Decision Analysis Task3

A. Manufacturing the Samba Sneakers cost-effectively is very important for the organization. The best option for the organization would be to manufacture the sneaker with the lowest cost for every 1,000 sneaker produced

The options to manufacture are:
1. Recondition the existing equipment with fixed cost of $50,000, variable cost of $1000 for every 1,000 sneaker.
2. Buy New Equipment with fixed cost of $200,000, variable cost of $500 for every 1,000 sneaker.
3. Outsource with no fixed cost, with variable cost of $3000 for every 1,000 sneaker.
.

Based on volume output the best option to cost-effectively manufacture the Samba Sneakers would be to buy New Equipment with fixed cost of $200,000, variable cost of $500 for every 1,000 sneaker.
-Buying new equipment has the lowest cost option for a volume over 300 sneakers manufactured.
The breakeven points for each option are as follows:
BREAKEVEN POINTS Units Dollars
Reconditioned vs. New Equipment 300 350000
Reconditioned vs. Outsource 25 75000
New Equipment vs. Outsource 80 240000

However, buying New Equipment has the lowest cost according to the graph for volumes over 300 sneakers. (See Graph)

A1. A1a. The decision analysis tool to Buy New Equipment is the best fit for the organization. Buying New Equipment provides the lowest cost based on volume for producing the Samba Sneaker. According to the graph, Buying New Equipment would be more cost-effective for the organization based on volumes of output with a lower cost for the organization when compared to Reconditioning existing equipment or Outsourcing. Therefore, Buying New Equipment with fixed cost of $200,000 variable cost of $500 for every 1,000 sneaker is more cost-effective for the organization.

B. The future periods of sales are displayed for periods 10-21 along with forecasted sales for each period. Within the Least-Squares method the demand is equal to 85027.78 +3683.333 *Time the quarter the organization will be in. The Correlation coefficient for data lined up on a line is 0.891. Therefore, about 90% of the data can be explained by the equation of a line. The coefficient of determination is 0.795 which tells how well the model fits the data. The sales volume forecast for periods 10-21 will gradually increase from 121861.1 to 162377.8.
The exponential smoothing techniques using a smoothing constant for the average of 0.3 and a smoothing constant for the trend of 0.4 has a forecast for next period of 121620.4

B1. See Attached Spreadsheet for accurate copy of computer –generated output.

B2. The proper model to select for forecasting would be the model that minimizes forecast errors. Therefore, the model with the best results will be determined by its error measures. When comparing the Least-Squares method to Exponential smoothing techniques with trend for (MAD), (MSE), (BIAS), (STANDARDARD ERROR), AND (MAPE) the best model to would be the value with the lowest error. The lowest error would determine which model is more accurate over the other. MAD MSE BIAS MEAN ERROR Standard Error MAPE
Least-Squares Method 4183.951 23356180 -0.001 5479.907 3.945%
Exponential Smoothing with Trend 5142.629 51038600 4499.051 8100.683 4.67%
Lowest Error= Least-Squares Least- Squares Least- Squares Least-Squares Least-Squares

Therefore, based on the model with the lowest error measures would be the Least-Squares Method. The least-squares method will be the chosen model to go with for sales forecasting for the organization.

C. Statistical Process Control (SPC) is the application of statistical techniques to the control of processes (Heizer|Render, 218 n.d.). Processes are measured on a Control Chart. Control Charts graphically represent the process of data over time (Heizer|Render, 218 n.d.). In order to improve the quality in the Shuzworld production, we must first determine what processes are within the control limits. According to the current Control Limits for Shoe Sole Height Sample, the chart shows what changes have occurred within the mean. Based on past data, the current control limit for the organization is 99.73% for this process, with the random selection of 16 soles over a 15 hour period for a size 10. Therefore, in order to improve quality we must set up control limits for sample means using standard deviation. The random selection of 16 soles we must find the overall mean to calculate its control limits.

The average length in the sample size can be determined by adding the lengths and dividing them by the total number of samples 10+10.3+10.2+10.1+10+10+10.2+10+9.9+10+9.8+10+10.8+10.6+9.7/15=10.11

The average mean of the samples size are 10.11

Now that the average mean size has been determined, we must determine the UCL upper control limits and the LCL lower control limits.

The UCL = x+zox= 10.375
The LCL = x-zox=9.625

Based on the UCL of 10.375 and the LCL of 9.625, samples that fall out of the range are consider to be out of control. The current Control Limits for Shoe Sole Height Samples are between 9.625 and 10.375. Some selections within the 15 hour period fall out the upper and lower control limits. The samples are out of control within the hours of 13 and 14. . As a result, the work for hours 13 and 14 should be examined to control limits.

Control charts allow the organization to randomly measure selected shoes to determine if the process are within the organizations control limits. Trends for the Control Limits for shoe Sole Height Samples include decreased trends between the hours of 2-5. The decrease goes from 10.3 to 10 between the hours of 2-5. Trends within the control charts for Eyeletting Fraction Defective discloses erratic behavior between operators 12-20. Fraction Defective range from 0 to 13, 13 to 0.06 etc. Trends for decrease dispersions, and erratic behaviors can be put back into control by setting clear and specific SPC policies for employees to follow. Some policies many include employees implementing a run test. A run test is a test used to examine points in a control chart to see if nonrandom variation is present (Heizer|Render, 231 n.d.).

References:
(Heizer|Render, 218 n.d.) Retrieved from http://wpscms.pearsoncmg.com/wps/media/objects/9447/9673736/heizer10_flash_main.html?page=230

(Heizer|Render, 231n.d.) Retrieved from http://wpscms.pearsoncmg.com/wps/media/objects/9447/9673736/heizer10_flash_main.html?page=230