AFP’s latest Financial Planning and Analysis (FP&A) Guide, underwritten by Workiva, focuses on the power of statistics.
THE NEED FOR STATISTICAL TOOLS
Statistical tools are gaining in importance as the volume, variety, and velocity of data increases. These tools are built into the spreadsheets, EPM tools, reporting software, and business intelligence packages at rates of increasing sophistication. If we are not using these tools, then we are sub-optimizing. If we are using them incorrectly, then we are in danger of drawing false conclusions.
The rewards for being fluent in statistical tools are many. We become more efficient and effective in everything we do, and we can keep pace with the new normal of new capabilities driving new operating models. We can remain conversant with our partners in marketing, supply chain, and other areas that are already using statistics in their daily work. This will help us to provide effective challenges to the business and drive decisions as valuable business partners. Without it, we lack a seat at the decision-making table.
The new FP&A Guide is not intended to be a primer or introductory text in leveraging statistical tools. Instead, we asked FP&A and finance professionals to list the statistical tools that are most overlooked or misused. Then, we asked them to explain these tools and how they benefit professionals.
Tips for Using Statistics Well
The power of statistics is the ability to understand the world and make meaning from the increasing piles of data that accumulate around us. The danger is in their misuse, or misunderstanding. Benjamin Disraeli said there are three kinds of lies: “Lies, damned lies, and statistics.” We need to speak this language or be at the mercy of others who do.
Statistics is a huge topic; this guide presents a few tools you might see, as well as a case study that shows how they can be applied. Taking a step back from the specifics of the statistical application, we can take a look at data analyses in general. How do you make sure that your analysis starts off strong with good foundational questions and data, proceeds with good analysis, and comes to a logical set of recommendations?
Here are some tips on how—questions to ask that will help all your statistics and data projects.
- Which came first, the data or the question?
- Be careful that you are managing the numbers—don’t let the numbers do the managing for you, or of you.
- What data do you have, and is it the right data for this purpose?
- Can you tell me about the source of the data you used in your analysis?
- Are you sure that the sample data represents the population?
- Are there any outliers in your data distribution? How did they affect the results?
- What assumptions are behind your analysis?
- Are there conditions that would make your assumptions and your model invalid?
- Why did you decide on that particular approach to analysis? Did you use multiple approaches?
- What transformations did you have to do to the data to get your model to fit well?
- Did you consider other approaches to analyzing the data, and if so, why did you reject them?
- How likely do you think it is that the independent variables are actually causing the changes in the dependent variable?
- Is there additional analysis that can be done?
- How do you know that the correlation is causality?
- Did someone check (and duplicate) your findings?
By some estimates, we have created more data in the past three years than we have in all of history, and that is a fraction of what we will create in the next five years. Statistics is a critical tool to work with data, to interpret key messages, make predictions, and take action upon that wealth of data. The capabilities to apply data are expanding as well; it is our responsibility as financial stewards to make sure we are prepared to harness the data and apply our tools appropriately.
There are plenty of statistics tools to focus on but, we’ve picked 5 we think you need to explore more in depth. Check them out in our interactive experience.