Thoughts about media in Canada

Baby Stepping into Digital Number Crunching


I’m Marc, french speaking guy from Montreal. Sorry in advance for not being able to understand the difference between those & these and how to properly use verb tenses.

In the next weeks, months, years, I’ll try to post a few times a month. Most of the posts will have to do with Data, Reporting, Optimization, Analytic, Targeting. To me, everything is logical, rational, quantifiable. Everything can be number crunched. Problem is: Numbers can be your worst enemies because they are so very (too) often misleading. Here are a few examples:

For the life of me, I cannot find the original one. It was published in a Montreal newspaper a few years back. A survey to ask people if they lie during surveys… Bravo!

Another one I cannot find: A web-only panel asking people what media they first use to consume fresh news. The result was about 94% web. Now, I work in the digital sphere. I should be thrilled. Good words for my industry. Woo!

Seriously, I can show real numbers to prove the medium is efficient, I don’t need something so obviously flawed (which was tweeted, retweeted, Facebooked, reblogged by dozens of people) to make it look good

So how about this? I’ll do a Phone survey, landlines only and I’ll ask people if they are homeless.

This just in: A survey reveals that there is no more Homelessness in Canada! Isn’t that great news? Sample base 3001 respondents, 99.4% confidence, 19/20 times.

It sounds like I’m kidding, right? Well… yeah… but not that much. Every day, I see on Facebook someone posting a completely false stat. Every week, I see a study result with a flawed methodology. Every month, someone tries to convince me that this very specific property over indexes at 165 against my target, I need to buy it! I. Just. Need. To!

At first, you’d think the person’s right. But then, you take the time to think and figure that since your target, which is very niche, represents 1% of the population, the person in front of you is trying to sell you a property with a 1.65% audience composition! Only a 98.35% spill!

Where do I sign? Can I pay up front?

OK, you probably get the picture, I’ll stop with the examples, for now.

Stay tuned logged as, in the following weeks, we’ll go through some basics of Digital Media Measurement. We’ll see why a CTR is one of the worst measure of success for Display/Video, we’ll see how not all GRPs are born equal, how Time on Site doesn’t necessarily means engagement, how Reach/Frequency is oh so easily distorted in order for you to like the numbers you see.

We’ll also (mostly) see positive stuff: How to measure Media Synergies, tips to optimize your campaign, how your site can be your best salesman, not just a necessary evil, etc.

Please feel free to comment and let me know of topics you’d like me to cover. I write for you guys.

See you soon.


  1. Pingback: How to look good, data wise | Thoughts about media in Canada

  2. Pingback: Why I don’t trust (most) case studies | Thoughts about media in Canada

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: