In an explanatory research design, the most likely kind of bias is the citation type. In citation bias, researchers may be reluctant to publish some discouraging findings, especially if they believe that they may tarnish their reputations or personal abilities and affect the effectiveness of their products. For that reason, citation bias makes researchers submit positive results only for publication, while suppressing negative findings. In most cases, the motive of citation bias is to gain popularity or self-appraisal (Riegelman, 2005). Positive results, also known as statistically significant findings, may include results that show that a certain intervention is functioning well.
Citation bias is likely to be encountered in explanatory research designs because through them, causal hypotheses can be investigated, analyzed, tested, and published. Explanatory research investigates why certain variables are related and it tries to look into the causes of certain phenomena. However, in the process of publication of the findings, some researchers are likely to concentrate on positive results alone and ignore the negative ones (Riegelman, 2005).
Citation bias may be common in medical research studies, especially in those that try to find the cure for a significantly important or mysterious pathogen. In this case, only the positive sides of the results are likely to be published. For example, a potential drug against a certain intractable virus, which has been researched on, is likely to be published quickly in medical journals and in English language to target many readers (Riegelman, 2005). However, the negative side effects of the drug may be suppressed in such publications.
In this case, the most likely type of bias is measurement bias. It includes systematic errors that are likely to arise during collection of significant data. It also includes calibration errors from instruments, which can cause inaccurate measurements in data recording (Mitchell & Jolley, 2012). In addition, measurement bias may also refer to inappropriate measuring of data to force an expected outcome.
This type of bias is likely to be experienced in descriptive research...