Finding the story in the data - Ray Poynter - 2015
6 likes1,153 views
The document by Ray Poynter discusses the importance of storytelling in data analysis, emphasizing that data alone does not convey meaning and frameworks are essential for extracting and organizing stories from data. It outlines a structured approach to transforming data into compelling narratives that address specific business problems and facilitates decision-making. Key steps include defining the problem, understanding the context, and effectively communicating the findings to elicit the desired response from stakeholders.
Finding the story in the data - Ray Poynter - 2015
- 1. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Learn How To Find The Story In The Data Ray Poynter December 2015 #NewMR 2015 Corporate Sponsors #NewMR 2015 Supporters Schlesinger Associates Keen as Mustard
- 2. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Why are we interested in storytelling? Memorable ABenCon Grabbing Easier to understand Gives coherent message Shows we understand it
- 3. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 The data doesn’t speak for itself
- 4. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Storytelling – NarraHve Theme Wake Breakfast Travel Work Lunch Work Drinking Travel Sleep Get changed Warm up Run Warm down Shower Get changed • Smallpox emerged about 10,000 years ago • 300-‐500 million deaths during 20th Century • One of the first to be tackled by vaccinaCon • Declared exCnct in 1979 • One of only 2 so far (Rinderpest) • Let’s tackle others, e.g. Polio
- 5. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Frameworks Most of the teams that reliably produce good analysis and useful stories use frameworks – Individuals are less dependent on frameworks Elements of frameworks – How to frame the problem – Linking the project to a wider context – A standard method of organising the data (qual and quant) – SystemaCc methods of analysing data – A preferred method for extracCng the story and linking it the wider context
- 6. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Further Reading Published by Wiley, 2004
- 7. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 From Data to Stories 1. Define the problem 2. Establish what is currently known/believed 3. Check and organise the data 4. Find the message in the data 5. Cra` and tell the story Starts when the request for a study emerges. It does NOT start when the fieldwork finishes.
- 8. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Define the Problem “A problem defined is a problem half-‐solved” Sources of informaCon: – The request for a study – The proposal – Discussions between sponsor, insight team and supplier • What is the background to the project? • What would success look like? • What acCons should follow from the research? • What do people think the results are going to be? (Or, what are the prevalent hypotheses?) Smith & Fletcher, 2004
- 9. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Establish What is Already Known? • The frameworks approach avoids focusing on just the current research project • The analysis, the validity, and the story need to blend research with the wider context • The context is a web of exisCng knowledge: – Within your organisaCon – Within the agency/supplier – In the public realm
- 10. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Who is the project for? _________________ What is the business issue/problem that is being addressed? __________________________________________________ What does the business want to do, once it has addressed this issue? ______________________________________________________ What do we already know? Item Held by: DescripHon 1 ______ ______ ______________ 2 ______ ______ ______________ 3 ______ ______ ______________ AssumpHons and predicHons Who What 1. ______ ______ 2. ______ ______ Simplified
- 11. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Assembling the Evidence • QuanCtaCve – Standardize? Missing Data? Indexing? Re-‐basing? • QualitaCve – TranslaCons? Transcripts? Notes? • The nature of the sources – Credibility? Bias? InteracCons?
- 12. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015
- 13. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015
- 14. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015
- 15. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Normalising by ‘Share of’
- 16. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 ‘Share of’ is a relaHve measure
- 17. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Normalizing by Coding • SenCment analysis, open-‐ended comments converted to PosiCve, NegaCve and Neutral • DigiCzing from analogue to binary • AllocaCng to segments • Scoring different elements – (think American Football or Rugby, different points for different events, leading to points in a league)
- 18. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Normalizing by Growth PaXerns Forbes: hBp://bit.ly/NewMR_208
- 19. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Is My Data Right? We see paBerns, even when they are not there. Image from Viking I, 1976 Mars – led to theories of intelligent life.
- 20. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Spurious CorrelaHons
- 21. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 HRT and CHD • Several studies showed that women taking HRT were less likely to suffer from coronary heart disease • Some leading doctors propose that HRT was protecCng women against CHD • Randomised Controlled tests showed that HRT created a slight increase in risk of CHD • Huh! – Women taking HRT were typically from higher income, healthier groups in society – who have lower rates of CHD
- 22. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Embedding Frameworks • Establish your framework • Share it with colleagues • Share it with suppliers • New projects can be designed to produce inputs that work well with the framework you are using
- 23. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Finding the Story 1. Know what the quesCon is. Have an idea of what success looks like. 2. What is the big story? – What do most people do? Why do most people do it? 3. What are the relevant excepCons? 4. Determine how the message in the data answers the business quesCon and cra` that as a story.
- 24. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Find the Total Picture First Then the relevant detail Quant • Look at the Total Column • Look for big numbers and big paBerns • What is the big picture? • This will frame the detail Qual • Read the transcripts – Unless you conducted the fieldwork • Create notes and memos • What are the main messages In the context of the Business QuesCon
- 25. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Where does the best MR come from? Column % Which of the following best describes you? Countries Merged Total Research or Consultancy Supplier Supplier to the research industry Research Buyer/ User Academic + Other English Speaking Non-‐English Speaking UK 63% 61% 60% 92% 40% 66% 60% USA 51% 52% 50% 46% 60% 52% 50% Germany 18% 13% 30% 15% 60% 16% 21% Australia 15% 14% 15% 15% 20% 16% 12% Canada 11% 8% 20% 0% 40% 9% 14% France 7% 7% 10% 8% 0% 7% 7% Japan 5% 3% 15% 0% 0% 3% 7% Brazil 3% 3% 5% 0% 0% 3% 2% China 2% 1% 5% 0% 0% 3% 0% Italy 2% 1% 5% 0% 0% 0% 5% Other 8% 10% 10% 0% 0% 9% 7% None of these 11% 15% 5% 0% 0% 9% 14% Column n 109 71 20 13 5 67 42 The wrong approach to starCng analysis
- 26. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Where does the best MR come from? Column % Which of the following best describes you? Countries Merged Total Research or Consultancy Supplier Supplier to the research industry Research Buyer/ User Academic + Other English Speaking Non-‐English Speaking UK 63% 61% 60% 92% 40% 66% 60% USA 51% 52% 50% 46% 60% 52% 50% Germany 18% 13% 30% 15% 60% 16% 21% Australia 15% 14% 15% 15% 20% 16% 12% Canada 11% 8% 20% 0% 40% 9% 14% France 7% 7% 10% 8% 0% 7% 7% Japan 5% 3% 15% 0% 0% 3% 7% Brazil 3% 3% 5% 0% 0% 3% 2% China 2% 1% 5% 0% 0% 3% 0% Italy 2% 1% 5% 0% 0% 0% 5% Other 8% 10% 10% 0% 0% 9% 7% None of these 11% 15% 5% 0% 0% 9% 14% Column n 109 71 20 13 5 67 42
- 27. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 0% 10% 20% 30% 40% 50% 60% 70% Which Country Produces the Best MR? The Big Message Big story QuesHons Why are the UK & USA so high/different? Is this true for everybody? What are the implicaCons of this?
- 28. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 The Cartographer and the Journalist
- 29. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 The Lead Nora Ephron When Harry Met Sally Sleepless in Sea1le 1st Day in Journalism School 5 Ws (Who, What, When, Where & Why?) Asked to write the Lead for the school newspaper “The en3re school faculty will travel to Sacramento next Thursday for a colloquium in new teaching methods. Among the speakers will be anthropologist Margaret Mead, college president Dr. Robert Maynard Hutchins, and California Governor Edmund Brown.” All the students wrote about the 5Ws – good, but not right. The Lead? No school next Thursday!
- 30. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Different PerspecHves
- 31. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 The Tenuous Link Between Finding the Story and Telling the Story • In finding the story we have mulCple data sources • We have differing degrees of confidence in those sources – A conjoint study with consulCng surgeons might be our best source for finding the story • The best way to convey the story does not have to rest on the ‘best’ data – A vox pop video with a paCent might be a poor way to find the story, but it can be a great way to tell the story
- 32. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 What are the key findings? 1. Link to the project objecCves 2. ‘Need to know’ not ‘nice to know’ 3. Supported by paBerns or themes in the data – Not just a single data point 4. Clear findings – e.g. In the chart UK and USA were a long way ahead in terms of Best Research
- 33. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Hans Rosling 1. What is his key message? 2. What is the story? 3. What has he le` out? hBps://youtu.be/jbkSRLYSojo
- 34. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Hans Rosling & NarraHve Theme? Key Message: – It is possible to tackle world health problems Key Story: 1. 200 years ago short-‐life expectancy was the norm, then the West moved ahead, but over the last 50 years most countries have caught up 2. There are some countries sCll behind, and some regions of other countries, but since most of the world has been solved, the rest can be Key narraHve axis: – 200 years from 1810, from bad to good
- 35. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 What Did Hans Rosling Leave Out? Numbers: – A few dates, 3 life expectancies, 3 income levels – Based on 200 countries and 120,000 numbers DefiniHons: – Which 200 countries? – How did he deal with country amalgamaCon and fragmentaCon? 517 other staHsHcs: – GapMinder lists 519 key global stats, over Cme
- 36. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Using an Insight
- 37. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 You’re not you when you are hungry • People behave differently when they are hungry • Snickers is big enough to end the hunger • Global campaign – Local execuCons • Sales increase – e.g. USA sales +8%
- 38. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Developing your narraHve theme • Select your primary axis • This is the elevator pitch • Use a structure that works with the audience • Typical USA structure – The main finding was X, so we recommend Y & Z – Now, let’s tells you why it is X, and why are it’s Y & Z – But it can be different in different places
- 39. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 The Big Picture • Develop a framework approach • Define the problem before you try to find the answer to it • Put the research project into the context of what is already known • What do you want the client to think, feel, do a`er hearing the results? – The story is a device to deliver that acCon
- 40. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Thank You! Follow me on TwiXer @RayPoynter Or sign-‐up to receive our weekly mailing at hXp://NewMR.org
- 41. Learn How To Find The Story In The Data Ray Poynter, UK, December 2015 Q & A Ray Poynter The Future Place #NewMR 2015 Corporate Sponsors #NewMR 2015 Supporters Schlesinger Associates Keen as Mustard