The Visual Art Behind Data Science
2/12/2013

Return to Article

View Comments: Newest First | Oldest First | Threaded View
Page 1 / 2   >   >>
DavosCollective
User Rank
Prospector
Re: Think Different
DavosCollective   2/17/2013 11:00:27 PM
NO RATINGS
There's nothing intrinsically wrong with any type of chart, you just have to use them correctly. You also need to carefully consider that most people can't easily read charts so you need to remove all ambiguity from them.  Pie charts are good for showing percentages of a whole, where there are not too many categories as to make it illegible. The worst crime of pie chart usage is to use multiple pie charts for time series. e.g. comparing the profit % this year with the profit last year % can be misleading if the total revenue has changed significantly.

Everybody loves to jump on the Tufte piechart bashing bandwagon, I've seen some very apt usage of pie charts, like this example.

Noreen Seebacher
User Rank
Blogger
Re: Think Different
Noreen Seebacher   2/15/2013 7:05:41 AM
NO RATINGS
Pity the much maligned pie chart!

Jeff
User Rank
Data Doctor
Think Different
Jeff   2/13/2013 12:04:13 PM
NO RATINGS
I always take notice when a graph is unique.  When you can tell they went a little further to drive the point home.  I hope this trend continues.  The simple pie chart is not cutting it any more.

BethSchultz
User Rank
Blogger
Re: Share please
BethSchultz   2/13/2013 9:30:51 AM
NO RATINGS
I'll have to do that going forward. Starting in this fall my household will shrink by 3. I bet I'll see a nice dip in my electricity usage.

Noreen Seebacher
User Rank
Blogger
Re: Share please
Noreen Seebacher   2/12/2013 10:08:44 PM
NO RATINGS
I like to compare my own usage year-over-year and my electric bill lets me do that with a simple bar graph

BethSchultz
User Rank
Blogger
Re: Share please
BethSchultz   2/12/2013 5:22:03 PM
NO RATINGS
I'm not sure about that. My household consumption is so out of whack in the energy report comparison my electric utility sends me that I find it really hard to believe its using good comparables. I don't think, for example, that it's enough to show comparisons between houses on the same block. My house is virtually the same as the one two doors down -- except there only two people are in residence and here five (and six when my daughter is home from college). That's generally three times the amount of laundry being done, and dishes, and cooking, etc. Plus there's the fact that I work in a home office, and so on. 

Noreen Seebacher
User Rank
Blogger
Re: Nice is a 4-letter word for "We're screwed."
Noreen Seebacher   2/12/2013 1:34:14 PM
NO RATINGS
LOL callmebob

Callmebob
User Rank
Master Analyst
Nice is a 4-letter word for "We're screwed."
Callmebob   2/12/2013 1:10:15 PM
NO RATINGS
Noreen - Whoa boy. I guess this falls into the "good" data visualization but showing a bad result. About the only improvement that would help the visualization is to put a piece of toast on the Really Scary Things row next to the "Ocean floor methane released causing runaway climate change. Possiblity of mass extinction."

At least it will only take up to 300,000 years to re-absorb the atmosphere's CO2 and we can start over again.

Noreen Seebacher
User Rank
Blogger
SAS blog
Noreen Seebacher   2/12/2013 11:11:34 AM
NO RATINGS
SAS has a nice blog post on Make better business decisions with Visual Analytics

Take a look.

Phoenix
User Rank
Data Doctor
Re: Share please
Phoenix   2/12/2013 10:53:02 AM
NO RATINGS
One of the most helpful data representations I receive comes in the form of our electricity and water bill. At the back of the bill you get two graphs showing the national average for water and electricity consumption for my house type along with my monthly consumption. This generates awareness. Inevitably if I have consumed more than the national average I would become more conscious about that fact. The next month I would most likely try to conserve more.  

Page 1 / 2   >   >>
Information Resources
More Blogs from Noreen Seebacher
Everyone is talking about big-data as an HR solution, so why doesn't it seem like we're any closer to solving the people problem?
Even at a trade fair better known for seminars on information technology, big-data was too significant to ignore.
All Analytics readers have serious issues with the data hidden in digital photos.
The system we use to select American courtroom juries is riddled with delays, frustrations, and inefficiencies.
It was actually a little too easy to slip a cellphone past security at a federal courthouse.
Quick Poll
Quick Poll
Information Resources
Radio Show
A2 Conversations
UPCOMING
James M. Connolly
Visualization: Let Your Data Speak


10/13/2016   REGISTER   0
ARCHIVE
James M. Connolly
How Colleges and Tech Are Grooming Analytics Talent


9/7/2016  LISTEN   56
ARCHIVE
James M. Connolly
How Machine Learning Takes Handwriting Recognition to New Levels


8/25/2016  LISTEN   40
ARCHIVE
AllAnalytics
A Look at Tomorrow's Data Scientist


8/9/2016  LISTEN   83
ARCHIVE
James M. Connolly
Analytics and the Making of a President


7/21/2016  LISTEN   76
ARCHIVE
James M. Connolly
Analytics: Where We've Been, Where We're Going


7/12/2016  LISTEN   48
ARCHIVE
James M. Connolly
How Predictive Analytics Can Take Your Company to the Next Level


6/28/2016  LISTEN   22
ARCHIVE
James M. Connolly
How Analytics Can Transform State Government


5/17/2016  LISTEN   51
ARCHIVE
James M. Connolly
Save Labor Costs With Predictive Analytics


5/10/2016  LISTEN   53
ARCHIVE
James M. Connolly
What the IoT Means to You and Your Insurer


5/6/2016  LISTEN   75
ARCHIVE
James M. Connolly
When It's Time for a Robot's Job Review


4/27/2016  LISTEN   21
Infographic
Infographic
How Far We've Come With Analytics
You might be surprised by the progress that analytics have made in just the five years that All Analytics has been monitoring the field.
Cartoon
CARTERTOONS
About Us  |  Contact Us  |  Help  |  Register  |  Twitter  |  Facebook  |  RSS