Threats to Validity
Validity refers to how accurate or trustworthy the research findings are (Cozby & Bates, 2015). There are various types of validity that researchers evaluate. Internal validity refers to accuracy in the cause-and-effect relationship. This relates to how confident we are that the observed relationship between the independent and dependent variables in the study is accurate. External validity, on the other hand, deals with our confidence in being able to generalize the results of the study to other populations and settings. That is, are our results trustworthy only for our sample, or can we assume that the same relationship is observed in other samples and locations. The concept of validity, and particularly internal validity, is mostly applicable to experimental and quasi-experimental studies. Studies with experimental and quasi-experimental designs have the possibility of establishing a causal relationship among variables of interest. However, correlational studies, such as the current study, do not provide researchers with confidence about casual relationship among variables. That is, a researcher cannot make causal relationships based on correlational studies. Researchers working with correlational studies could make inferences on the relationship between variables but cannot specifically state that one variable caused changes in another. Thus, internal validity threats such as mortality, history, and selection are not applicable to this particular study. For example, since participants complete the survey once, there is no threat of significant changes in the participants to affect the confidence we have in the results. However, internal validity of the study of correlational studies are mostly concerned with validity of instruments used. Reliability and validity of measures used in this study has been reported in previous sections.
External validity refers to our confidence in being able to generalize the study’s findings to other populations and settings. The current study employes a convenience sampling approach to data collection. Convenience sampling presents a threat to the study’s external validity as it provides the researcher with little confidence that the participants in the study are representative of the target population. Studies with probability sampling, in which each member of the target population has the same statistical chance of getting selected for the study, have higher external validity as compared with studies using convenience sampling.
Ethical Procedures
Summary
