Introduction
The Process Improvement Plan entailed regular steps with the aim of finishing a given duty. Throughout week one, getting ready for classes in time was an exhausting procedure that the student required minimal time to do. They regularly gathered data exhibited bottlenecks in the process. The theory of constraints overcame the difficulty leading to the beginning of the improvement process. This paper, therefore, uses statistical process control to define control limits, confidence intervals, and seasonal factors using the data gathered from day one.
Morris & Ha (2002) noted that Statistical Process Control was a production standard method for computing and controlling quality in the course of producing goods and providing services. Attribute data and measurements collected from the goods during the production process. Through setting up upper and lower control limits, differences in the production process were noted prior to resulting in defective products, thereby eradicating the requirement for final inspection of the goods.
According to Kanji & Arif (2010), the data gathered during the production process was plotted on a graph that had preset control limits. The control limits were determined using the capability of the process while the specification limits were determined by the consumer’s requirements. The Lower Control Limit line was noted as a line that illustrated the average less three standard deviations of the last fifteen to thirty days of data collection. He further defined the Upper Control Limit line as a line used to illustrate the average in addition to three standard deviations of the last fifteen to thirty days.
Statistical Process Control calculated the control limits through the use of an iterative calculation process. The iterative calculation process utilized in the provision of control limits reflected only the Common Cause examples.
Statistical Process Control also determined the control limits through the utilization of all the models in the control set and then evaluated every model to the control limits. Any sample that fell outside the control limit was done away with from the calculation and the statistical process control would reevaluate the control limits using the other models. The procedure would go on until all the models were within the control limits or to such a moment that nearly half of the models were removed from the calculation. The anomalous sample points were removed and disregarded in the control limit evaluation.
Seasonal Factors
According to Yu (2007), seasonal factors were connected to given durations of time marked by a given activity. In other words, these factors were short-term behaviors within the anticipated data as a result of a given duration of time. Even though the implementation process of minimizing the time taken to get ready for class took place during the first week, a seasonal factor pushed a data point out of the control limits.
The general temperature was the seasonal aspect that negatively affected the overall time taken to get ready for the classes. The classroom and outside temperatures dictated the type of clothing worn by the student. On warm days the student chose to wear shorts and as a result reduced the time taken to get ready for the classes as compared to the cold days.
Confidence Intervals
Morris & Ha (2002) noted that uncertainty was an assessable approximation of error that was found in all process performance data gathered. Computing the confidence interval was a tactic that was mainly applied in the removal of uncertainty. The confidence interval was also used in obtaining the approximated scope of values around the mean to articulate how exact the evaluation was. Confidence intervals presented three main factors applied in the computation, thus, the standard error, the mean, and the z value. The assurance level determined the amount of confidence interval.
A confidence interval of 99% would be very narrow in comparison to a 95% interval that depicted a larger confidence level. The overall number of the data points is considered an essential factor for the computation of the confidence intervals. Fewer data points would result in a wide range thereby resulting in difficulty in identifying the exactness, that is, a larger number of data points narrowed the range thereby making the data collected more important.
Conclusion
In conclusion, I would like to note that every given process comprises routine steps with the objective of finishing a given task. Throughout the first week, getting ready for the classes each morning, in a timely way was such a demanding process that the improvement plan wanted to utilize minimal time carrying out. Data gathered on a daily basis and analyzed at the end of the third week depicted a bottleneck that was in existence within the process.
In spite of this, the application of Goldratt’s theory of constraints overcame the difficulties that were present in the process, and the process enhancement process began. As a result, the paper utilized statistical process control to explain the control limits, seasonal factors that affected the data gathered, and the confidence intervals and their importance based on the number of data points using the data gathered from the first week.
References
Kanji, P. G., & Arif, H. O. (2010). Statistical Process Control. Friendswood, Texas: Wisdom House.
Morris, R. K., & Ha, W. T. (2002). The Book of Statistical Process Contro. Orland Park, Illinois: American Technical Publishers Limited.
Yu, L. (2007). A Statistical Process Control Approach to Cycle Counting for Retail Environments. Ann Arbor, Michigan: ProQuest,.