Distributed lag

Imagine you want to know how much ice cream you will sell next month depending on the temperature today. You decide to keep track of the temperature every day for the next month.

However, you realize that not everyone will buy ice cream immediately after the temperature changes. Some people might wait a few days or even a week before deciding to buy ice cream. This is called a lag, which means there is a delay between the cause (temperature) and the effect (selling ice cream).

But how do we account for this delay in our analysis? That's where distributed lag comes in.

Distributed lag is a fancy term that means we are taking into account the lag between the cause and effect by spreading it out over time. We assume that the effect of the cause (temperature) is not just immediate, but it can continue to have an impact over time. So instead of just looking at the temperature today and the ice cream sales tomorrow, we look at the temperature today and ice cream sales over the next few days or even weeks.

This helps us get a better understanding of the relationship between temperature and ice cream sales because we are not just looking at immediate effects, but also the delayed effects.

In summary, distributed lag is a way of accounting for the delayed effects of a cause by spreading it out over time. It helps us get a more accurate picture of cause and effect relationships.