Tricia Aanderud

The Election Aftermath: Is Data Dead?

NO RATINGS
View Comments: Newest First | Oldest First | Threaded View
Page 1 / 10   >   >>
magneticnorth0
User Rank
Data Doctor
Re: Catastrophic failure of polling
magneticnorth0   11/29/2016 1:31:31 AM
NO RATINGS
They pointed to the the 1982(?) California governer election where everyone said they were voting for the then LA mayor. But come election day .... no they voted for the other guy.

When I do market research that involves predicting consumer behavior, especially when it comes to testing new products, I never include the question, "would you buy this?" It almost always yields inaccurate results. Predicting your own behavior well enough requires ample self-knowledge. As a marketer, I've grown to understand that consumers really don't know themselves well. What I do is I test for factors that will help me predict behavior, such as perceptions, past behavior, current consumption, etc. Or, if the brand could afford it, it would be best to actually sell the product in test markets, and then predict behavior in a more general market based on the data in the test markets.

magneticnorth0
User Rank
Data Doctor
Re: A Sea of Red
magneticnorth0   11/29/2016 1:21:34 AM
NO RATINGS
I'd hate to say this amongst this wonderful group of writers, journalists, and data people, but it's clear that many US media outlets had been drowning in liberal ideology and in Clinton's "incentives." Being in such an environment can really convince you that there's no doubt Hillary would win. A Trump win just wouldn't make sense. Have that mindset in a tight race and it's easy for the data to bend according to your worldview.

SaneIT
User Rank
Data Doctor
Re: Fleeting Fame and Nate Silver
SaneIT   11/18/2016 1:24:38 PM
NO RATINGS
Just to be clear I'm not implying that Nate was lucky in the past, in that last post I was agreeing that it's possible but he's been too close to actuals for it to be blind luck.  I also don't believe that his model is fundamentally flawed, it just didn't account for some things that very few if anyone saw coming.  It's part of working with data, sometimes new variables pop up and you have to adjust.  

PredictableChaos
User Rank
Data Doctor
Re: Fleeting Fame and Nate Silver
PredictableChaos   11/18/2016 12:18:35 AM
NO RATINGS
In Nate's defense -

It's difficult to remember now, but Nate Silver was taking heat in the days before the election from people who thought his analysis was overestimating Trumps chances.

I don't think his prior success was luck at all. He's a skilled analyst. Who, like most of us, is not entirely unaffected by the chorus of other voices around us.

SaneIT
User Rank
Data Doctor
Re: Fleeting Fame and Nate Silver
SaneIT   11/17/2016 2:37:36 PM
NO RATINGS
@Louis Watson, it is possible that Nate was just lucky in the past but I have looked at his results and he was very accurate in the past two Presidential elections down to the county level.  I think we'll hear more about the flaws in many of the models out there, not just his.  I have heard about exit polling issues, phone polling issues and of course the always sketchy web based poll.  If we learn anything from this election cycle maybe it's that the hivemind who upvoted Boaty McBoatface into the winner of a government run name our new vessel poll isn't the most predictable group. 

SaneIT
User Rank
Data Doctor
Re: Fleeting Fame and Nate Silver
SaneIT   11/17/2016 2:37:35 PM
NO RATINGS
@Louis Watson, it is possible that Nate was just lucky in the past but I have looked at his results and he was very accurate in the past two Presidential elections down to the county level.  I think we'll hear more about the flaws in many of the models out there, not just his.  I have heard about exit polling issues, phone polling issues and of course the always sketchy web based poll.  If we learn anything from this election cycle maybe it's that the hivemind who upvoted Boaty McBoatface into the winner of a government run name our new vessel poll isn't the most predictable group. 

Broadway0474
User Rank
Blogger
Re: Rural vs. Urban Perspective
Broadway0474   11/17/2016 4:07:00 AM
NO RATINGS
Hopefully the pollsters learn their lessons from this election, but given the realities --- the increasingly complex problems of contacting people who want to be reached, let alone those who don't --- I think they should quit while they are behind. As for the protestors who didn't vote, I am not sure they will learn their lessons. They are worse than sore losers who claim to be exercising their right to free speech but who refuse to protect that right at the ballot box.

PredictableChaos
User Rank
Data Doctor
Re: Can Any Analytics Be Trusted Now?
PredictableChaos   11/16/2016 9:34:49 PM
NO RATINGS
Thanks @Bryan - I missed that one.

The US presidential process is long and tedious. People in Europe can't understand how it was "too late" for Biden to throw his hat in the ring when the election was still about a year away.

Despite being tiresome, I think it's a good process. People, especially politicians, can act like something they're not... for a few months. The year+ process means that all of us get to see our candidates for who they are - the best parts and the charactor flaws.

 

bkbeverly
User Rank
Data Doctor
Re: Can Any Analytics Be Trusted Now?
bkbeverly   11/16/2016 9:19:45 PM
NO RATINGS
@PC

There is an urban radio show, called The Breakfast Club - very popular and ton of videos on You Tube.  She was a guest on their show (4/18/16) and made reference to having a bottle of hot sauce in her bag.  One of the culinary practices in the black comunity is to put hot sauce on foods such as fried fish.  And there are some folks who actually carry small bottles with them.  This was an attempt to pursuade the listeners that she 'was down with the homies'. In fact if you enter 'clinton hot sauce purse' into a Google search, this event comes up. This act, in addition to getting a shout out from Jay Z and Beyonce, was designed to get the black vote; the premise was that any one who carried hot sauce in their purse understood the needs of black americans and was fully prepared to adjudicate their claims for justice, equality and economic empowerment.

Hence from a socio-political perspective, she tried to identify with people who did not look like her and told the people who looked like her that they were a basket of deplorables - think about that one for a minute ...

She believed that she could sacrifice the votes of the deplorables (and the pollsters supported her in that belief) in order to get the black vote. She should have read Acts 1:8 in the bible - start in Jerusalem, move through Judea, Samaria and then the entire world.  In short Christ told his disciples to start with the base, then expand to those outside of the base and then expand beyond your region. HRC skipped her base in Jerusalem and Judea, took her hot sauce to Samaria and never looked back. If there was ever a time to use the bible for directions in running a campaign, this was it. 

Hence PC - HRC demonstrated that she was more in touch with black people than Bernie. Even though he marched with MLK, she carried hot sauce and was therefore the better candidate. And she also knew Jay z and Beyonce - so that proved that Bernie was not in her league.

And yes - we the analytics community affirmed her hot sauce by only polling the people who used it.

PredictableChaos
User Rank
Data Doctor
Re: Can Any Analytics Be Trusted Now?
PredictableChaos   11/16/2016 9:18:16 PM
NO RATINGS
Oh, she carries a bottle of hot sauce in her purse?

And she tells people about this to establish that special bond - that we both like spicy food.

I can see why that didn't come off as real. Sheesh.

Page 1 / 10   >   >>
Information Resources
More Blogs from Tricia Aanderud
Using Excel as an enterprise reporting solution will always put you on a path to failure.
Election blather just might be turning people off from their social media use. Do you read? Do you turn off? Do you blather?
When presenting data it's easy to stay focused on the number. But remember that there are real people with real concerns and emotions behind those numbers.
While pretty pictures as reports look nice -- and easy to understand -- for an analyst, the consumer of that data might sit there and say, "Huh?"
Radio Show
A2 Conversations
UPCOMING
Jessica Davis
Data Analysts in Training: Meeting Tomorrow's Demand


3/8/2017   REGISTER   0
ARCHIVE
Jessica Davis
Our Bodies, Our Data: Medical Records For Sale


2/21/2017  LISTEN   62
ARCHIVE
Jessica Davis
Energy Analytics: Using Data to Find Savings


2/14/2017  LISTEN   44
ARCHIVE
Jessica Davis
Sharpen Your Analytics & Data Management Strategy


2/8/2017  LISTEN   74
ARCHIVE
Jessica Davis
Analytics: Make the Most of Data's Potential in 2017


1/19/2017  LISTEN   19
ARCHIVE
Jessica Davis
A2 Radio: Can You Trust Your Data?


12/20/2016  LISTEN   70
ARCHIVE
James M. Connolly
Retail Analytics: See Where Style Meets Statistics


12/6/2016  LISTEN   53
ARCHIVE
James M. Connolly
Why the IoT Matters to Your Business


11/29/2016  LISTEN   45
ARCHIVE
James M. Connolly
Will Data and Humans Become Friends in 2017?


11/22/2016  LISTEN   40
ARCHIVE
James M. Connolly
We Can Build Smarter Cities


10/20/2016  LISTEN   31
ARCHIVE
James M. Connolly
Visualization: Let Your Data Speak


10/13/2016  LISTEN   70
Information Resources
Quick Poll
Quick Poll
About Us  |  Contact Us  |  Help  |  Register  |  Twitter  |  Facebook  |  RSS