Please enable JavaScript.

Coggle requires JavaScript to display documents.

Chapter 21 - Coggle Diagram

- - - - The alternative hypothesis is the statement the team is trying to prove is true, usually that a specific change or difference is present
        
        Teams must choose a confidence level usually 95% which sets the alpha risk at 0.05 this represents the small risk of saying something changed when it actually didn't
- - - - If the P-value is high more than 0.05 the team fail's to reject the null and concludes there isn't enough statistical proof to say anything changed
        
        This math helps teams move from guessing to knowing for sure
        
        Using software like minitab allows teams to get these results quickly without having to perform hours of complex, manual math by hand
- - - - The 2-proportion test is used when you want to compare two different groups to see if one has a better rate of success than the other
        
        An example of a 1-proportion test is checking if a specific classroom has a higher failure rate than the average rate for the rest of the shcool
        
        These tests are common because they help prove if a process changed actually reduced the number of errors or "defects" reaching the customer
- - - - The 2-sample T Test compares the averages of two totally separate groups, such as comparing the productivity of two different legal teams
        
        The paired T Test is a special version used to compare the exact same group before and after a change was made to the process
        
        The Chi-square test is used when teams want to compare how much the data spreads out rather than just looking at the average
- - - - The mann-Whitney Test is used to compare the medians of two different groups to see which one performs better
        
        Using the wrong test- such as a normal test on non normal data can lead a team to draw the wrong conclusions and make bad business decisions
        
        Teams usually run these tests in the analyze or improve phases to verify if their theories about root causes or solutions are actually correct