Types of Data

Start-Tech Academy
A free video tutorial from Start-Tech Academy
1,700,000+ Enrollments | 4+ Rated | 160+ Countries
4.3 instructor rating • 38 courses • 791,374 students

Lecture description

In this lecture you will learn about the different types of data.

This course 'Machine Learning Basics: Building Regression Model in R' will help you to solve real life problem with Linear Regression technique of Machine Learning using R. First step in any Machine learning technique is to have a good business knowledge and data understanding. The Second step of Machine Learning is to get a deeper understanding of your data using Preliminary analysis of data using Univariate and Bivariate analysis before running Linear regression. Next step is an iterative process in which you try different variations of linear regression such as Multiple Linear Regression, Ridge Linear Regression, Lasso Linear Regression and Subset selection techniques of Linear Regression in R. Final step is to interpret the result of Linear Regression model and translate them into actionable insight. This course 'Machine Learning Basics: Building Regression Model in R' will walk you through all these steps of Linear Regression technique of Machine Learning with R.

Learn more from the full course

ML for Business Managers: Build Regression model in R Studio

Simple Regression & Multiple Regression| must-know for Machine Learning & Econometrics | Linear Regression in R studio

06:13:53 of on-demand video • Updated November 2020

  • Learn how to solve real life problem using the Linear Regression technique
  • Preliminary analysis of data using Univariate and Bivariate analysis before running Linear regression
  • Predict future outcomes basis past data by implementing Simplest Machine Learning algorithm
  • Understand how to interpret the result of Linear Regression model and translate them into actionable insight
  • Understanding of basics of statistics and concepts of Machine Learning
  • Indepth knowledge of data collection and data preprocessing for Machine Learning Linear Regression problem
  • Learn advanced variations of OLS method of Linear Regression
  • Course contains a end-to-end DIY project to implement your learnings from the lectures
  • How to convert business problem into a Machine learning Linear Regression problem
  • How to do basic statistical operations in R
  • Advanced Linear regression techniques using GLMNET package of R
  • Graphically representing data in R before and after analysis
English [Auto] Hi everyone let us start with the basics of statistics. What are the things we must know when we are planning to do what data analysis. The first thing is the different types of data. We must know this because different types of analysis run on different types of data and when we see these data we should be able to quickly identify its type and then figure out what type of analysis is to be done on it. Basically there are two types of data qualitative and quantitative qualitative is also called categorical data because it has categories within qualitative. We have nominal and ordinal data and within quantitative. We have discrete and continuous data let us look at these types one by one is a definition of qualitative radar data which can be classified into two or more categories is quantitative or categorical data. Such data is further classified into nominal and ordinal. This is the capability of putting these categories into some order nominal is where we cannot assign any order. For example if we collect data of students and one only variable is students gender. This data is categorical as it has categories such as male or female. But we cannot order these we cannot assign rank one or rank to do any particular gender similarly the country to which a person belongs is also nominal. It only has name. It has no other information. It may have meaning for you but the data analysis software will treat all countries equally. On the other hand ordinal data has names and order that is you can drag the categories as higher or lower. For example when reviewing service of a restaurant the options such as not satisfied satisfied and delighted can be ordered by doing analysis. It will be better that you tell the order of preference of these values. Similarly spiciness of food is another ordinal categorical data. It contains value such as less spicy my Lenhart. We know that hot is more spicy than my but we do not know with how much amount. We know that my less more spicy than less spicy. But we cannot quantify the did the amount of spice more spiciness that mine has the less spicy to these three are categorical variables and we can order them in the order of spiciness. But these do not have particular numerical values assigned to it so we cannot quantify it now let us look at quantitative data quantitative data can be measured numerically that that is it has numerical value. It has inherent order based in numerical value. There are two types of quantitative variables one which can take discrete values. These will have only certain values and cannot have intermediate values. For example if you toss a coin 10 times the number of times you will get ahead can be any integer value from zero to 10 but it cannot be one point five or two point one etc.. Second divers continuous variable continuous variables can take any value in between also for example height of student it can take any value like 170 centimetre 170 point five centimetre one twenty point five six in the middle etc. It may have a range between which the values will fall but within that range it can take up any value so these are the different types of data. Remember these keywords which we used in this lecture as these will be used in the lectures to come also.