Hello. Welcome to Statistics for Data Science-1. I am Usha Mohan, Professor at the Department of Management Studies, IIT Madras.
Over the next 12 weeks, we would travel together to understand the basics of statistics that is needed for your online degree programme. So, we first begin with understanding what is statistics. So, first we look at what is the definition of statistics.
So, one of the most popular definitions of statistics tells us statistics is the art of learning from data which includes collection of data, analysis of data, presentation of data, and then, drawing conclusions from data. So, one of the main things you are going to learn in this course is to first, we are going to look at how you collect data So, that is one of the main things which we will do. So, we start with data collection.
So, we look at how you collect data and then, we go on to see how you actually present this data. During this course, we learn about how you do present data in a tabular form; we introduce a concepts of frequency tables; we introduce a concept of relative frequency and we look at how you tabulate data. We also learn about the different types of data that you encounter.
Then, we look at how you further look at describing data using graphical techniques. Some of the graphical techniques that you would learn are bar charts, pie charts, histograms, stem leaf plots etcetera. We then, also go about learning how you actually come up with numerical measures of data.
What we look here mainly is at the measures of central tendency; namely, mean, median and mode and the measures of variation; namely, range, variance, standard deviation. So, far we have just talked about describing a single variable, we also look at answering questions about association between variables. Towards this, we also introduce the concept of contingency tables, scatter plots and we also introduce what is a correlation matrix.
So, predominantly in the descriptive statistics module, you will be learning about collecting data, organising data and describing data. Describing data both using graphical techniques and numerical techniques. Now, once you are comfortable with just describing data, where the question is you just want to describe whatever data you have.
The next step is to try and see I said that statistics is the art of using data to draw conclusions. So, you want to infer something from data. So, this lays the playground for you to go next level which is inferential statistics.
Inferential statistics will be taught in the next course on statistics. But, however, in this course, we will help you by laying the foundation or the building block to understand inferential statistics. What do I mean by building block to understand inferential statistics?
We motivate this through a small introduction to the probability theory. When we go to probability theory, we start by what we mean by permutation and combinations. This is something which you are going to revisit.
Most of you would have learned this in high school, but you are going to revisit the concept of permutation and combinations. Then, we introduce the notion of probability through random experiments like rolling a die, tossing a coin and then, afterwards we talk about probability of events, the combination of events and why they are necessary. Finally, we end this course by introducing to two main distributions; namely, the binomial distribution and the normal distribution.
Throughout the course, the focus is going to be on teaching at a conceptual level and applying these concepts to real world problems. So, you will have a lot of assignments which will test your knowledge, both at a conceptual level and an application level. There would be at every stage, we will try and motivate the learner to look at understanding the concepts and applying their concepts through a set of case studies specifically designed for this course.
Welcome again to the world of statistics and this course which is Statistics for Data Science-1.