<link href="//maxcdn.bootstrapcdn.com/bootstrap/4.1.1/css/bootstrap.min.css" rel="stylesheet" id="bootstrap-css"> <script src="//maxcdn.bootstrapcdn.com/bootstrap/4.1.1/js/bootstrap.min.js"></script> <script src="//cdnjs.cloudflare.com/ajax/libs/jquery/3.2.1/jquery.min.js"></script> <!------ Include the above in your HEAD tag ----------> how to start learning data analytics How to Start Learning Data Analytics especially if you are from a non-technical background? If you have an analytical bend of mind, are interested in learning new technology, and mathematics and statistics are subjects that interest you, then it is easy for you to start learning Data Analytics on your own. The only prerequisite is that you are ready to learn new things and upgrade your knowledge constantly and are ready to evolve. To start your journey on “How to Start Learning Data Analytics”, first let’s focus on what are the fundamental topics falling under the purview of Data Analytics. Data Collection: The methods for Data Collection can be classified under two categories, Primary and Secondary. Primary Data Collection is when the data is collected directly from the respondent which is known as primary data collection. The researcher has the advantage of altering the collection method that suits their purpose. The methods involved in this type of collection are surveys and questionnaires, interviews, study groups, and focus groups. Secondary Data Collection is when the information is collected from pre-existing data, then it is known as Secondary Data Collection Method. The sources to apply this method are published sources like newspapers, medical journals, surveys, statistic reports, government records, and data published for the public by individuals like expert opinions, and social organizations, this is a secondary method of data collection and past research studies. Data Preprocessing and Cleaning: The data when collected is in raw form. It is then cleaned, modified, and consolidated before it is subjected to analysis. This process is known as Preprocessing. The methods for processing are Data Cleaning in which errors like outliers, duplicate data, and missing values are identified, and removed with the help of methods like Binning method, regression, and clustering. Data Transformation is the second step and it is the process of categorizing the cleaned data into set formats for ease in Analyzing. The methods employed for this are Normalization, Standardization, Dicreditization, Concept Hierarchy generation, and Attribute Selection. Data Exploration: This includes identifying patterns and trends which are relevant to the goals fixed by the company, before the final analysis is known as Data Exploration. The data which distorts the analysis is removed and the data which aids the final analysis is separated to be focused on only. Data Analysis: It encompasses discovering trends and patterns in the data and arriving to figure out the relationship between them, so as to understand the negative or positive impact that events have had on the targeted activities of the company. There are mainly four types and Data Analytics methods. And they are Descriptive Analysis, Diagnostic Analysis, Predictive Analysis, and Prescriptive Analysis. Data Visualization: The graphical representation of the analytics report with visual aids like graphs, pies, charts, Geospatial maps, infographics, and Dashboards is known as Data Visualization. The mainobjective of this method is to make the Data Analytics reports and findings comprehensible to non-technical people. Data Modeling: This involves creating a blueprint for the software for data analysis based on the objective of the company is known as Data Modeling. The diagram identifies the specific data as the base, the text and symbols to identify that data, the data flow source, and the relationship between the variables. There are different types of data modeling applications, a few being generally used often are Star Schema, Hierarchial Database Model, Relational Model, Object-Oriented Model, Network Model, Entity Relationship Model, and Document Model. Interpretation and Inferences: This involves interpreting the reasons of the relationship between the variables which either have created a bottleneck or been an aggregator of growth is known as Interpretation. The end goal of this process is to assist the company to make informed business decisions. https://iimskills.com/how-to-start-learning-data-analytics/