Analytics Roundup
By Ken Hilburn
September 14, 2007
Find more about:
analytics
email
graphics
nytimes
productivity
social_network
statistics
trends
video
visualization
- Nielsen/NetRatings' August social media numbers: Not much change
- Interesting post I stumbled on related to Nielsen's web analytics service. Several references to "juicy" or "juiciness".
- Inbox Zero
- Merlin Mann on cleaning your e-mail inbox.
- The New York Times > Home Prices Across the Nation
- The most interesting / important part may be the talking head in the lower left, should you be annotating your reports with video?
- Introduction to Statistical Thought—free ebook
- 1) explains how statisticians think about data
2) introduces modern statistical computing
3) as lots of real examples
Analytics Roundup: Chicken presentation and so much more
By Ken Hilburn
August 18, 2007
Find more about:
ai
algorithms
blog
business
collaborative-filtering
datamining
excel
graphics
graphs
humor
intelligence
machinelearning
netflix
powerpoint
presentations
squarepie
statistics
trends
typography
usability
userexperience
video
visualization
- Programming Collective Intelligence
- Pulling information from community contributed data.
- Videos that can change your organization
- Top ten business videos on YouTube.
- The Encyclopedia of Business Cliches
- UC Berkeley CS160 User Interfaces Fall 06
- Course readings and student notes.
- Language Log: Chicken: the PowerPoint Presentation
- The presentation you dare not give.
- Prometheus Meets the Enterprise Management System
- I laughed, I cried, I laughed again.
- Diagrams: Tools and Tutorials
- Data Visualization: Modern Approaches
- A grab bag of ideas.
- fontblog : Introducing Ambiguity
- A typographic symbol to indicate ambiguity, compare to the typographic mark lol which indicates stupidity.
- Whimsley: The Netflix Prize: 300 Days Later
- Process Trends Website
- Good excel charting and visualization tips.
- BusinessWeek: Who Participates And What People Are Doing Online
- A simple and fairly effective use of square pies.
TV Ratings and Online Audiences... Or, Where to Find Skeet Ulrich's Bio
By Zach Gemignani
July 23, 2007
Find more about:
metrics
statistics
The TV ratings system is broken. Everyone knows it, but nobody wants to admit it. Nielsen ratings struggle to accurately measure audience quantity (limited tracking of DVR usage and online viewers) and quality (are viewers engaged? are they skipping the ads?). However, admitting so would undermine the delicate balance TV networks share with their advertisers.
I caught an interesting segment on KCRW's "The Business" podcast about TV series that find themselves on the "bubble," i.e. at risk of getting canceled. The producer of CBS's Jericho, "a post-apocalyptic drama starring Skeet Ulrich" (shouldn't that description alone put it on the chopping block?), explained how they received a temporary stay of execution when their small but loyal audience protested network plans to cancel show. The interview raised questions about the validity of Nielsen ratings and how an fervent online audience can bring additional perspective to the performance of a show.
All this talk of measurement gave me an itch to look at some real data. I tracked down the Nielsen audience size (Subscription required) for TV series over the 2006-2007 TV season. Then I pulled from comScore (a Juice client and leading source for data about Internet traffic and usage behaviors) the unique visitors and time spent on websites of TV shows over the same September to May time period.
I had a few questions I was curious about:
- Which shows have dispropotionately larger internet audiences—an indicator of a loyal and rabid fan base? Are there other shows like Jericho that struggle to build a large TV audience, but have a strong online following?
- Which TV show sites have the most engaged audiences?
- What TV networks have been most successful at building online traffic to their sites? Which types of shows spawn online audiences?
The table below shows the top 20 TV series by ratio of monthly unique website visitors to average TV viewership. This metric suggests an ability to get viewers to look for more content, whether it is additional video, information about the actors, or discussion boards. If Jericho's 9.5 million TV viewers (tied for 48th overall) represents the proverbial bubble, there are eight other shows with bubble-level ratings that can also claim strong online support (highlighted in this list).

I also wanted to get a sense as to the engagement of the online audience. Were people simply stopping by the website to check the TV schedule, or were they digging deep for more content? One measure that gets at this question is minutes per unique visitor. The top 20 websites are listed below. Interestingly, 12 of these sites are also found in the previous table. Jericho is one of four of the bad-Nielsen-ratings/strong-online-audience group that overlap with the table above. (NBC, if you are grousing about ratings for The Office, hopefully these numbers will make you feel a little better.)

The final table addresses my third question about the TV networks and types of shows that are best at building an online audience. ABC has done more than twice as well as CBS in getting viewers online, which may be a reflection of the traditionally older CBS audience. Note: I pulled the top-end outliers (American Idol, You Think You Can Dance?, and Deal or No Deal) from the Network comparison.
The second half of the table brings those TV series back into the mix in the reality/contest category, and you can see the impact. I was surprised at the dearth of sitcoms on this list. It may be that a website for a sitcom doesn't typically make sense.

With all the money spent on TV advertising, I can only hope the networks go beyond the top-line Nielsen ratings to try to get a complete picture of their audiences.
16 comments | Show all comments only the last 5 are shown
Jane said:
Excellent article. It seems that CBS is well aware of the online fans yet they continue to depend on Nielsen's. In an article yesterday Leslie Moonves is quoted as saying he wants Jericho viewers in front of the TV because that's how CBS gets paid. This man needs to get a clue. We are in front of the TV and we've gathered many new viewers so CBS needs to make sure they're counted. They won't be as long as this reliance upon Nielsen continues.
Our Jericho board even got nominated for an Emmy. We're the best free advertising CBS could get.
gt said:
Very interesting article and the extra lenghts you went to in order to get the WHOLE picture is greatly appreciated. I totally agree that all viewers need to be counted.
jkegrngrl said:
Skeet Ulrich was the reason I tuned in to the show. He is a phenomenal actor, and when he first came on the scene 12 years ago, he was touted as a virtuoso. He has matured and grown as an actor even more so than his contemporaries and deserves a freaking emmy, especially for the dramatic season finale. Old stereotypes are the refuge for the ill-informed.
ahma said:
Thank you so much, your article gives me hope that the networks might eventually realize having viewers sitting in front of a tv viewing there show live is not the be all end all it once was. This is not the 1950's or 1960's we have all this new technology that allows us to view shows at times that are more convenient for us. I would certainly think that someone at some network will finally come up with a way to count all their viewers. I would love to know what the criteria are for being a neilson family. Father works 9 to 5 Mom stays home and fixes dinner to be served by 5:30 so we can all sit down in front of our tv's in time for prime time television. No taping, no dvr, no Tivo, no ON Demand, just you in your chair in front of the tv. Thankfully, Nina Tassler seems to realize there is a bigger picture. Unfortunatly, Mr. Moonves, is her boss. That would be "CLUE"LES Moonves.
Grace said:
I sure hope Les Moonves and Nina Tassler read this because I LOVE JERICHO!!!
I don't watch online and I am not a Nielsen family, so I never get counted. NOT FAIR!!
I never missed an episode of JERICHO yet!
JERICHO ROCKS!! WATCH IT! You'll LOVE it!!
I PROMISE!!
Jess said:
Thanks for the article - I have been fascinated by this story (although I should admit, I've also been a participant). One thing to also take into consideration is that your numbers take into account those internet views that can be monetized by CBS - but because you are only looking at the 'official' cbs.com site, you aren't really seeing the full impact of the online audience. For example, over 100,000 fans signed a petition, and the self-proclaimed 'Jericho Rangers' have created countless sites to fuel the fan movement. Some of the most popular (no, I don't run any of these) are jericholives.com and jerichorallypoint.com.
Paul said:
Nice post Zach. I agree that the Nielsen ratings system is broken, and getting more broken. However, it's not AS broken as most people think. It exists to measure investment in TV advertisements - not the popularity of TV programs. These things used to be one in the same, these days they are diverging - as you point out. My guess is the divergence hasn't yet reached a point whereby the monetization of the non-TV audience comes close to making up for the shortfall in TV audience ratings revenue. Why is that? Interested to hear your thoughts (if you agree).
Zach said:
Paul, I agree. In fact, the larger failure is on the part of the networks, not Nielsen. Networks need to find ways to succeed financial both when they have a large and shallow audience and when they have built a narrow and loyal audience. Why treat every eyeball uniformly? Surely there are ways to generate more dollars per viewer for these fanatical Jericho fans.
Paul said:
Completely agree. But it's a bit of a conundrum for the networks. The real value in a fanatical fan is that they consume (or are prepared to pay to consume) more of the content. But as long as the networks try and monetize shows based on advertised product consumption (ultimately), they never tap into that real value.
Let's see... 100,000 fanatical Jericho fans each paying $1.50 for one of a 10 episode season... $1.5M. Hmmm... if they paid Skeet what he is actually worth - $10/show - they should be able to break even :)
John said:
I believe the issue here is much more fundamental than network programming decisions and Neilsen ratings. The “broadcasting” technology and business model is a mass market medium which places value on aggregating large, demographically identifiable audiences.
The ultimate users of Neilsen data are the media buyers, and by extension the product advertisers. They are usually much more interested in how the ratings break down at the gender/age level. For example, when Chevrolet wants to advertise the Silverado pickup truck, they are probably going to want to target Males aged 18-34. They might concentrate their media buy on “Monday Night Football,” for instance, rather than spreading it out over many fragments of their target audience, even if those fragments are equally loyal and reliable viewers of other respective programs.
Compare this to the Google model, where the smallest advertiser can pinpoint a potential base of customers for their customers in a precise and predictable way by using contextual ad placement.
The other fundamental problem for broadcasters is that loyalty alone is almost impossible to monetize unless it is highly popular and can be franchised (“Law and Order” for example). The ancillary revenue that networks receive from web sites and merchandise are miniscule compared to the dollars that advertisers will pay to reach a large television audience.
Hadley Wickham said:
In the first table, the second column is labelled "Website audience / TV audience", but the values in the columns are percents. This doesn't make sense to me- does 5.5% mean there were 5.5 times as many web viewers as tv viewers, or only 5% of the number of tv viewers used were website viewers? It's a big difference!
A scatterplot of web audience vs tv audience would also be useful, especially if supplemented with some reference lines (eg. 2x 5x 10x)
Paul Robinson said:
Just out of curiosity, why did you ignore Deal or No Deal in your conclusions? It has by *far* the biggest gap between Nielsen and website audience and it has the longest avg visit time online - yet you don't refer to it once.
I also agree with Hadley - you've spent time putting this stuff together, which is great, but you've not explained what the figures actually mean. Tufte would be ashamed of you! :-)
Zach said:
Hadley, You are correct in pointing out that I incorrectly used percentages when it isn't truly a percentage. The metric is intended to show the size of the online audience relative to the TV audience -- but it isn't as if one is truly a percentage of the other. 5.5% represents the ratio of one audience to the other (as shown in the column header). I find it a stretch to interpret 5.5% as 5.5x.
Paul, Good observation. I had suspected that "contest shows" like Deal or No Deal or American Idol drive traffic to their site by getting people to vote online or play an online version of the game (or look at photo galleries of the Deal models in skimpy dresses). In that sense, I was more interested in talking about shows that seemed to be creating loyal audiences through the characters and content of the show.
Jennifer Reed said:
I was a Nielson TV home. The amount of equipment that had to be placed in and on all my tvs, vcrs, video games etc. sucked. But overall it was kind of cool. Shows like House, Dateline NBC, and the entire cartoon network were watched. I have a large family and we made sure we watched television of substance not like the crap with Paris Hilton. It is kind of cool to feel you have a say in whats good tv. I did this for a few years until I moved. There was no money paid to participate except $30.00 every six months to cover the electric all the annoying equipment used. Furthermore, they wanted us to be very secretive and completely accurate in what we watched, advising us not to use the tv for company noise, etc.. Nielson, to me is very competent in how they research who watches what . They once even called me because the tv was on for several hours on the same channel and wanted to know why. It was because the kids were sick and watched cartoon network all that day. Please, I would not doubt Nielson, they are going to be the most accurate you could get unless you monitored every home in the entire world.
Zach said:
Jennifer, Thanks for sharing the details of the Nielsen family experience. I've always wondered what exactly was involved. My concern isn't whether they do what they set out to do well...it is that they don't attempt to capture the full picture. With DVRs/TiVos and online viewing, the outside-the-living-room picture is becoming increasingly relevant.
Tina said:
Hi Zach,
I am a student in economics at Harvard University and am looking for data on online viewer audiences for specific tv shows on a weekly basis. Did comscore have this data? do you have to pay for the data? do you have suggestions of how i could find this data?
Add a comment
Analytics Roundup: Wise guy edition
By Chris Gemignani
June 22, 2007
Find more about:
analytics
humor
management
statistics
- Dunning-Kruger effect - Wikipedia, the free encyclopedia
- Mistakes in Experimental Design and Interpretation
- Taxonomy of ways to fail your experimental design.
Analytics Roundup: Late April edition
By Chris Gemignani
April 27, 2007
Find more about:
census
data
juicesite
population
powerpoint
presentation
presentations
pubapp
statistics
tools
- Population Estimates Data Sets
- US census data
- Are you generic? / Wilson Miner Live
- Wilson Miners post re: Django's generic views





0 comments | Add a comment
said: