Question

Q1

We will be examining the variable number of points per player for the 210 top scoring NHL players in 2013-2014. Below are two displays of the distribution of the number of points per player. of Points Per Player Boxplot of PointsAssign 50 50 40 30 Number of Players Points.Assign3 10 40 Points

Q2

Answer 1

of Points Per Player Boxplot of Points Assign3 SO Number of Players PointsAssign3 24 4 Points

NOTE- It's your graph you uploaded in the question on basis of that the answer below is given:

I would suggest you to choose the mean or median to summarize the center of this distribution.

Mean or median will tell us that where the data is highly densed and where the data is low densed.

Like in graph 1: it shows that tail to the right of the curve has covered more area than the left. Here, median will help you out in partioning the data and saying that this value is grater than the median value and this value is less than the median value.

And yes, the above graph is positively skewed.

Now,the graph 2 represents the similar thing because it belongs to the same dataset, this boxplot also shows that data is positively skewed and it shows that it's median lies somewhere between the 20-30.

-> Features of the distribution:

Mode - As you can see in graph 1 the highest peak lies on the number of players at 50 and points corresponding to it is 24, Hence 24 is our mode.

Symmetry- As i have already told you above that tail towards th right has more area in it which represents that this curve is positively skewed.

Outliers- You can clearly see the outliers in both the graphs, in graph 1 blar in between the 64 and 72 represents the outlier and in graph 2 points outside the whiskers of the boxplot i.e., 5 points (above 50 points) are the outliers.

-> Features of display that are visible in graph 1 but not in graph 2.

There are two features that you can find in graph 1 but not in graph 2 i.e., are as followed:

1. Mode- You cannot locate the mode in the boxplot visualization but you can findout by the summary data it given in the result.

2. Mean- It is also not possible to locate mean as well in the boxplot directly. Because boxplot gives description about the partioning of the datatset.

-> Eerything required to create the boxplot would be calculated as followed:

Interquartile range would be as followed: IQR = 23-Q IQR = 49.50 -34 IQR = 15.5 Range would be as followed: Maximum value of the data= 54 Minimum value of the data= 10 Range= maximum - minimum=54-10= 44 Quartile fences would be calculated as followed: L = Q -1.5x IQR L = 34 -1.5x15.5 L=10.75 U = Q3 +1.5x IQR U = 49.5 +1.5x15.5 U = 49.5+23.25 U = 72.75

NOTE- Q3, Q1 was given in the problem that's why i have not shown its calculation above.

This shows that there is one outlier in the dataset, all the values below 10.75 and above 72.75 would be considered as outliers and here 10 is below the fences (i.e., 10.75).

Boxplot would be as followed:

Audit times 60 50 40 Audit times 30 20 10 #