Descriptive Statistical Analysis of Data in Data Science



The science that handles with the gathering, grouping, investigating, and explanation of numerical actualities or information, and that, by utilization of scientific hypotheses of probability, urges request and normality on totals of pretty much dissimilar components. So from the above definition, we can understand statistics in two parts (descriptive statistics or summary statistics) and inferential statistics.

Descriptive Statistics
Descriptive statistics or summary statistics is outlining information about data in a significant and applicable way. Let us understand in a simple way, suppose we have population data of India and we want to know which city has the maximum population, the sexual orientation proportion of every city, death rate and proficiency status …
So from the data chart, it’s really complicated to get all information in a reliable way but if we represent them in graphs with all the labeling, then it will be easier to get information about data. Let me show you an example for clear visualization.

Descriptive Statistics Fig-1

Mean, Median, Mode
Gives now a chance to examine a portion of the scientific term which we had extremely recognizable in our schools days i.e Mean, Median, Mode, Min, Max. Mean in a simple way, the addition of all data and divide the sum by total number e.g 17, 4,2,33, 2, 51 –> 18.16. Median is mid estimation of the data series when orchestrated in rising or slipping order. If information arrangement is odd than mid esteem can be taken and when even at that point mid esteem is the normal of real two center focuses e.g 2,2,4,17,33,51 – > (17+4) /2. Mode most as often as possible happened number and for this situation, it’s 2. Min and Max are the most reduced and most astounding an incentive in data series i.e 2 and 51. You should surmise that all of a sudden why I am talking about all these and what is the criticalness ? When I say, I have a data series of 6 points and summarize it in the following way, min value 2 max value 51 and average of 18.16 I need you to make some psychological picture of that data.
A psychological picture implies imagining of information and simplest approach to envision information is utilizing Distribution. Distribution is occurring of data point in data series. Figure explain more about it.

Descriptive Statistics Fig-2

From this data, we can understand that mean or average value 18.16 which signify that more data points are nearer to Min value side rather max value. Up to this point I think so I make you understand what is the use of descriptive statistics, how about we go more profound with the goal that we get a reasonable view. Let us now talk about range. Before starting range let us discuss quartile. Quartile which divides data into four equal parts. Difference between the third quartile and the first quartile is called Interquartile. What’s more, the contrast between highest observation and lowest observation is called Range.

Descriptive Statistics Fig-3


Leave a Reply