Standard work is simply the best way to do a particular task or a process. ‘best’ means consistent, meeting customer requirements, efficiency, and safety. Standard work is a philosophy of continuous, on-going improvements and it should be included in all work areas.
A mathematical method that employs probability theory for inferring the properties of a population parameter from which the sample is taken is known as inferential statistics. Inferential statistics is a set of methods used to make generalizations, estimations, or predictions. Example: If determining the statistical capability of a process, we would take periodic samples of parts from a process and from these samples we would make inferences about the performance of the whole population of parts produced by the process.
Statistical Process Control (SPC) is a process improvement methodology to monitor, control, and continuously optimize a process. SPC is really a subset of six sigma. SPC is usually associated with control charts and design of experiments.
SPC separates common-cause from assignable-cause variation. The team identifies and removes assignable-cause variation and reduces common-cause variation around three targets – – nominal-is-best, larger-is-better, or smaller-is-better characteristics.
The steering committee is an upper management level team whose job it is to craft the strategic approach to process improvement.
Stem-and-leaf plots (also known as stem-and-leaf diagrams) are a valuable combination of a check sheet and a histogram in which the actual data values are recorded so that the raw data is maintained and the distribution of the data is also obvious for all to see. The data are divided into leading digits (‘stems’) and trailing digits (‘leaves’).
In the war on waste, the team needs to understand the customer demand rate. Think of a metronome (the ticking, swinging tool used by musicians to maintain constant timing). The metronome can be adjusted to different beats per minute. Takt Time is similar to the metronome. The team can adjust the takt time if it knows the average consumption rate of customer demand. If the rate of making a product is slightly faster than the takt time, there is very little built up inventory; hence minimal waste. If however, if it team ignores takt time, they are in danger of not having enough capacity to keep up with demand or too much capacity will be produce stacked up inventory. If there is inventory, there has to be a place to put it. There is a cost associated with that space. If there is inventory, it also has to be moved. There is a cost associated with that movement as well, and so on.
A test statistic is calculated. The test statistic is compared to a critical value (found in a table). If the calculated test statistic is beyond the critical table value, the null hypothesis is rejected. If the test statistic is not beyond the critical value, the null hypothesis has not been rejected (i.e., failure to reject the null hypothesis)
This type of testing using a test statistic is used in the f test, the t-test, and the chi-square tests.
Considering that a lean Initiative concentrates on reduction of waste and continuous flow, a team needs to understand the theory of constraints concept. Once the most constraining step in a process has been identified by the team, the idea of theory of constraints is to exploit this constraint to find ways of speeding up that particular step. Once that step has been optimized, the team will find ways to refine the next slowest step, exploit the step, optimize the step, and the process repeats until it’s no longer economical to refine any further.
SWOT Analysis is a methodology for the team to explore the Strengths, Weaknesses, Opportunities, and Threats of an item, or area of interest.
When a team is faced with a condition where they only have available to them small sample sizes (< n = 30) and they want to find the difference between two means, they would use a t-test based on the t distribution. (also known as student t distribution). To compare the difference between two means using a t-test is much like the method for using larger samples, however for small sample sizes; we need to use the t table for critical values instead of the Z table for the normal distribution. So, samples >30, use the Z table. For samples <30, use the t-table. Refer to the lecture for more on this.
