Statistical process controls are a more scientific way of determining whether a metric is behaving normally. However, if you want to be more rigorous, you can employ statistical process controls. Often, like with the example above, a quick look at the shape of the data over time will tell you if your spike is normal. By looking at the trendline over time (in this case, over the past month), the manager can see that this spike is completely normal. They’ve noticed what looks like a spike in their data.īut that’s because this metric carries a lot of variance, especially when calculated each day. In the example below, a Customer Success Manager is looking at the average first response time over the past week. Have there ever been spikes this extreme before? Is the current spike consistent with any wider trends? Ask yourself: how does the metric usually behave? Is it usually steady, or does it carry variance? (In other words, does it jump around a lot?)Ī simple way to check this is by looking at how the trend changes over time. Sometimes we see irregularities in data that are, in fact, completely normal. Prioritize your investigations, or give them an appropriate time frame. Smart leaders choose to focus on the metrics that matter. And living in the ‘era of big data’ doesn't mean you have to be across every data point. Of course, curiosity is a valuable quality for anyone working with data – but so is efficiency. Remember that not every anomaly requires detailed investigation. Scenario C: There wouldn’t be any significant consequences. Schedule a time to investigate the issue (and make sure you follow through.) If you responded to every blip in your data immediately, you would never get anything else done. Scenario B: It’s significant, but doesn’t need urgent attention. Remember to clearly communicate to others the extent to which you have been able to verify the data. Respond to the issue as if it was genuine, but also begin the process of investigation. It’s potentially a critical issue, so you may need to begin a parallel process. Scenario A: It’s significant and needs urgent attention. How urgently would they require attention?.Ask yourself: if this spike was genuine and represented a real-world change: This makes sure we respond to the most important issues quickly, without unnecessarily distracting ourselves from our current priorities. Is this metric important?īefore investigating any data anomaly, it’s important to triage the issue. Instead, here are some simple steps to work through when you notice a spike in your data. And depending on which it is, you may be feeling a strong urge to pop the champagne or hit the panic button.īut as we know, data can be deceptive, so don’t jump to conclusions just yet. Now, obviously, I have no way of knowing if your y-axis represents something really good (like new customers) or something really bad (like system errors). Or if you’ve caught it early, it might even look something like this: Maybe your trendline looks something like this? So, you’ve just noticed a spike in your data.
0 Comments
Leave a Reply. |