Descriptive vs. Inferential Statistics

Both descriptive and inferential statistics are measures used to analyze different theories.

Descriptive statistics are set of statistics which measure frequency, central tendency, and variability. All of them are used to test descriptive theories, identify and analyze the characteristics of research participants, as well as to describe the amount or extent of each theory concept. These statistics simply describe the data, thus they do not allow us to make conclusions beyond the data we have analysed.

Among descriptive statistics, measures of frequency use numbers and percentages, measures of tendency use the mean, the median, and the mode while measures of variability use the standard deviation, the range, and the standard error.

Descriptive statistics are used when the research participants are the entire population or a sample is drawn from the population.

Inferential statistics measure relations and effect. It is appropriately used only for samples drawn from populations. Inferential statistics are used to test explanatory theories (in case of relations) and predictive theories (in case of effect). Inferential statistics are techniques that allow us to use these samples to make generalizations about the populations from which the samples were drawn. What is important, and different from the descriptive statistic, is that this information about a population is not stated as a number.

In order to measure relations, inferential statistics use all correlational statistics, such as bivariate coefficients of correlations, multiple regression, logistic regression, and structural equation modeling.

In order to measure effect, the tools of inferential statistics include various analyses of variance and analysis of co-variance statistics.

So, in summary:

Both descriptive and inferential statistics are used to analyze number data. They differ in terms of employed statistical measures, sample origin and tested theory.