Question-6: What do you mean by skewed data?

Answer: When outlies in the data pull the data either too much upside or too much downside then data become skewed.

As in previous example we have see higher salary $15,000 pull the mean salary upward and this is because of outlier. And this dataset is known as Skewed data.

Question-7: What do you mean by skewed to the right or left?

Answer:

                Image-1

When higher value is less, but have tail on the right side, then this is right skewed data & pulls the mean towards right.

                Image-2

In case of left skewed data, lower age is outlier and causing skewed data, and pull the mean towards left.

Question-8: What do you mean by symmetric data?

Answer: If data does not have outlier then the data would be called symmetric. And mean always remains in the middle and data would not be pulled either direction.

Question-9: If your data is skewed or has outlier then what other method you can use to find average?

Answer: We can use median as well, the get the median value, we need to order the data in ascending order and find the middle value.

e.g. Age of learners on HadoopExam.com SAS trainings are

29 29 30 30 30 31 31 51 55

Middle value is the median, if there are total number are even then the average value of the middle values can be a median. Hence, median is a position based.

Question-10: Can you use mean and median with the categorical data?

Answer: No, mean and median can only be calculated for the numerical data.