Normalizing Data Visualization for More Accurate Results

Reading Time: 2 minutes

Here’s something you might not want to hear: Accurate, effective data visualization involves a lot of math. Inflation, normalization…the list of concepts applied to data visualization scenarios goes on.

But the good news is that you don’t necessarily need a degree in mathematics or economics to create and understand data visualizations when you have the right software tackling the complex math for you.

Economic Concepts Keep Analytics On-Track

Inflation and normalization are two economic concepts that software uses to ensure accurate data visualization. Both concepts are vital to providing a clear data visualization picture, but sometimes they are overlooked.

In his recent blog post, Alberto Cairo describes the heart of the problem:

“Not adjusting for inflation is like comparing the number of homicides in New York City (population: 8 million) with the homicides in Tucson, Arizona (population: 524,000.) It wouldn’t be fair to do so. It’d be better to use homicide rates (cases per 100,000 people. Absolute numbers are tricky. In most cases, it’s advisable to normalize them somehow before jumping to conclusions.”

Adjusting for normalization means comparing apples to apples, not apples to oranges. In the example above, it means dropping the numbers to 1 in 100,000, so that you compare New York City’s population to New York City, not to the population of Tucson, Arizona. That way you can see accurate numbers in percentages, not drawn out of proportion because of individual units.

Don’t Mislead With Incorrect Comparisons

These concepts also apply to financial data. For example, when you’re reviewing business trends over the last 20 years, $500 million in 1999 will not be the same as $500 million in 2019. And representing these numbers in dollars—rather than percentages—will just confuse and befuddle your analytics. Or worse, mislead your decision-making team.

Adjusting for inflation lets you compare actual value, not inflated (or deflated) prices that fluctuate over time. That’s one more way data visualization software makes your life easier: taking care of the math and leaving the high-level problem-solving to you and your experts.

Previous articleWhat Does Behavior-Based Architecture Really Mean?
Next articleBig Data: Driving the Manufacturing Renaissance
Steve Leung is Director for TIBCO Spotfire Cloud at TIBCO Software. He has over 15 years of experience in the enterprise technology with strong experience in financial services. Prior to joining TIBCO Software, Steve has been with companies such as Oracle, Autonomy, BEA and webMethods helping global organizations design and build complex enterprise architectures. Steve is a business technologist that has held multiple roles as a consultant to business development helping customers achieve business value from technology. Steve holds a Bachelor’s degree in Computer Science from Binghamton University.