What I’ve Learned about Statistics
Statistics is all around us that, in fact, it would be difficult to go through the day without being flooded with some sort of statistics or statistical information. It is so commonly used in everyday conversations – be it regarding customer surveys, weather forecasts, political polls, or sports statistics – that we find it difficult to differentiate flawed from actual valid claims. So many times we hear “9 out of 10 says…” or “99 percent of the people” that statistics has been labeled as the science of stating precisely what we do not really know. In this paper, I will break down what statistics actually is and its daily application in our lives, ...view middle of the document...
GPAs, AFOQT scores, and job classifications are also some of the other similar data maintained.
Inferential statistics. Inferential statistics involves taking a deeper look at the information gathered from a sample to draw conclusions about the population (Tanner & Youssef, 2013). Using data collected from previous years on either all of the cadets enrolled in the program or cadets from each Academic Status (AS) level, we are able to predict approximately how many join the program for free tuition/books, how many are interested in being a nurse/pilot/navigator, how many drop out of the program each term, or how many actually complete the program and commission. Based on previous terms’ enrollment data, we could estimate the number of students who will stay in the program for its entirety and commission upon graduation. We would have to look at not only how many graduated each year, but the variables that may have contributed to them staying in the program – availability of scholarship funds, number of active duty slots being offered, changes in requirements, etc.
Null hypothesis. Tanner and Youssef-Morgan (2013) identify null hypothesis as the prediction of the result being insignificant or of no difference. It is your assumption that there will be no change to your theory prior to even conducting a test.
Alternative hypothesis. The alternative hypothesis is the exact opposite of the null hypothesis. It reflects that there will be an observed significance in the test – typically identified by an inequality symbol.
Hypotheses are generally testable statements of the relationships among the variables that an individual intends to study in order to either confirm or reject a theory. Poor quality analysis can lead to drawing incorrect and inappropriate conclusions; therefore it is crucial to select the appropriate test for your hypotheses.
Selection of Statistical Test and Evaluating Results
One-sample t-test. The one-sample t-test is used when we want to know whether our sample comes from a particular population, but we do not have all the population information available to us. For instance, we may want to know if a particular sample of college students is similar to or different from college students in general....