Some of these functions include the standard deviation, median, means, kurtosis, and skew among others. This follows that for the cases of descriptive statistics the population parameters of intrinsic interest are estimated. For instance, calculation of the sample mean and standard deviation act as fundamental instruments or indicators, which are used in estimating the population mean and standard deviation respectively (SELKIRK, 2008). In most cases, these parameters have been cited to be biased in comparison with the ideal estimators; however, an element of utility in estimating the population parameters is attributed to them.
Similarly, the descriptive statistics in most cases intends to describe a big chunk of data by providing a summary charts and tables; however, it does not attempt to make any relevant conclusion about the population attributed to the samples. This forms the distinctive feature of descriptive statistics (BLANK, 2008). For instance, a sample of 30 is selected randomly from a population of 300 and the parameters such as means and standard deviation calculated (CONWAY, 2003). These parameters will be used in approximating the population estimators and consequently used in graphs and charts to provide a summary of the data. This is uninformative.
On the other hand, from the meaning of the word inference, inferential statistics is the process of reaching a conclusion regarding a parameter. In essence, inferential statistics is characterized by use of functions of the sample data, which help in drawing an inference that concerns a hypothesis regarding a certain population parameter. Some of the classic inferential statistics include z, t, and F-ratio among others. For the case of the hypothesis, we have both the null and alternative hypothesis. In this case, the expected value is immensely influenced by the sample size