The Effects of Parametric, Non-Parametric Tests and Processes in Inferential Statistics for Business Decision Making —A Case of 7 Selected Small Business Enterprises in Uganda

Abstract

The article gives a critique of parametric and nonparametric tests and processes of inferential statistics in forecasting customer flows in 7 selected small business enterprises in Uganda. Forecasting is one of the decision making tools in a business enterprise. This may include forecasting customer flows, volumes of sales and many others. This is a vital component of small businesses success. In the long run, what drives business success is the quality of decisions and their implementation. Decisions based on a foundation of knowledge and sound reasoning can lead the company into long-term prosperity; conversely, decisions made on the basis of flawed logic, emotionalism, or incomplete information can quickly put a business out of commission. In many instances, business decisions have been guided by parametric tests and processes and /or non-parametric tests and processes of inferential statistics, which have subsequently affected the futures of business differently. As we refer to population mean knowledge for hypothesis testing using parametric tests, we only refer to mediums for samples, for nonparametric tests. A parameter is a characteristic that describes a population. These may include μ (the Mean), δ2 (the variance) of a distribution. We commonly refer to the normal distribution, when it is symmetric, with the measures of central tendency (Mean = medium = mode). Usually these parameters are very useful, when testing hypotheses to enable researchers and decision makers infer about the population using samples. It would always be better to have knowledge of or/and about the population parameters, but more often than not, we find ourselves with very minimal, or no knowledge about the population parameters. To make the generalization about the population from the sample, statistical tests are used. In other words, we want to know if we have relationships, associations, or differences within our data and whether statistical significance exists. Inferential statistics help us make these determinations and allow us to generalize the results to a larger population. We employ parametric and nonparametric statistics to show basic inferential statistics by examining the associations among variables and tests of differences between groups. It is recommended by many scholars that business analysis uses parametric and nonparametric inferential statistics in making decisions about effects of independent variables on dependent variables. On the contrary, it is argued that the use of inferential statistics adds nothing to the complex and admittedly subjective, no statistical methods that are often employed in applied business decision making analysis. There are several attacks made on inferential statistics, perhaps with increasing frequency, by those who are not business analysts. These attackers are not in for the use of inferential statistics in research and business decision making, and commonly recommend the use of interval estimation or the method of confidence intervals. However, interval estimation is shown to be contrary to the fundamental assumption of business decision making analysis.