Five Tips for Presenting Data Analyses: Telling a Good Story with Data - PDF

Please download to get full document.

View again

of 5
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Information Report

Concepts & Trends


Views: 11 | Pages: 5

Extension: PDF | Download: 0

Related documents
Five Tips for Presenting Data Analyses: Telling a Good Story with Data As a professional business or data analyst you have both the tools and the knowledge needed to analyze and understand data collected
Five Tips for Presenting Data Analyses: Telling a Good Story with Data As a professional business or data analyst you have both the tools and the knowledge needed to analyze and understand data collected by your organization, but that s only one part of the job. You also need to communicate insights gained from your analysis to others better placed to take action and make use of the information that you and your data models can provide. And that s not so easy. You could just report bare facts and figures, but these are easily lost in the mass of letters, s, tweets, and other collateral that hard pressed execs have to handle. A presentation is far better, especially with some colorful charts to help make your point. However, we ve all experienced death by PowerPoint and know just how hard it is to engage an audience and get them to understand often quite complex data without nodding off and losing focus. It can take a lot more than a deck of slides to get the message across. Whether telling engineers how to minimize failures by rescheduling maintenance or advising the board on the ramifications of a proposed takeover, good communication skills are also required. Indeed, they are an absolute must and a key part of the role of a data analyst. Unfortunately communication skills don t always go hand in hand with those required to understand and apply the kind of statistical models on which data analytics are based. So we ve come up with five key points to consider when engaging with an audience during an analytics presentation Key points, designed to help you get the message that you ve uncovered using data analytics across, simply, quickly, and effectively. WHITEPAPER 2 1 ALWAYS LISTEN TO THE DATA. One of the main benefits of data analytics tools such as TIBCO Spotfire is their ability to not just identify relationships and trends hidden in corporate data, but through the power of visualization, empower you to weave those discoveries into a story that can be understood by others. Unfortunately that power can be misused, and a common mistake is to approach data analytics from the wrong direction, with a fixed agenda or preconception of the final results. This can lead to data manipulation, effectively invalidating the whole exercise. You might, for example, be asked to come up with an explanation as to why sales personnel in one area are performing better than those in another, with the clear implication that you will find fault with the people involved. Or perhaps, following an acquisition, those who initiated it might ask you to justify the purchase with analytics that prove the economies of scale now possible. How could you, as a mere data analyst, do otherwise than come up with the results implicitly being requested? Of course you may get lucky and find that the data does, in fact, support the outcome you ve been asked to prove. But that s not always the case. Skewing the results may help to fulfill the implied terms of the brief, but it will make it a lot harder to build a convincing case and communicate the results of what you know to be a flawed analysis. In the longer term, too, this kind of spin can cause commercial harm, damage your career prospects, and perpetuate the scepticism that already exists about the benefits and value of data analytics. Do not start with a goal in mind. Allow conclusions to emerge from the data to build strong evidence of your points. Start with an open mind and allow the story to surface out of the analytics. This will make the results more plausible and easier to communicate. If the data doesn t support the premise you ve been asked to prove, the premise is most probably wrong, and you should say so. Always remember that strong supporting data will allow you to make strong and authoritative conclusions. Skewed results may win approvals in the short term, but are harder to present, harder to justify, and will not stand up to detailed scrutiny. 2 TURN YOUR ANALYSIS INTO A STORY. One of the best ways of communicating any kind of complex information is to turn it into a story, starting at the beginning and working your way through to the end. If you can make the story relevant to the audience that can also help, by making the results both easier to understand and more likely to be remembered. A good story will also make it easier to convince an audience of the validity of your approach and make them more likely to accept and take action based on your conclusions. An anecdote or humorous metaphor is a good way of starting an analytics story because these can really help get the audience on your side and paying attention. For example, Have you ever noticed how sales in the North are like balloons, or thought about what makes them go up or down so often? Use this as an opening gambit and you can go straight to charts showing exactly what causes these sales balloons to rise or fall. Although a good starting point, keep the anecdotes and metaphors to a minimum and avoid adding extra threads to the story because the audience (and, possibly, you) could easily lose track of what you re really trying to communicate. Friendly is good, but you need to be authoritative and concentrate on getting the job done. WHITEPAPER 3 Build a story around your data and create a storyboard to help structure the presentation of your analytics and conclusions. Look for relevant and interesting graphics beyond charts to help reinforce your message and make it more memorable. Don t be afraid of making the presentation personal or of using humor. It doesn t have to be all about the figures. Opinions and other qualitative data can be included to embellish the numbers and to drive home the hard facts you want to communicate. Encourage questions but ask the audience to wait until the end of the presentation because dealing with ad-hoc queries can interrupt the flow and may be answered in a later slide anyway. 3 KEEP IT SHORT AND SNAPPY. Communicating the results of a data analytics project as a story is a good idea, but you don t have to start at the beginning or document every step along the way from start to finish. Less is always more when presenting complex points, especially when your audience is more likely to be interested in the destination than the journey. Think about the most memorable steps that led to your results and use these to structure your storyboard without making it too lengthy. A timed run-though, with or without an audience, will enable you to tell whether the presentation is the right length or not. There are no hard and fast rules here, and the exact timing will depend on the importance and nature of the analytics. However, the average attention span starts to get stretched after about minutes. If you can t prune the material back, you might want to consider a break in the proceedings to, for example, hear comments from a colleague with a personal viewpoint on the analysis before summarizing and concluding. Try and relate what you include to the audience concerned, but do not expect them to follow an analysis and work out what the results mean for themselves. You re the analyst: you need to do the hard work and make it easy for those without analytical skills to understand your conclusions and why you came to them. Less may be more, but some detail and background is required. While you may find it interesting to recount the many failed statistical models and other mishaps that occurred before coming to your conclusions, others will quickly stop listening. Too much information and they could end up missing the point altogether. When putting a presentation together, keep the number of slides to a minimum and limit the number of elements on each slide. Clean and simple is good. Avoid too many fancy graphics and pictures. As a general rule, the more senior the audience, the less interested they will be in detail, so keep it simple and get to the point as quickly as possible. Use notes to provide more detailed background material or produce a separate report to support the presentations. Keep supporting material short and sweet also. Be prepared to guide your audience through the data points that led to your conclusion. You only have that moment to earn the confidence from your audience when they ask the question. WHITEPAPER 4 4 VISUALIZE, VISUALIZE, VISUALIZE. There s a very good reason why applications like Spotfire include powerful and easy to use visualization tools. Put simply, visualization makes complex data much easier to understand and remember. So, instead of complicated tables that audiences will try and (typically) fail to interpret for themselves, employ appropriate charts to summarize and display the information in a more digestible format. Don t be afraid to use visualization tools to get your message across, but go for maximum impact by keeping your visualizations simple, with signposts to direct the audience to the information you want to communicate. The ideal result should be a visualization that can be appreciated and understood within seconds, not one that requires minutes of study to appreciate. Or, worse still, a visualization that needs a lengthy explanation to understand. Make sure your visualizations accurately support and reflect the results of your analytics and that you don t just use them to liven up your presentation. Visualizations need to be relevant, and you should choose the right type of chart to suit the type of data involved. For example, while a bar chart is a good way of comparing values, for showing change over time you should use a line graph and a scatter chart to show relationships between values. Pick the appropriate data visualization for your data. Do not constrain yourself to the familiar bar and line charts if the data does not warrant it. Spotfire users have the benefit of the built-in Recommendations engine, which will suggest the most suitable charts for the data being analyzed. Although visualizations need to be based on data, there is no need to include the data itself in the charts you create. Category labels and summary data is OK, but leave out the detailed supporting detail. If your data includes geographic information (sales by country or region, for example), use actual maps to make the associations more obvious and memorable. If a visualization looks too big or complex to follow, use layering and drill down from a summary visual at the start to more specific charts. This will also enable the audience to concentrate on what is most meaningful to them. Rather than exporting charts or re-creating them in a presentation tool, consider adding extra drama and authority by using a data analytics application like Spotfire to present the visualization live using real data. WHITEPAPER 5 5 EMPLOY COLLABORATION. You may be the best data analyst on the planet, but you re not infallible, and chances are you won t have the business acumen of those wanting to make use of your analytics. Letting the data inform and drive your results provides a solid base, but it s still good practice to validate the approach being taken and get colleagues to review your models and the conclusions you ve made before attempting to convince others to put them into practice. Your audience may not always focus on the areas of the visualization that support your conclusion. Provide guidance to your viewer by adding annotations that tell them where you are expecting them to focus, then allow your viewers to add their own comments or even have a conversation. This will allow your viewers to create their own relationship with your points, creating a much more powerful, collaborative experience. You should also brush up on your presentation skills (no matter how big or small the potential audience), and rather than just lecturing, expect to have a two-way conversation with your audience to help them understand your analytics. More than that, you should actively encourage questions and be open to constructive criticism and discussion of both the methods employed and the conclusions drawn. Make both your presentation and the supporting analytics available for your audience to explore themselves. Pick a tool that allows your audience to have transparent dialog about your insights. Transparency creates deeper connection with your audience and will make collaboration much more productive. Ask for comments and feedback using , social media, blogs, and other channels and be prepared to re-visit and modify your analytics on the basis of that collaboration. Do not make the collaboration process open-ended. Set reasonable timescales for responses to be sent in and assimilated; schedule follow-up meetings and set out firm deadlines to keep the process moving. LEARN MORE As a data or business analyst, one of your key goals will be to use analytics to help others generate insights and understand trends and relationships otherwise hidden within their data. Communication is key to achieving that goal, and we hope this document is of some help in that respect. In addition, you also need the right tools to both perform the necessary analytics and help visualize the results in a format easily understood by a nontechnical audience. Naturally, we think TIBCO Spotfire is just the tool for that job, but don t just take our word for it, find out more about what Spotfire has to offer and check it out for yourself by signing up for a free trial today. Global Headquarters 3307 Hillview Avenue Palo Alto, CA TEL FAX TIBCO Software empowers executives, developers, and business users with Fast Data solutions that make the right data available in real time for faster answers, better decisions, and smarter action. Over the past 15 years, thousands of businesses across the globe have relied on TIBCO technology to integrate their applications and ecosystems, analyze their data, and create real-time solutions. Learn how TIBCO turns data big or small into differentiation at 2016, TIBCO Software Inc. All rights reserved. TIBCO and the TIBCO logo, and Spotfire are trademarks or registered trademarks of TIBCO Software Inc. or its subsidiaries in the United States and/or other countries. All other product and company names and marks in this document are the property of their respective owners and mentioned for identification purposes only. 02/12/16
We Need Your Support
Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

Thanks to everyone for your continued support.

No, Thanks