Welcome back, guys. I'm Katherine MK Iver, and this is your lean six Sigma green belt. We are going through the last of our hypothesis testing type modules and we're going to discuss probably.
So I want to introduce the idea of probability to you because it is a factor in our hypothesis. Testing on that is really when we talk about probability as part of hypothesis, testing were starting to push into black belt land. But I want you to be aware of the concepts behind it.
So probability is, and on Lee, the likelihood of something happening. Why we care about it and lean six Sigma is because when we want to look at the probability that our intervention is, in fact
what is changing the process
so we can look at both positive and negative, which starting to talk about statistical process control When we start, we talked a lot about our normal distribution being very important in stable companies because it gives us a sense of where the data should fall and it tells us what type of variation it is.
is both twofold. What is the probability that our solution is in fact being beneficial. And what is the probability that we're going to see ex whatever that number is result in comparison to our mean on our normal distribution.
So those statistics 34% an additional 13% plus or minus above or below are mean
gives us the probability that the number that we're looking at it falls in that range. So that's that's how it ties together with your distribution. We care about it because it's a measure of confidence. So you've heard when you watch the news or you've read studies,
you've heard the confidence interval.
The probability tells us, at what percentage are we confident that this value is correct? So if we're looking at the 95 percentile were saying that the number that we are reporting is within 95% or two standard deviations of the mean.
So we feel really confident
that the number that we're looking at is within that range. It's a measure of confidence. It can also indicate your level of waster variation. More specifically, variation that we do know that variation is a preclude er to waste. Um,
when you're looking at your probability, if you have numbers that are popping in your two standard deviations or three standard deviations from the mean
you know that you need to do an intervention. But really, at the end of the day,
we care about this because it gives us a sense of security and the solutions designed Probability is how we counter act to the fear of the Hawthorne effect. And why we're afraid of the Hawthorne effect is because one day the boss won't be watching.
So then we have to ask ourselves, Are solutions really effective? Probability tells us
so. The easiest way that I can remember why I care about this is it's your hand of poker. So you study probability because you want to know what is the likelihood that the hand that you are going to play is the best solution out of your options in your hand.
So that's why we study probability. We're looking for the likelihood that this is the best solution we're going, Of course, take all of the data that we collect. That's how we're going to be able to derive it.
When we get to Black Belt, I'll tell you more about how to calculate it. If you're super excited. Your Excel Data analysis pack does have some probability functions. In any time you do a statistical analysis within it, you will get a P value, which is a probability function.
So today we went over and over you. We talked about why it was important, why we care. And we understand that it's the last piece of our hypothesis development and testing where not only are we saying yep, there is, in fact, a statistical significance were also saying
This is how likely it is that it's going to happen.
So with that, we're going to switch over to regression analysis. So we're gonna look at our hypothesis tests that relates to relationship, So I will see you guys there.