Time is always moving forward making it difficult to execute daily processes slowly. Travelling is a daily process that takes much time and resources. Time spent on travelling can be known as waste time as the main goal is to transport from point A to point B without analyzing or performing actions on other tasks. Multitasking is not advisable meaning a high focus should be on the road and other road users plus it is illegal. The process if done as quickly as possible can reduce the cycle time leaving extra time for more profitable processes. The activity to drive from home to office is graphically shown below in the form of a flowchart.
Currently time taken to execute the activity is not efficient. Certain processes are occupying heavier proportion from the total cycle time. A process improvement plan is drawn not only to analyze and reduce current time but also not forgetting to achieve a safe trip.
Statistical Process Control
Data below tabulates five weeks of travelling time from home to office. The next step is to deduce whether the data is efficient by running a test. Statistical process control (SPC) tests random samples from processes to determine the productivity is perfectly efficient (Chase, Jacobs & Aquilano, 2006). The test graphically depicts the upper control limit (UCL) and lower control limit (LCL) of each the average mean and average range graphs. Average of time taken and range from each week in combination with the range and average factors are requirements to calculate both limits. Graphs with the limits first, plot the weekly average mean and average range. Observation is made from the graphs to decide on whether or not all sample data is within the control limits. The sample data that either is higher than the UCL or lower than the LCL will be the overuse time. Value of data is not only under observation but also the pattern of the chart is also under monitoring. The pattern of a stable chart is sample data closely plotting around the mean data. Patterns that exhibit an increase toward the UCL or decrease toward the LCL or erratic behavior must undergo investigations (Chase et al., 2006).
The both chart depicts that the average of total time and range is within the UCL and LCL. The observation only concludes that the current data is allowable but not perfectly efficient. The pattern of the data in the average mean chart depicts a run of three plots above central line. The practice to avoid the first week’s traffic congestion is to leave from home reaching office exactly at 9.00 a.m. The second and third week changes practice as work is piling up and requires more setup time.
The pattern of the data in R chart depicts an increase. The final plot reaches a range nearly to the UCL. The reason is the zero value recording of total cycle time on Monday.
The data above is in normal tabulation manner meaning no trips involving external variables or environmental factors intervention is taken into consideration. External variables present itself in seasonal or cyclic durations. The latter is easily taken into consideration as the operation time is constant but the former makes it harder to analyze any given length of duration. Seasonal usually associates with duration of the year involving particular activities (Chase et al., 2006). The trip from home to office is under different seasonal influences.
The fasting period of the Muslims is a major influence in the trip. Traffic is much lighter not only for the trip to the office but also from the office especially on the weekends.. Vehicles on the main route and highway are less reducing driving time. The drive is much smoother requiring less petrol eliminating the duration to drive to the petrol station and fill petrol.
Holiday’s season is another major influence in the trip. Academic institutes such as schools, colleges and universities are undergoing final examination. Institutes deem holidays reducing the morning. Vehicles belonging to school bus drivers, college or university students and instructors reduce allowing working adults to use the routes and highway freely. The current assumptions are made relying on past personal experience of the last five years.
Finally observation relying on past personal experiences has shown that in the initial week traffic is at the highest at peak hours but reduces by the end of the month. Employees tend to stay late at office at the final week of the month mostly because of the need to complete monthly closing reports. Amount of cars reduces as the weeks run in a monthly cycle.
Total cycle time needs to be as less and independent as possible. Cycle time that easily reacts under any influences will make decisions harder to conclude as observations are not consistent. Seasonal factor is the adjustable correctional value in a given time series of the season of the year. The table below records the seasonal factor that adjusts the next month’s cycle time to 300 minutes comparing to the current 347.14 minutes.
Confidence intervals are brackets that the true population occur base on the confidence levels (NIST SEMATECH, n.d., para. 2). 95% is set as the confidence level for the above data. The sample size is below 15 and the chart below depicts the distribution of average mean for the five weeks being normal (University of Phoenix, 2010, Estimation and Confidence Intervals, p. 305).
The distribution scale put to use is the t-distribution satisfying the above conditions. The interval that encloses the true population parameter in a 95% confidence level base on the current data is from 61.98% to 79.57%.
The process undergoing the plan records a nearly stable result from the (SPC) within the control limits, producing seasonal factors for next month forecast and nearly a high confidence interval for its confidence level. The process is still open for modifications as the plan has point out areas for improvements. The SPC pattern’s requires the data to be graphically stable, the average mean are not to be heavily leaning against the seasonal factors and the confidence interval must increase so that the quickest cycle time is achievable.
Chase, R. B., Jacobs, F. R., & Aquilano, N. J. (2006). Operations management for competitive
advantage (11th ed.). New York: McGraw Hill/Irwin.
NIST SEMATECH (n.d.). What are Confidence Intervals? Product and Process Comparisons.
University of Phoenix. (2010). Statistical Techniques. Retrieved August
21, 2010 from University of Phoenix, QNT 561 – Applied Business Research & Statistics