There are two aspects of validity, internal validity and external validity. Internal validity refers to an approximate truth about inferences regarding causal relationships. Internal validity is only necessary in circumstances where there is a need to establish a cause and effect relationship. External validity is closely related to generalizing, and the ability to generalize a particular study to other people and other situations. This short paper will discuss both internal and external validity, and the threats to the data collection process. Internal Threat to Validity of Data Collection Process
Regardless of the business an evaluation process is necessary. Even when it seems everything is falling into place there still are threats that question the validity of the information collected. One of the most common types of internal threats that an evaluation process may encounter is selection bias. This would occur when more of one type of person gets into a study or evaluation. Monitoring that there is an equal mix of participants will ensure that bias is less likely to occur.
External Threat to Validity of Data Collection Process. Researchers identify major threats of external validity in three ways, people, places and or times. Threats are seen as a generalizability where as results are limited. External validity threats are identified in four different classes. The first one is interactions or reactive effects testing, next, interactions effect selection of bias interactions. Third class is reactive effects of treatment arrangements and last, is multiple treatment interference.
Posavac, E. J., & Carey, R. G. (2007). Program evaluation: Methods and case
studies (7th ed.). Upper Saddle River, NJ: R. G. Carey and Associates.