Kathy Vogler, Communications Manager, Expedient Technology Solutions
Early on in my career, I was told by a boss that my intuition was a gift and that I should always trust my guts in every decision I made. That advice has really worked for me most of my life. However, the new reality in a data-driven culture embraces the use of data in decision-making.
“If we have data, let’s look at data. If all we have are opinions, let’s go with mine.” ~ Jim Barksdale; President and CEO of Netscape 1995 - 1999
Maybe my mind captures, cleans and curates meaningful data. But the volume of our organizational data is much more than my job or my thoughts. Our culture is supported by data-driven decision making and the data holds our teams accountable.
The literacy level of any team member to leverage the data at hand and turn that into appropriate decisions is key. Hence a systematic approach to analysis of the data and reporting that is understandable and actionable is of utmost importance. The staggering amount of data that we store and analyse means that we need to meet often to review data findings, choosing what needs to be measured and what metrics will be implemented. Our data wizards have created detailed metrics on our customers’ experience which helps our team deliver wow.
No Departmental Silos Allowed
Departments tend to focus on the data that affects them directly, and rightfully so. But this sometimes creates a logjam and we become ignorant to the language of data that is being interpreted by each team. If we tie every team in an explicit and quantitative level, it helps us to understand if we have enough data for a reliable model to make intelligent decisions. We need to evaluate uncertainty by testing and reevaluating the data collectively. It’s been said that promising ideas greatly outnumber practical ideas. Proof of concepts will determine if the idea is viable in production. The immediate goals directly affect each team member by saving time and avoiding rework with readily accessible knowledge at their fingertips. Metrics should be universal and each team should take ownership of interpreting their data to help the literacy of the enterprise.
Measure what you Should, not what you Can
More data doesn’t guarantee better decisions, but it is always better to start with data. Better decisions almost always begin with better informed teams. And it’s our duty as team members to ask questions. And so I bring up skewed data …
1 Some distributions of data, such as the bell curve or normal distribution, are symmetric. This means that the right and the left of the distribution are perfect mirror images of one another. Not every distribution of data is symmetric. Sets of data that are not symmetric are said to be asymmetric. The measure of how asymmetric a distribution can be is called skewness.
The mean, median and mode are all measures of the center of a set of data. The skewness of the data can be determined by how these quantities are related to one another.
One measure of skewness, called Pearson’s first coefficient of skewness, is to subtract the mean from the mode, and then divide this difference by the standard deviation of the data. The reason for dividing the difference is so that we have a dimensionless quantity. This explains why data skewed to the right has positive skewness. If the data set is skewed to the right, the mean is greater than the mode, and so subtracting the mode from the mean gives a positive number. A similar argument explains why data skewed to the left has negative skewness.
Pearson’s second coefficient of skewness is also used to measure the asymmetry of a data set. For this quantity, we subtract the mode from the median, multiply this number by three and then divide by the standard deviation.
X = mean value
Mo = mode value
S = standard deviation of the sample data
Skewed data arises quite naturally in various situations. Incomes are skewed to the right because even just a few individuals who earn millions of dollars can greatly affect the mean, and there are no negative incomes. Similarly, data involving the lifetime of a product, such as a brand of light bulb, are skewed to the right. Here the smallest that a lifetime can be is zero, and long-lasting light bulbs will impart a positive skewness to the data.
1 Taylor, Courtney. "What Is Skewness in Statistics?" ThoughtCo, Aug. 25, 2020, thoughtco.com/what-is-skewness-in-statistics-3126242.
It’s important to take note of skewness while assessing your data since extreme data points are being considered. Take into consideration the extremes for current logic instead of focusing only on the average which provides a better picture of the future logic. Flawed data analysis leads to flawed conclusions which often result in poor business decisions.
I do trust my instincts, but my reporting to others is much better with statistical data.