Reference no: EM131549290

Question: From a statistical point of view, J. Park and Park (2016) reveal a population is all "persons, objects, institutions, or other entities" that can facilitate the acquiring of data which is of interest to the researcher, whereas a sample is a proper subset of the population and contains the "persons, objects, institutions, or other entities" that are observed and from whom data is collected (p. 5). For example, if the researcher is interested in the 18-20-year-old American male perspective on the benefits of social media, the population is quite large. However, the researcher may only be interested in the 18-20-year-old males in a smaller geographic region, which would reduce the number of individuals within the population of interest, and then the sample would be drawn from this smaller population.

Based upon an a-priori G*Power analysis for the Linear multiple regression: Random Model, using four predictors, each with an estimated correlation of ? = 0.1, with a = 0.05 and Power = 0.80, the estimated sample size needed for my research study is 294 participants (Faul, Erdfelder, Buchner, & Lang, 2009). At present, I have tentative permission to access a proprietary archival data set from a nationally representative sample with over 10,000 participants. My goal will be to utilize a subset of this data that comprises community college students, which is estimated to include approximately 2,000 participants. If the IRB at GCU denies access to this archival data set, the target population and resulting sample will change. In addition, permission will be sought to utilize data collection instruments that are known to be reliable and valid, as the estimated cost of these instruments is about $5.00 per participant. Given that I need 294 participants at a minimum, the cost is approximately $1500.00 just for the instruments.

The types of descriptive statistics that will be calculated include frequencies of gender, minority status, and age groups, as well as the mean, range, and standard deviation of participants ages and of each variable in the study. Graphical displays and tables will also be constructed to provide a quick visualization of the descriptive statistics. Furthermore, a correlation matrix will be created that incorporates the results of the correlational analysis.