Jeff: "So I have a great example of, one of our warehouses wanted to save some money and invented a new kind of divider in between inventory on a shelf, and this divider was made of cardboard, which was inexpensive.And they installed these dividers across the whole portion of the warehouse.They were very proud of the work, and we were proud of their scrappiness. And unfortunately though, after a couple of months, we saw inventory defects spike in this part of this particular warehouse. We went back to do some deep dive analytics and inspection to understand why. And it turned out that as pickers were removing items, they were bumping the items next to them and slowly they would flatten some of the cardboard. And so, items from one bin were drifting into another bin. And when we assigned an inventory checker to go out to check to see if the item was there, it was no longer in the place it was supposed to be. It was in the one next to it, and that counts as a defect. Because when a picker comes, they're only looking in the zone where the software tells them to pick. If it's not there, they note it as a defect and move on. So we actually were introducing more customer defects because of this change that was made to the process."

Using a 95% confidence level, calculate your best estimate of the true defect rate of storage type 1,2, & 3

Based on your analysis and the information from Jeff Wilke, which storage type do you think uses the cardboard divider? Why? What is the true defect rate of the inventory separated by the cardboard dividers?

Let's analyze the inventory sampling data Amazon collected after the implementation of cardboard dividers. In particular, let's construct confidence intervals to estimate the true inventory defect rate for each of the three different storage types at the warehouse. One of these storage types uses the cardboard divider. Amazon sampled 5,000 observations from each of the three different storage types and recorded "1" if there was a defect in the bin and 0 if there was not. The mean defect rate and standard deviation for each storage type are provided below. A 1 2 B D Storage Type 1 Storage Type 2 Storage Type 3 0.0298 0.0326 0.0586 0.1701 0.1776 0.2349 5,000 5,000 5,000 Mean 3 Standard Deviation 4 Sample Size 5 6 Lower Bound 7 Upper Bound 2.51% 3.45% 2.77% 3.75% 5.21% 6.51% Let's analyze the inventory sampling data Amazon collected after the implementation of cardboard dividers. In particular, let's construct confidence intervals to estimate the true inventory defect rate for each of the three different storage types at the warehouse. One of these storage types uses the cardboard divider. Amazon sampled 5,000 observations from each of the three different storage types and recorded "1" if there was a defect in the bin and 0 if there was not. The mean defect rate and standard deviation for each storage type are provided below. A 1 2 B D Storage Type 1 Storage Type 2 Storage Type 3 0.0298 0.0326 0.0586 0.1701 0.1776 0.2349 5,000 5,000 5,000 Mean 3 Standard Deviation 4 Sample Size 5 6 Lower Bound 7 Upper Bound 2.51% 3.45% 2.77% 3.75% 5.21% 6.51%