often used by qualitative researchers in all major traditions, but some exceptions are noted. Credibility Credibility is viewed by Lincoln and Guba as an overriding goal of qualitative research, and is considered in the Whittemore et al. (2001) synthesis as a primary validity criterion. 

    Credibility refers to confidence in the truth of the data and interpretations of them. Lincoln and Guba point out that credibility involves two aspects: first, carrying out the study in a way that enhances the believability of the findings, and second, taking steps to demonstrate credibility to consumers. 

    They suggest a variety of techniques for improving and documenting the credibility of qualitative research. Prolonged Engagement and Persistent Observation Lincoln and Guba recommend several activities that make it more likely to produce credible data and interpretations. 

    A first and very important step is prolonged engagement the investment of sufficient time collecting data to have an in-depth understanding of the culture, language, or views of the group under study and to test for misinformation and distortions. Prolonged engagement is also essential for building trust and rapport with informants, which in turn makes it more likely that useful, accurate, and rich information will be obtained.

    Credible data collection in naturalistic inquiries also involves persistent observation, which concerns the salience of the data being gathered and recorded. Persistent observation refers to the researchers' focus on the characteristics or aspects of a situation or a conversation that are relevant to the phenomena being studied. As Lincoln and Guba (1985) note, “If prolonged engagement provides scope, persistent observation provides depth”

Triangulation 

      Triangulation can also enhance credibility. As previously noted, triangulation refers to the use of multiple referents to draw conclusions about what constitutes truth, and has been compared with convergent validation. The aim of triangulation is to “overcome the intrinsic bias that comes from single-method, single-observer, and single-theory studies” (Denzin, 1989, p. 313). 

    It has also been argued that triangulation helps to capture a more complete and contextualized portrait of the phenomenon under study a goal shared by researchers in all qualitative traditions. Denzin (1989) identified four types of triangulation: data triangulation, investigator triangulation, method triangulation, and theory triangulation. 

    Data triangulation involves the use of multiple data sources for the purpose of validating conclusions. There are three basic types of data triangulation: time, space, and person. Time triangulation involves collecting data on the same phenomenon or about the same people at different points in time. 

    Time triangulation can involve gathering data at different times of the day, or at different times in the year. This concept is similar to test–retest reliability assessment; That is, the point is not to study the phenomenon longitudinally to determine how it changes, but to determine the congruence of the phenomenon across time. Space triangulation involves collecting data on the same phenomenon in multiple sites. 

    The aim is to validate the data by testing for cross-site consistency. Finally, person triangulation involves collecting data from different levels of persons: individuals, groups (eg, dyads, triads, families), and collectives (eg, organizations, communities, institutions), with the aim of validating data through multiple perspectives on the phenomenon .

    The second major type of triangulation is investigator triangulation, which refers to the use of two or more researchers to analyze and interpret a data set. Through collaboration, investigators can reduce the possibility of a biased interpretation of the data. Moreover, if the investigators bring to the analysis task a complementary blend of skills and expertise, the analysis and interpretation can benefit from divergent perspectives. 

    Blending diverse methodologic, disciplinary, and clinical skills also can contribute to other types of triangulation. Investigator triangulation is conceptually somewhat similar to interrater reliability in quantitative studies.
    With theory triangulation, researchers use competing theories or hypotheses in the analysis and interpretation of their data. Qualitative researchers who develop alternative hypotheses while still in the field can test the validity of each because the flexible design of qualitative studies provides ongoing opportunities to direct the inquiry. 

    Theory triangulation can help researchers to rule out rival hypotheses and to prevent premature conceptualizations. The quantitative analogue for theory triangulation is construct validation.
    Method triangulation involves the use of multiple methods of data collection about the same phenomenon. In qualitative studies, researchers often use a rich blend of unstructured data collection methods (eg, interviews, observations, documents) to develop a comprehensive understanding of a phenomenon. 

    Multiple data collection methods provide an opportunity to evaluate the extent to which an internally consistent picture of the phenomenon emerges.