Data collection involves taking measurements, and this seems like a simple thing when the subject is relatively simple. However, even the simplest of cases has the potential to be messed up. I found this out the hard way once. I hope sharing it helps you avoid a similar experience.
Experienced researchers and quality practitioners know they need to verify that a measurement system provides valid results. For instance, you can use Minitab’s Gage R&R study tools and the Gage linearity and bias tool to determine whether your measurement system is accurate and precise from a statistical standpoint. Using these tools helps you trust your data, and if you can’t trust your data, you can’t trust your results.
But before we even begin to assess the measurement system itself, we need to consider three even more fundamental questions:
If the answer to any of these questions is “yes,” the accuracy and precision of your instruments doesn’t matter. You’ll either obtain bad measurements, or accurate measurements for something that you didn’t intend to measure.
That’s exactly what happened to me. I’ll explain in my next post how you can get problematic data even when you use a “gold standard” measurement system.