Monday, August 29, 2016

Sunday, Sunday

Along with reading the Sunday newspaper, CBS Sunday Morning is a favorite in our household. Click on the video above for a short report on a streaming pay TV customer satisfaction survey conducted by JD Power. The report mentions four categories: "cord cutters", those who have cancelled TV service, "cord nevers", those who have never subscribed to pay TV and only subscribe to a streaming video service, "cord shavers", those who still subscribe but now to a downgraded TV service, and "cord stackers", those who keep pay TV but also use streaming.  From the report:
The inaugural study measures overall satisfaction among customers who have used a subscription- or transaction-based streaming video service within the past six months. The study measures customer satisfaction by examining six key measures (listed in order of importance): performance and reliability; content; cost of service; ease of use; communication; and customer service. Scores for each measure are reflected in an index based on a 1,000-point scale.
The measures for "cutters", "nevers", "shavers", and "stackers" are 802, 807, 822, and 826. Here is a frame from late in the video that reports on the right most bar "stackers" as it relates to the other categories."

It's clear that that Sunday Morning is in sore need of knowledgeable graphics editors. Perhaps their artists make their charts telegenic by filling them up with what we would call "chart junk", but in ignoring the proper representation of the data, they are presenting false and misleading images. The numbers are said to be represented here, are again, 802, 807, 822, and 826. The second bar from left almost looks twice as tall as the left-most bar and not a bar that should only be about 0.6% taller. The third bar from the left looks about 3 times taller than the left-most bar and it should only be about 2.5% taller. Finally, the right-most "cord stackers" bar should be under 3% taller, not over 4 times taller! Yes, they give a grid background to judge the sizes, but they are misleading sizes to judge. The 'smiley' satisfaction faces are probably the most reliable description of the data: The satisfaction scores are amazingly the same. From smallest to largest they vary by less than 3%.

Here are the data shown on the graph and then a more accurate rendering (without the chart junk).

Not much difference in satisfaction across all type customers.

Monday, August 22, 2016

The Wear of Love

As part of the Virginia Tourism Corporation's promotion campaign, this LOVE artwork has been placed in the Robert Reed waterfront park in Chincoteague, Virginia. It displays four, 10 foot tall Adirondack chairs. The wooden chairs spell out the LOVE with the symbols 
L O  E.
Of course, when posing for pictures, tourists prefer to sit in the      chair over the others as evidenced by the greater frequency of wear on the chairs as people climb up and rub off the paint.

This view looks at the letters in reverse. The nearest chair is E, the next is     with the most wear, then O and L. Note that the pattern of wear is in a bell-shape, with more wear near the middle of the seat and less towards the edges.

Monday, August 15, 2016

Alien Corn

Another Eastern Shore vacation outlier find. This corn stalk, amid the soybeans, is a triple threat outlier: by type, by height, and by location. Enjoy the rest of your summer.

Monday, August 8, 2016

Skewed Fast Food

This is a view of the side of a small counter at a fast food restaurant in Snow Hill, Maryland. Patrons have slid this chair back and forth to sit at or leave the adjacent table. This chair movement has marred the paneling of the counter into a pattern that is skewed to the right: much more wear on the left with decreasing use and wear as the chair is set closer to the table. Of course, on the right, the chair's wear pattern is truncated since it must stop short of the table. On the left, we've got no wall to reveal the chair's position. The chair's wear is censored. What remains is a right skewed pattern of the frequency of use and wear. The pattern somewhat resembles the pattern of a sample from a right skewed exponential distribution.

Monday, August 1, 2016

A Distribution on a Cylinder

Here's a utility pole at a traffic intersection in Aspen Hill, Maryland. The pole has served as display for the many yard sales, community meetings, and businesses that have had their advertising flyers posted on the pole. The flyers have long since been removed. Only their staples and nails remain. These accumulated staples show a distribution of the heights of flyer postings. 

The close-up view below shows the distribution of individual staples and nails on the cylinder of the pole. The staples are distributed both around the pole and vertically up and down the pole. Vertically, it's too difficult to put flyers high on the pole and few staples can be found there. Flyers very low on the pole wouldn't be easily seen by those passing by, so few staples are also found there. Most staples and nails are at a comfortable shoulder and viewing height. If we imagine the height of a staple above the ground is our random variable, we find few staples with small height, few with large height, and many more with a medium height. This is a bell-shaped pattern up and down the pole that we have seen often.

Horizontally, the staples are distributed circularly around the pole. They would also have greatest frequency towards the traffic and lesser frequency on the backside of the pole. This is likely also a bell-shaped distribution, wrapped around a circle. We have seen such a distribution before connected with the characteristic function of a random variable. We've also seen a distribution on a pole at the Rodin museum in Paris.