Trends in e-commerce
Sorry, FRED, not back to "normal."
The FRED blog has a graph like the one in Figure 1 and states (emphasis mine):
The FRED graph above shows the evolution of e-commerce as a proportion of total retail sales. It’s no secret e-commerce has become more prominent and that it boomed during the pandemic, when access to retail premises was restricted. So, what’s the economic lesson here?
First, it’s important to realize that any particular economic activity measured as a share of an aggregate economic activity cannot grow indefinitely in any significant way: It can never go above 100%. Given that, we would expect the share of e-commerce to level off at some point. Has it?
What we do know is that e-commerce is back on its pre-pandemic trend, after a temporary bump in early 2020.
Other than this graph, FRED doesn’t provide any evidence that e-commerce sales are “back on its pre-pandemic trend.” There are two questions here that are worth exploring. What was the pre-pandemic trend, and when do we stop that trend to see if we are back on the trend? Now, this isn’t the world’s most critical issue, but I think exploring the ideas here is generally relevant and transferable to other situations.
Step 1. Figure 2 looks at two possible trends. A linear trend (blue) and a quadratic trend (red). The trend lines use the data up to and including the data from the fourth quarter of 2019. Two things seem clear here. First, the pre-pandemic trend was not linear, while the quadratic trend appears to be a good fit. In both cases, the trend lines are well below the last data point, which is the fourth quarter of 2023.
Creating trendlines with data stopping at the fourth quarter of 2019 may be too soon. Figure 3 shows the quadratic trend we get if we stop the data in the first quarter of 2020.
The quadratic trendline in Figure 3 helps us see that the uptick in e-commerce sales started at the end of 2019. We also still have a noticeable gap in the last data point between the actual sales and the trendline. Based on this stopping point and trend, e-commerce sales are certainly not back to pre-pandemic levels. Let’s be really generous and use data through the first quarter of 2020.
Figure 4 creates the quadratic trendline with data including the second quarter of 2020, which is the peak of e-commerce sales. If you use this trendline, then sure, e-commerce sales are back to the pre-pandemic trend. But if we look carefully at the trendline in Figures 3 and 4, we can see how that last point, which is an outlier, really pulled the trendline upwards. My post, Regression leverage and influence, part 2 (2/17/2024), demonstrates this idea with an animation.
I would argue that we stop using data at the first quarter of 2020 (Figure 3) and not the second quarter of 2020 (Figure 4), in which case e-commerce sales have definitely not returned to pre-pandemic trends. I disagree with the conclusion put forth in the FRED blog, and they need to do better to back up their claims.
Please share and like
Please help me find readers by forwarding this article to your friends (and even those who aren't your friends), sharing this post on social media, and clicking like. If you're on Twitter, you can find me at BriefedByData. If you have any article ideas, feedback, or other views, please email me at briefedbydata@substack.com.
Thank you
In a crowded media market, it's hard to get people to read your work. I have a long way to go and I want to say thank you to everyone who has helped me find and attract subscribers.
Disagreeing and using comments
I'd rather know the truth and understand the world than always be right. I'm not writing to upset or antagonize anyone on purpose, though I guess that could happen. I welcome dissent and disagreement in the comments. We all should be forced to articulate our viewpoints and change our minds when we need to, but we should also know that we can respectfully disagree and move on. So, if you think something said is wrong or misrepresented, then please share your viewpoint in the comments.