 Let's say you open a shop you open a food outlet and you're selling sodas burgers fries and juices and Then you want to know how much each of the item is sold so that you can make further business decisions Which item has the largest demand? That's what you need to know and in such cases you already have a data for example Let's say if eight sodas were sold in a day five burgers were sold three fries and ten juices were sold Clearly the demand for juices were the most and below that the soda had the highest demand Now you want to make business decisions Of course you will have to Prepare your material so that you can sell more and more juices and you won't spend a lot of raw Material or money on preparing fries or burgers for that matter And this is a very simplistic version of why mode is important and I'll quickly tell you what mode is but before that what if you just Calculated the mean of the data. What was the average number of items sold? So if I calculated mean It would be 10 plus 3 plus 5 plus 8 divided by 4 Since there were four total number of items and this comes out to be 13 plus 5 Which is 18 plus 8 26 divided by 4 and this is around 6.5 So would it be fair if you bought or you prepared your raw material in a way that you could sell 6.5 sodas or 6.5 burgers or 6.5 fries or 6.5 juices Clearly this is a wrong decision So using mean in such scenarios where you want to know which item was sold the most mean doesn't work And that's where we think about Mode if I define mode mode is the observation in the data set That appears most of the time. So in this case the observations were soda juice a burger and fries and Clearly you knew how many times each item was sold soda was sold eight times Juice was sold ten times Burgers five times and fries three times and after that you knew that The mode of this data is juice since it was sold the most and that is the utility of Calculating a mode of the data set since this is very useful in instances where you have to look at the data set or the Observation which is appearing most of the time in the raw data. Let's look at a quick example So, let us say we wanted to find the mode of the event data set and the data is going to be the birthday month of the students in a classroom and Some student went on asking birthdays to everybody and he just noted the birthdays birthday months down and now The student has this raw data and you need to find out the mode of the data set What would the mode really mean in this case? This would mean a month which appears most of the time in the data set which is basically the birthday month of Maximum students in the classroom, right? So I'll just write that down. So the mode in this case would be birthday month with maximum birthdays of students in the classroom Now, how do we really find the mode? We will have to count how many times each month appears and there is a very interesting method when there is a huge Data set like this and that is called tally marks. Let's prepare the tally marks. So first of all what we do is We have to know what different kinds of observations appear in the data set. So let's prepare the table We know that these are birthday months. So every month from January to December is going to be appearing in the data set So let's prepare the table. So we are going to use tally marks method to obtain the mode here This is a raw data set and we will look at each observation and once it is tallied Under the table for that particular observation We will draw a vertical line like this and once every group of five has obtained the fifth line will be slanted So for November, we have tallied so we'll just cut off November and we have a vertical line then for September and Then for January will each have the vertical line again January two lines Then October and so on. So we do this for everything Once we implement the tally marks method We know the number of birthdays for each month and we clearly see from the tally marks table January has five birthdays February has five birthdays March only one April 4 May has seven birthdays June and July 2 and 3 respectively August have none surprising September one birthday October has Five birthdays November 4 and December 3 and now clearly we see that may has the most number of birthdays And that's why more of this data set is the month of May and This is how we really find out the mode It's just the observation which appears most of the time in any raw given data set I will encourage you to find out different Instances in real life where you will be able to find out mode and which is really useful in any kind of application