Talking with human resources practitioners and learning professionals about measuring the business impact of their programs can be a difficult conversation. It seems everyone except pollsters and data scientists hates statistics, and people don’t get into HR work because they love math.
In our modern world, we use statistics to inform, impress, persuade, frighten, and manipulate people. News organizations use polling to create news so they can report on it. A Google Trends Search on “I hate statistics” indicates that the deluge of polling statistics related to the 2016 U.S. presidential election may have caused an increase in search traffic. Yet when we study reactions to statistics, we find that citing them, even with spurious and irrelevant numbers, increases the trust level of an audience.
In today’s business environment, we are expected to have enough understanding of measurement and statistics to evaluate our programs and activities. Our CEO wants to see impact on the business. The CFO wants to know what we are doing is showing a return on investment. We need to know if our programs are effective.
We want to help you measure the impact of HR programs and activities without busting your budget, hiring a gaggle of data scientists, or measuring everything.
Discomfort in measuring comes from misunderstandings and myths of measurement. In his popular book How to Measure Anything, Douglas W. Hubbard explains three misconceptions that lead us astray:
Today’s article is about understanding how estimate helps us make better decisions. We will discuss the object and methods of measurement in the following articles.
When you ask people to define measurement, most will respond with thoughts of precision or an exact calculation. But in the practical worlds of science, mathematics, and business, measurements are approximations. If science depended on exact precision, we would not have been able to land men on the moon. If business leaders needed pinpoint accuracy, they would never make a decision.
The purpose of measurement in business is to make better decisions. For example:
In every one of those examples, an exact number would be impossible or impractical, but an approximation will help make a better decision.
Suppose we survey 300 managers to see if a learning intervention improved performance but only 120 respond. How confident are you that a particular response, chosen by 60% of respondents, reflects the entire population? For a yes/no question, your confidence might be 50%. For multiple choice with five answers, your confidence might be much lower.
Using a confidence interval calculation, we can be 80% confident in the response with a confidence interval of 5.73%. That means we have between 74.27% and 85.73% confidence that 60% of the respondents would choose the same answer. How does that match up to your guess?
Will you be more certain or less certain you want to continue that part of the program? Will the estimate help you decide?
With a little bit of study, a good data analyst, and some help with asking the right questions, you can measure anything--not with precision, but enough to make better decisions.
In a later article, we will show you how selecting only five random examples from a population size can increase the uncertainty of a decision.
If you need to brush up on measurement and statistics, try I Hate Statistics online learning. If you want to explore how ridiculous and funny statistics can be, check out Tyler Vigen’s Spurious Correlations. Who knew per capita consumption of mozzarella cheese correlates with the number of civil engineering doctorates?
References:
1. Hubbard, Douglas W. How to Measure Anything: Finding the value of “INTANGIBLES” in Business, 3rd ed. P, 29. John Wiley & Sons, Hoboken, New Jersey, 2010.