So to follow-up on my last blog post, I took a shot at developing a matrix that shows the relation between various concepts, and how combining these concepts can be of statistical significance for Health Care organizations. Before I go into detail about the matrix, I would like to stress one fundamental idea; through aggregation of this information, anonymity of individuals -henceforth referred to as “the participants”- must be maintained at all times. This would mean that the data collection procedure should focus on collecting information of statistical significance only.
Obviously counting how many times the name “Smith” was repeated is of no true value for our purpose here, and therefore, we do not need to collect the user names for the purpose of analytics (but only in the background to count unique users across each SM platform). In this way, we get the information we need, without disclosing the participants’ identities. On the other hand, we need to include blocks of information that provide some meaning when quantified. For example, how many unique posts were related to Diabetic Retinopathy? Read the rest of this entry