WHAT IS DESCRIPTIVE ANALYSIS?

In order to provide insightful information about the provided data, raw data is converted into such a form that will make it easier to understand & interpret, rearranging, ordering, and manipulating data. This is called descriptive analysis. It is the type of analysis of data which helps to describe, show or summarize data points in a constructive way such that some patterns might emerge which fulfill every condition of the data.




One of the most important steps for conducting statistical data analysis  is descriptive analysis. It  helps you detect typos and outliers, and permits you to identify similarities among variables and provides you a conclusion of the distribution of your data, thus it makes you ready for conducting further statistical analyses.   

 

Techniques for Descriptive Analysis

 

Two techniques used in descriptive analysis are data aggregation and data mining to churn out historical data. In Data aggregation, in order to make the datasets more manageable, data is first collected and then sorted. 


  1. Constructing tables of means and quantiles, methods of dispersion such as standard deviation or variance, and cross-tabulations or "crosstabs" are included in the methods of descriptive techniques that can be used to carry out many disparate hypotheses.

 

  1. Using specialized descriptive techniques, measures like segregation, discrimination, and inequality are studied. 


  1. In order to show important differences across subgroups,  a table of means by subgroup is used, which mostly results in inference and conclusions being made. 


Types of descriptive analysis


  1. Measures of Frequency

 

It’s essential to know, in descriptive analysis, how frequently a certain event or response is likely to occur. To make a count or percent, this is the prime purpose of measures of frequency.

 

  1. Measures of Central Tendency

 

Finding out the Central (or average) Tendency or response is very important in descriptive analysis. With the use of three averages, central tendency is measured— mean, median, and mode. 


  1. Measures of Dispersion

 

It is quite essential to know how data is divided across a range, sometimes. Let's take a hypothetical situation and consider the average weight in a sample of two people. The average weight will be 60 kg, if both individuals are 60 kilos. However, the average weight is still 60 kg if one individual is 50 kg and the other is 70 kg. 

 

  1. Measures of Position


In relation to others, descriptive analysis also includes identification of the position of a single value or its response. Some useful measures in this area of expertise are percentiles and quartiles.

 

Apart from it, you can use the Bivariate or Multivariate descriptive statistics to study whether there are relationships between them, if you’ve collected data on multiple variables. 


In bivariate analysis, the frequency and variability of two different variables are simultaneously studied to see if they seem to have a pattern and vary together. Before carrying out further types of statistical analysis, you can also test and compare the central tendency of the two variables.

 

Multivariate analysis and bivariate analysis are similar in nature but bivariate analysis is carried out for more than two variables. 
Location: Noida, Uttar Pradesh, India

Comments

Post a Comment

Popular posts from this blog

INFORMATION GAIN IN DECISION TREE THROUGH GINI INDEX

Image
Best suited for classification and regression problems, decision trees are supervised machine learning algorithms. These algorithms are constructed by breaking down the training data into subsets of output variables of the same class by implementing the particular splitting conditions at each node. The information gain in decision trees is directly formulated through training  into a hierarchical structure. The knowledge is holed and displayed by this structure  in such a way that it can easily be understood, even by non-experts. While building a decision tree,  each node focuses on identifying the attribute and a split condition on that attribute which minimizes the class labels mixing, because pure homogeneous subsets is not possible to achieve consequently giving relatively pure subsets. In this blog, we will discuss the concept of , information gain, gini index and gini index. With the root node of the decision tree, this process of classification begins and  gets expanded by appl
Read more

Fundamental & Technical Analysis | Analytics Steps

Image
To understand the business from an investment perspective, there are always two schools of thought that come to mind, people who follow fundamental analysis and those who follow technical analysis . However some investors do both analysis to understand the business from every aspect. Let us understand both in detail. Fundamental analysis Fundamental analysis is a method or approach to understand business deeply and separate the daily short term noise in the stock prices to concentrate the underlying business performance. Fundamentally strong companies' stock prices tend to appreciate in the long run and therefore create wealth for the investors. Fundamental analysis is generally done from a macro to micro perspective in order to identify securities which are not correctly priced by the market. An investor can perform fundamental analysis just by looking at the overall state economy, bond value, interest rate etc. A fundamental analyst creates a model to estimate the company’s shar
Read more

TIMELINE OF ARTIFICIAL INTELLIGENCE

Image
In today’s world, having some kind of knowledge about the history of artificial intelligence is crucial as it is prevalent everywhere. But if we consider it as a contemporary tool, then it would be our misconception. Our forerunners had been building the concept of AI  for quite some time with the help of classical philosophers analyzing human thinking to be more of a symbolic system. A popular myth among the ancient Greeks was robots, while automates can be traced back to the ancient Greeks.  Let’s now discuss the timeline of Artificial Intelligence. Maturation of AI (1943-52) Year 1943 : Warren McCulloch and Walter pits initiated the very first work which is currently recognized as AI.  and Walter pits in 1943. Year 1949 :  An updating rule for the modification of the connection strength between neurons was demonstrated by Donald Hebb.  Year 1950 : An English mathematician, Alan Turing pioneered Machine learning in 1950. A test was proposed by Alan Turing under ‘computing machiner
Read more