Even though the data can be applied to several areas of the human aspiration to implement the theory and methods of modern statistics to various different fields. Many useful elements were included in this course like descriptive statistics, inferential statistics, hypothesis development and testing, selecting appropriate statistical tests and evaluating the statistical results; which aides me to make better decisions in my personal and professional life. The intention of this paper is to be able to review each of these individual elements that we studied throughout this course.
Descriptive statistics are typically utilized for describing the general features of the information received from a study. The results provide a brief summary of sample and measures. This type of statistics along with a simple graphic aid, creates the basis for nearly all quantitative data analysis. It is also used for presenting quantitative descriptions of data in a comprehensive and manageable form (Schlaifer, 1982). In a research study, there is a possibility of several different measures or it can be a scenario where we are able to measure a lot of people on any form of measure. Descriptive statistics helps us to present a large quantity of data in a much more manageable and realistic form. Each statistic in the descriptive form lowers the quantity of data into a much simpler summary.
Inferential statistics helps us to analyze predictions, inferences, or samples about a specific population from the observations that they make. With inferential statistics, you are trying to reach conclusions that extend beyond the immediate data alone (Trochim, 2006). The goal for this type of data is to review the sample data to be able to infer what the test group may think. It does this by making judgment of the chance that a difference that is observed between the groups is indeed one that can be counted on that could have otherwise happened by coincidence. In order to help solve the issue of generalization, tests of significance are used.
For example, a chi-square test or T-test provides a person with the probability that the analysis sample results may or may not represent the respective population. In other words, the tests of significance provides us the likelihood of how the analysis results might have happened by chance in a scenario that a relationship may not exist between the variables in regards to the population that is being studied.
Hypothesis Development and Testing:
Hypothesis testing and development provides a baseline for taking ideas or theories that were initially created by another person in regards to the markets, economy, or investing and then determining if the ideas are true or false. Specifically the hypothesis testing and development to help decide whether the ideas that were tested are probably true or probably false as the conclusions are made on the hypothesis testing basis, are not necessarily made with a confidence level of 100%. In the process of hypothesis testing, we use different degrees of confidence, such as 99% or 95 %, but we do not made conclusions with absolute certainty (Fraser, 1956).
Hypothesis testing is typically associated with the process for developing and acquiring knowledge that refers to the scientific method. In similar fashion, as it pertains to the fields of economic investment and research. For example, how business topics pertain to other more traditional science fields like mathematics, physics, medicine, and so on.
Selection of Appropriate Statistical Tests:
There is great significant importance for data analysis when selecting appropriate statistical tests. Choosing the wrong or inappropriate statistical test(s) may lead to receiving an incorrect conclusion that have may have results that are misleading. Tests that are inappropriate have the ability to be observed in various situations such as an analyzation of the data that is unpaired with the utilization of paired tests or by using the parametric statistical tests for any data that does not follow inaptness of the statistical tools or normal distribution with the type of data provided.
It has been made easier to apply appropriate statistical tests based upon the type of data that is being studied with the wide variety of statistical software on the market. The only real requirement is to carefully choose the most appropriate statistical test for the scenario at hand. The following three things must be considered before the final selection of the correct statistical test is made:
1. What type of data is under review for analysis?
2. Is the data distributed normally?
3. What is the basic objective of the study?
Evaluating Statistical Results:
The process of transforming data into information that is meaningful and have the potential to be utilized for drawing conclusions in regards to the data is known as data analysis. Even though there are not any rules set in stone on how we are to perform an analyzation of the statistical say, it should be established that a methodical and systemic approach since it will help the final results to be accurate. Performing an analysis with the use of an inappropriate statistical test it leads to drawing incorrect and inappropriate conclusions. Statistics provides us with a number of methods and tools that makes data analyzation easier. The various statistical tests that are available can be used to analyze the different data types and provide information that is useful from data that is in raw form.
Statistics as a discipline is the application and development of various processes to gather, interpret and perform an analyzation of the data. The quantification of biological, social, and scientific phenomenons, design and analysis of experiments and surveys, and application of the statistical principles are all statistical procedures that are more advanced in nature. I have been able to learn several useful concepts by studying statistics during this course that can aide me in making rational and informed decisions that are supported by the analysis results.
Fraser, D. A. S. (1956). Nonparametric methods in statistics. Leach, C. (1979). Introduction to statistics: A nonparametric approach for the social sciences. New York: Wiley. Schlaifer, R. (1982). Introduction to statistics for business decisions. RE Krieger Publishing Company. Trochim. (2006). Inferential Statistics. Retrieved September 28, 2014, from http://www.socialresearchmethods.net/kb/statinf.php Walpole, R. E. (1974). Introduction to statistics (p. 340). New York: Macmillan.