Last week we talked about normal distribution in your data. This week let’s kick the conversation off with non-normal distribution. There are a few different types of non-normal distribution, let’s take a look.
Skewed data is quite simply, a data distribution that is not symmetrical. Usually the longest tail points should point in the direction of the skew. Here’s what a skew looks like
Natural limits-these are the limits of sample size. The problem with natural limits is that these natural limits can bias the estimation of results and in some cases ensure that there can be no specific correlation between the sample and the data field.
This is also known as artificial limits and it’s important to realize that limits are imposed by the person analyzing the data. Basically artificial limits set an arbitrary point for acceptable and not acceptable. Say you make 40 chairs and hour, your designer decides that any chair that doesn’t make a rating of 80 is unacceptable. That acceptable rating is completely arbitrary based on the designer’s standards.
Mixtures occur when data from different sources is expected to be the same and is different. Say you’re looking for error data from two cashiers Shift A credit card receipts and Shift B, cash receipts and the skew is not the same. You were expecting the error rate for each method to have a normal distribution and what you got showed something like this.
Next week we will pick up with a continuation of non-normal distributions. Until then, Happy analyzing
First Time Yield (FTY) is a traditional metric that tells you how many defects your process produces for before any improvement is done. Generally this measurement is used in the manufacturing or production field, but it can make the switch to your office easily. The formula for FTY is:
FTY: Total Unit Passed/Total Units Tested
So if you work at a membership organization and you processed 120 retirement requests and found that 50 requests were entered incorrectly, our FTY is .58 %. 70 is the total number of request entered correct or passed and the total number of units tested is 120 retirement requests.
If your process has multiple measurement areas, you will need to perform a FTY for every measureable step in the process. The great about FTY is that it is one of the simplest metrics in 6Sigma and it creates a create illustration of the current state of your process
What does it look like?
A FTY can look like any typical graph you have seen, but most will resemble the chart below. My fancier ones include the curve illustration for clients that highlight the cost of these errors to the client and how the improvements will be quantified.
What doesn’t FTY do?
FTY is a great place to start, but it is important to understand its limitations. FTY will not measure rework or provide any accounting for the cost in time or resources for that rework. There is a more accurate method for measuring that, Rolled Throughput Yield, which we will cover next week.
FTY is a great foundational measurement piece and a great way to introduce your company to 6Sigma, in a way that makes a lot of sense to the people doing the work.