Question-16: Suppose in HadoopExam training classroom, we have data as below with the working experience as below.

                2  3  4  2  2  10  12  10  10  14

What is the mean, mode and median and what do you interpret?

Answer:

                Mode = 2 & 10  

                Median = 2 2 2 3 4 10 10 10 12 14 = 14/2 =7

                Mean = 69/10 = 6.9

Hence, it is wrong to say that average working experience of the student in training classroom is 7 years.

Because there are two sets of data with varied experience, hence to represent this data we cannot use single value but rather two values 2 & 10 years.

Question-17: What are two basic types of data?

Answer:  There are two types of data

• Numerical
• Categorical

You can use mean, mode and median with the numerical data. But mean and median can not be used with the categorical data. Mode can be used with the categorical data.

Question-18: What do you mean by modal class?

Answer:  When you find the highest frequency category or class as in previous example, we have seen Banana was highest occurring fruit that is known as modal class.

Question-19: Can you please tell me something more about the mode?

Answer: We should avoid using the mode when there are many mode values, because this is not going to help.

However, in case of categorical data you have “mode” is the only option to find the average value.

Question-20: When do you prefer the mean?

Answer: When our data has least outlier or less skewed, then we should use or prefer mean or we can say that data should be symmetric. So that mean represent one trend in the data.