Coursework

Posted: August 5th, 2013

Qualitative and Quantitative Research

            Research is divided into two categories namely, qualitative and quantitative research. Qualitative research refers to the inductive study of data through methods such us in-depth interviews, focus groups, and formulation of hypotheses. On the other hand, quantitative research involves a deductive process that validates hypotheses, theories and predetermined concepts through structured interviews, numeric documents, observations and surveys (Ritchie & Lewis, 2003). According to Polit & Beck (2008), these two categories are under broader worldviews termed as interpretive or naturalistic and positivist paradigms. The positivist paradigm under which quantitative research falls assumes the existence of a particular measurable reality while the naturalistic or interpretive paradigm is reflected by qualitative research and it is built on the assumption that there are numerous realities, which change with time. Therefore, according to the interpretive paradigm, it is difficult to be accurate with measurement on subjects of dissimilar characteristics that are constantly changing with time.

For example, to determine the rate of college dropouts in a popular college and the impact it has on the college, I will want to ensure that every present student and dropouts from the college has an equal chance of being a participant. I will select my participants as probability or simple random samples. I will employ quasi-random or systematic sampling by having random points on the list of the total students in one school (Babbie, 2012).This will allow me to identify the students who have problems with college in terms of fees, drug addiction or loss of interest. However, the random points on the list may fail to represents all students in the event that students of the same caliber follow each other by name. Thus, stratified sampling will be useful to ensure specificity and diversity among the population of the students in the particular college. In a population of 10,000 students, I will work with 1000 students because the number is feasible. it is large enough to ensure population validity and small enough to reduce errors and complexity in computing the variables.