I would like to generate two control charts to monitor waste produced on the shop floor.

Situation 1
The first control chart is to monitor the amount of waste produced at a set up. Unfortunately, due to the nature of the process, set up waste in unavoidable. So I would like to generate a control chart to monitor the amount of set up waste produced and highlight special cause variation. I would like to do this by machine, by job.

I have a fair amount of historical data and the waste is weighed (KG’s) so it should be relatively accurate.

When I look at the data in mini tab it is non-normal and as one would expect it is very much skewed to the right as it includes common and well as special cause variation.

What control chart should I use? (I-MR?) and what do I need to do to the data in order to calculate the control limits please?

Situation 2
During the production run, we also produce ‘Run’ waste, which we also weigh at regular intervals. As the process is continuous, we report the total amount of KG’s waste against the total amount of KG’s made.

Again, what control chart should I use and how should I calculate the control limits using the data already collated? I thought of doing a p-chart but I’m not sure.

Any help would be much appreciated!

I would like to generate two control charts to monitor waste produced on the shop floor.

Situation 1
The first control chart is to monitor the amount of waste produced at a set up. Unfortunately, due to the nature of the process, set up waste in unavoidable. So I would like to generate a control chart to monitor the amount of set up waste produced and highlight special cause variation. I would like to do this by machine, by job.

I have a fair amount of historical data and the waste is weighed (KG’s) so it should be relatively accurate.

When I look at the data in mini tab it is non-normal and as one would expect it is very much skewed to the right as it includes common and well as special cause variation.

What control chart should I use? (I-MR?) and what do I need to do to the data in order to calculate the control limits please?

Situation 2
During the production run, we also produce ‘Run’ waste, which we also weigh at regular intervals. As the process is continuous, we report the total amount of KG’s waste against the total amount of KG’s made.

Again, what control chart should I use and how should I calculate the control limits using the data already collated? I thought of doing a p-chart but I’m not sure.

Any help would be much appreciated!


Since your percentage is based upon weight, you should stick to I-MR or xbar-R. P-chart would be inappropriate because the P-chart is based upon a series of go-no go results. Your kilogram units don't match this situation - you don't decide if each kilogram is good or is scrap. An item scrapped may weigh a fraction of a kilogram, or many kilograms. IF you had a count of parts that we declared "good" versus sent back for "waste" you could do a p chart.

Since your percentage is based upon weight, you should stick to I-MR or xbar-R. P-chart would be inappropriate because the P-chart is based upon a series of go-no go results. Your kilogram units don't match this situation - you don't decide if each kilogram is good or is scrap. An item scrapped may weigh a fraction of a kilogram, or many kilograms. IF you had a count of parts that we declared "good" versus sent back for "waste" you could do a p chart.

Hi Steve, thanks for the reply.

So I should use an I-MR in both cases then I take it. Do I need to do anything with the data in order to use it to calculate the control limits, as it has special cause variation in it and it isn't normal.

As discussed in other threads here on the Cove, control charts do not depend upon normality for their operation. The I-MR will work fine with non-normal data for both cases.

As discussed in other threads here on the Cove, control charts do not depend upon normality for their operation. The I-MR will work fine with non-normal data for both cases.

Thanks for the help.

if you are unsure of your results don't hesitate to post your data here with your questions...