Descriptive statistics in statistics
Descriptive statistics in statistics

 This article "What is descriptive statistics in statistics" will lead us towards how to explain descriptive statistics and types of descriptive statistics.

What Is Descriptive Statistics In Statistics?

Descriptive Statistics

Descriptive statistics, also called “descriptive’ or ‘descriptive statistic’ is when we describe what data we have collected. The data that we’re describing could be numerical numbers like average income, percentage number of children and their ages, etc.,

Types of Descriptive Statistics

Mean is one of the most basic concepts in any statistical package. It describes average of all the values in a dataset. It doesn't measure the characteristics of different groups or subjects. If you want to know how many people died from being drunk on your street, it won't tell you the exact number of dead bodies, and it wouldn't tell the age of any person who died..

Standard deviation is calculated between two numbers and indicates the spread from mean. For example, if mean = 80 dollars, and standard deviation = 1, then standard deviation = 1/1,000 = 0.25. This number measures how far the data is away from the mean. If the standard deviation is more than one, it means the value is not likely to occur by chance. Standard deviations can give us an idea of how outliers are.

Mode is the value that occurs in every instance. If we have a dataset that has only 20 times that of all the people, and the frequency of this occurrence in people is one time out of 10, then mode = 20 times of 1000. But if the frequency of its occurrence is 1.5 times out of 100 people, then mode = 60 or 100 times out of 1000 people. So if we had 10 times that of 100 people and a frequency of 1.5, then mode = 60.

Precision is percentage of occurrences that can be identified as a particular factor in our study. This helps when the variable under consideration is important or has a lot of effect on something else. However, it may not indicate causation because of multiple reasons. A low precision means that many incidences were missed. On the other hand, high precision means that the same item was given many times but few incidences were identified. Precision is useful in cases where values are unknown but the values are there.

Recall is the number of incidences that were identified as a result of doing the survey. This could make the difference in what we do if a big population was involved in some other research. Remembering what the questionnaire showed us and the answer provided will help identify whether or not anything was wrong. Recalling can tell us which values or factors are missing. However, recall cannot tell us whether our results were accurate.