Global Challenges

Future Business
Jos Tavares

2015

Lecture 3
Data and Stories
 Data and Stories
Preparing the Story
Effective Storytelling
Features of Stories
Visualization: Form and Function
From Data and Stories to
 Data and Stories

"Data and Stories" combines

reason and hard data with narrative and empathy
to effectively communicate
information pertinent to business and the economy

Audiences need a balanced mix

rational and behavioural elements
understand and respond positively to complex issues
 Intro

Kurt Vonnegut on the shapes of stories

https://vimeo.com/53286941
 Data and Stories
The cost of collecting and storing data decreases magnificently
the volume of raw data can be overwhelming
Of all the data in existence, 90% was created in the last 2 years

When many people hear Big Data, they think Big Brother
Type big data is into Google and one of the top recommendations is, watching
you.

What it means to be human cant be tracked or quantified

But we can try!

A Data Scientists Real Job: Storytelling, Jeff Bladt and Bob Filbin
https://hbr.org/2013/03/a-data-scientists-real-job-sto
 Data and Stories
Difference between whats statistically significant and whats important for decision-making

Transforming data into decisions

Turn haystack of information into guidance

Humanize the data by turning raw numbers into a story

Sometimes a story is more numbers or different numbers

Data may can be qualitative

In the limit, data is information
Blurred line between data and stories

A Data Scientists Real Job: Storytelling, Jeff Bladt and Bob Filbin
https://hbr.org/2013/03/a-data-scientists-real-job-sto
 Data and Stories

1. Data gives you the what, but humans want the why
2. Look for data that affect individuals and organizations
3. Present data that most people grasp
4. Engage, discuss, and then return to the data with new questions

A Data Scientists Real Job: Storytelling, Jeff Bladt and Bob Filbin
https://hbr.org/2013/03/a-data-scientists-real-job-sto
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
 Preparing the Story
Tensions
Oversimplification and overwhelming detail
Interactivity and story
Exploration and decoration
Focus versus depth
Author versus audience

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
Preparing the Story

Storytelling with Data, Jonathan Corum

http://style.org/tapestry/
 Effective Storytelling

1. Sense of engagement and genuine interest

To what degree were users engaged?
Were users shared or conversed around the presentation?
2. Empathy or care for subjects involved
Did the story spark emotions?
Did the data story spurred any personal insights or questions?
3. Credibility of data and story
4. Motivation to work through the data, the story
Did users feel they understood the context of the data ?
Did they feel confident in their interpretation?
5. Resulting understanding of the subject
Did they learn it faster or better?
6. Take away
Did they feel they could make a more informed decision based on the presentation?
7. Extent of recall
Was it memorable, or did the audience forget it 5 minutes, 5 hours, or 5 weeks later?
8. Call to action
Extent to which exposure to story influences behavior
Effective Storytelling
Features of Stories
 Data Visualization
Types and Purposes

An Economists Guide to Visualizing Data, Jonathan A. Schwabish, Journal of Economic Perspectives

https://www.aeaweb.org/articles?id=10.1257/jep.28.1.209
 From Data and Stories
to Data and Stories

Bond on Womans Day

Half the class registers the hard data
Half the class the narrative sentences (no hard data)
Seat belt
Identify and discuss the empathy storyline
 From Data and Stories
Bond On Womans Day

Half the class registers the hard data

Half the class the narrative sentences

(no hard data)

https://www.youtube.com/watch?v=gkp4t5NYzVM
 From Data and Stories
Seat Belt

Identify and discuss the empathy storyline

https://www.youtube.com/watch?v=h-8PBx7isoM
 Stories with Numbers
Yes, Numbers Lie!

Bill Gates Is Richer Than 140 Nations

If Gates were an independent nation

he would be the 37th richest nation on the planet

http://www.forbes.com/sites/timworstall/2013/09/28/bill-gates-is-not-richer-than-140-nations/#25c526a52c58
 Stories with Numbers
From Figure to Causality: An Itinerary
Figures Raw, Absolute
Ratios Relative, Already a Story
Comparisons Across time and space
Correlations Many data points, visual, coefficient of correlation
Regression, Univariate Test, Statistics
Regression, Multivariate Many things co trolled for, cross effects
Causality Exogeneity, the Holy Grail of a story, methods (DiD, RDD,
IV)
 Stories with Pictures
Words
Photos, Paintings, Drawings
Graphs and Diagrams
Animations
Stories with Pictures
Words

http://13pt.com/projects/nyt060307/
Stories with Pictures
WordsWords
Stories with Pictures
Words
 Stories with Pictures

This is Langes most celebrated and iconic portrait of American

family life of the thirties and an image that stays in the mind for a
great deal of time, such is its power. The subject is Florence
Owens Thompson and the name of the photograph is Migrant
Mother. In Langes own words I did not ask her name or her
history. She told me her age, that she was thirty-two. She said
that they had been living on frozen vegetables from the
surrounding fields, and birds that the children killed. She had just
sold the tires from her car to buy food. There she sat in that lean-
to tent with her children huddled around her, and seemed to
know that my pictures might help her, and so she helped me.
There was a sort of equality about it. Some of this has been
slightly disputed by Thompsons son but the image remains a
portrait of strength in adversity, of a moment of quiet, desolate
thought in a desert of hopelessness.
 Stories with Pictures
Photos, Paintings, Drawings

http://www.eyewitnesstohistory.com/migrantmother.htm
 Stories with Pictures
Photos, Paintings, Drawings

http://www.independent.co.uk/news/world/europe/kos-crisis-the-story-behind-the-
photograph-of-a-syrian-father-shared-by-thousands-online-10461933.html
 Stories with Pictures
Photos, Paintings, Drawings
 Stories with Pictures
Photos, Paintings, Drawings

World Press Photo of the Year 2013, John Stanmeyer, USA, VII for National Geographic, 26 February 2013, Djibouti City, Djibouti
African migrants on the shore of Djibouti city at night, raising their phones in an attempt to capture an inexpensive signal from neighboring Somaliaa tenuous link to relatives abroad.
Djibouti is a common stop-off point for migrants in transit from such countries as Somalia, Ethiopia and Eritrea, seeking a better life in Europe and the Middle East.
 Stories with Pictures
Photos, Paintings, Drawings

Photograph by Spencer Platt, USA, Getty Images

Young Lebanese drive down a street in Haret Shreik, a southern suburb of Beirut, to check on their homes after bombardments by Israel.
 Stories with Pictures
Graphs and Diagrams
Map of the market
 Stories with Pictures
Graphs and Diagrams
Who Is Donald Trump Insulting?

http://www.nytimes.com/interactive/2016/12/06/upshot/how-to-know-what-donald-trump-really-cares-about-look-at-who-hes-
insulting.html?_r=1&hp&action=click&pgtype=Homepage&clickSource=story-heading&module=b-lede-package-region&region=top-news&WT.nav=top-news
 Stories with Pictures
Animations

All the Medalists: Mens 100-Meter Sprint

http://www.nytimes.com/interactive/2012/08/05/sports/olympics/the-100-meter-dash-one-race-every-medalist-ever.html?_r=1&

The Yield Curve

http://www.nytimes.com/interactive/2015/03/19/upshot/3d-yield-curve-economic-growth.html?action=click&contentCollection=https://www.publico.pt/2017/01/08/sociedade/noticia/o-
mundo-das-pessoas-de-pernas-para-o-ar-
1757178The%20Upshot&region=Footer&module=WhatsNext&version=WhatsNext&contentID=WhatsNext&moduleDetail=undefined&pgtype=Multimedia
 How Data Will Transform Business
Philip Evans

https://www.ted.com/talks/philip_evans_how_data_will_transform_business
 Global Business Challenges

Data and Stories

Correlation and Causation

Optimum
Bonded Rationality
Satisficing
 Lecture 3 Correlation and Causation
Concepts The idea that correlation implies causation is a

Correlation and Causation common fallacy. Correlation indicates a statistical

Optimum relationship between two variables, not necessarily
Bonded Rationality
Satisficing associated with cause and effect. Causation is
statistical relationship that can credibly be associated
with a cause and effect mechanism, validated through a
story, a model, an experiment, or a sophisticated
analytical technique.

Source: www.economist.com/economics-a-to-z/s

7
 Lecture 3 Optimum
Concepts As good as it gets, given the constraints the individual
or organization are operating under. For the concept of
Correlation and Causation
Optimum optimum to mean anything there must be both a goal -
Bonded Rationality
Satisficing say, to maximize economic welfare, and a set of
constraints - such as a limited stock of resources.
Optimizing is the process of doing the best you can in
these circumstances.

Source: www.economist.com/economics-a-to-z/o

4
 Lecture 3 Bounded Rationality
Concepts
A theory of human decision making that assumes that
Correlation and Causation people behave rationally, but only within the limits of
Optimum
Bonded Rationality the information available to them. Because their
Satisficing
information may be inadequate (bounded) they may
make decisions that appear irrational, or indeed are so.

Source: www.economist.com/economics-a-to-z/b

3
 Satisficing
Lecture 3
Concepts Settling for what is good enough, rather than the best
possible. Satisficing assumes individuals aim for a level
Correlation and Causation
Optimum of achievement that is good enough. Often occurs in
Bonded Rationality
Satisficing situations in which decision makers are trying to pursue
more than one goal at a time.

Source: www.economist.com/economics-a-to-z/s