Monday, August 1, 2016

Secondary data

What is secondary data? It is data that has already been collected by someone else. It may be data that is collected as a standard practice in an organization (e.g., medical charts, pre-employment testing). Some things to know about this type of secondary data, particularly if it is from an organization where you are employed. First, you will only be able to use information that is available to any outside researcher. Second, the data will need to be "de-identified" before you get access to it. This means someone else will have to remove all names of individuals, so the data is anonymous when you receive it. Check with IRB early in the process, if you are interested in this option.

Another source of secondary data is large datasets that have been available by the original researchers. Walden provides students with the opportunity to access hundreds of datasets. To see what is available – go to http://www.icpsr.umich.edu/icpsrweb/ICPSR/ The researchers provide information on the background, variables, and any coding they used for data input. The use of such a dataset is perfectly acceptable as a dissertation, however a few cautions. Make sure that the study you are considering has not been previously published with the data. Typically, the researchers give a bibliography of all articles published by them. However, it does not mean that other people have not published. Search the library carefully, and include dissertations in the search. Use the name of the dataset as a search term. Another very important caution is do not try to access the data until you have IRB approval, you must have Walden's ok to proceed. Also, be aware that it can be tricky to convert the data to SPSS, and to understand the logic of their data entry. You probably will not be able to contact the researchers, so you will need to figure it out with the help of your committee.

Secondary data analysis is a great way to get access to difficult populations' data; an example might be sex offenders. However, you are stuck with the variables that the original researchers used, and there is no possibility of getting additional information from the participants. If you decide to go this route, you can reduce your time to completion considerably, but be prepared to work through the issues I outlined above.

Next time, I invite you to look over my shoulder as to I do the literature search for an article I am writing. Do you have an issue or a question that you would like me to discuss in a future post? Would you like to be a guest writer? Send me your ideas! leann.stadtlander@waldenu.edu

No comments:

Post a Comment