Screenshot_20231113_001253_com.google.android.apps.docs

A .l = 0.00K/s 97% &) 12:12 AM & Individual Assign... [@ &% Individual Assighment Guideline MGT 314 *Read the 2™ page for specific guidelines and submission deadline Q1. Rolls of coiled wire are being monitored. A special sample containing 20 rolls has been examined, and the number of defects per roll are to be recorded in a table. Go to ChatGPT, then enter “Generate a dataset of the number of defects per roll observed in 20 rolls of coiled wire”. Copy the generated data values to Microsoft Excel, with the headings being “Observation” and “Number of Defects”. Then using the data values, answer the following questions. (a) Plot the values on a control chart using three standard deviation control limits. [2] (b) Is the process in control? [1] (c) Using z = +2, analyze the data of the “number of defects” using a median run test and an up/down run test to determine if the data is truly random. 2] Q2. 30 samples of defective coils are inspected, with each sample containing 20 rolls of coiled wire, and the number of defective coils in each of the 30 samples are to be recorded in a table. Go to ChatGPT, then enter “Next, generate a dataset of the number of defective coils observed in 30 samples of coiled wire, with each sample containing 20 rolls of coiled wire”. Copy the generated data values to Microsoft Excel, with the headings being “Sample” and “Number of Defectives”. Then using the data values, answer the following questions. (a) Construct and plot a control chart that will describe 99.74 percent of the chance variation in the process when the process is in control. 2] (b) Determine whether the process is in control. [1] (c) Using z = +2, analyze the data of the “number of defectives” using a median run test and an up/down run test to determine if the data is truly random. [2] Q3. In Q2, one sample was inspected every day, and it took 30 days to inspect the 30 different samples. Now, the number of defective coils found in a sample of 20 rolls of coiled wire are to be forecasted on the 31st day, using the data already generated in Q2. (a) Forecast the number of defective coils using exponential smoothing, with a smoothing constant of 0.10, and a naive forecast (actual value) of day 1 as the forecast of day 2. [2] Forecast the number of defective coils using a linear trend equation. Plot the forecasts of both (a) and (b) together on a single graph. [3] The actual number of defective coils on the next day is found by going to ChatGPT and entering “Next, generate the number of defective coils observed on the next (31st) sample of coiled wire, with each sample containing 20 rolls of coiled wire”. Using this value, the previously generated actual values, and the forecasted values from both methods in (a) and (b), compute MAD, MSE and MAPE for both set of forecasts from day 2 to 31. Which forecast appears to be more accurate according to each of the forecast accuracy measurements? [3] Plot control charts of errors for both forecasts in (a) and (b) with 2s limits, and determine whether each of the forecasts are working. [2] (b - - (c (d - Answer all three questions on a single Word Document. Word Document. e For Q3, take screenshots for both forecasts showing the actual values, forecasted valu and error, and paste it on the Word Document. e Take screenshots of all graphs and control charts plotted on Excel and paste it on the Worw Document according to each question. e The auestions that reauire calculation (exceot forecastine values and forecast accuracv e ForQland Q2, take screenshots of the generated dataset sheet on Excel, and paste it ?/ D