The researcher’s next task is to evaluate research data in order to make sense of what has been collected. Before the researcher can gain understanding from the collected data, he/she must first examine the raw information (i.e., what was actually collected) to make sure the information exists as required. There are many reasons why data may not be presented in the form needed for further analysis. Some of reasons include:
This most likely occurs when the method of data collection is not fully completed, such as when the person taking part in the research fails to provide all information (e.g., skips questions on a survey).
Data Entry Error
This exists when the information is not recorded properly which can occur due to the wrong entry being made (e.g., entry should be choice “B” but is entered as choice “C”) or failure of data entry technology (e.g., online connection is disrupted before full completion of survey).
This occurs when there are apparent inconsistencies in responses, such as when a respondent does not appear to be answering honestly.
To address these issues the researcher will take steps to “cleanse” the data which may include dropping problematic data either in part (e.g., exclude a single question) or in full (e.g., drop a respondent’s entire survey). Alternatively, the research may be able to salvage some problem data with certain coding methods, though a discussion of these is beyond the scope of this tutorial.