Random Sampling at Receiving Inspection: A Practical Implementation needed

#1
Dear all,

I need some support in an implementation of random sampling at receiving inspection. During an ISO audit it was found that we do not have a proper randomization process in place and as a result there is a risk of sampling bias.

We have looked at ISO 24153 Random Sampling and randomization procedures. We have learned that there are various ways that we can use randomization procedures to assure that all products in a lot have approximately the same chance of being selected for inspection.

The challenge is how to implement this in practice. We receive goods in many different forms: boxed on pallets, trays in boxes of various sizes, loose parts in bags etc etc. We are now trying to understand how to map a list of random numbers onto the wide variety of packing methods.

Juran gives some suggestions (5th edition, 46.16) for systematically packed materials and for bulk packed materials but is not very explicit. My colleagues from stores are very concerned that we will end up with elaborate and complex procedures (me too).

I am certain that other Quality colleagues have resolved such issues in pragmatic ways. I would like to ask those people to comment on:

  • Do you have experience with random tables versus computerized random number generation?
  • Can you give examples of how you map the random numbers onto specific packing methods (e.g. do you use the same approach if you have a pallet with 5x5x5 boxes stacked or if you have a pallet with 10x6x15 boxes stacked?)
  • Which methods do you use for bulk items (Juran describes the use of a gridded board with small parts strewn onto the board)?
  • Are there any standard SW solutions available?
I can come up with solutions for all the above, but the concern is that the methods wil be complex (as there are many different packing methods and form factors), hard to handle by stores or QC personell and difficult to control.

Paul
 
Last edited:
Elsmar Forum Sponsor

Jim Wynne

Staff member
Admin
#2
Dear all,

I need some support in an implementation of random sampling at receiving inspection. During an ISO audit it was found that we do not have a proper randomization process in place and as a result there is a risk of sampling bias.

We have looked at ISO 24153 Random Sampling and randomization procedures. We have learned that there are various ways that we can use randomization procedures to assure that all products in a lot have approximately the same chance of being selected for inspection.

The challenge is how to implement this in practice. We receive goods in many different forms: boxed on pallets, trays in boxes of various sizes, loose parts in bags etc etc. We are now trying to understand how to map a list of random numbers onto the wide variety of packing methods.

Juran gives some suggestions (5th edition, 46.16) for systematically packed materials and for bulk packed materials but is not very explicit. My colleagues from stores are very concerned that we will end up with elaborate and complex procedures (me too).

I am certain that other Quality colleagues have resolved such issues in pragmatic ways. I would like to ask those people to comment on:

  • Do you have experience with random tables versus computerized random number generation?
  • Can you give examples of how you map the random numbers onto specific packing methods (e.g. do you use the same approach if you have a pallet with 5x5x5 boxes stacked or if you have a pallet with 10x6x15 boxes stacked?)
  • Which methods do you use for bulk items (Juran dscribes the use of a gridded board with small parts strewn onto the board)?
  • Are there any standard SW solutions available?
I can come up with solutions for all the above, but the concern is that the methods wil be complex (as there are many different packing methods and form factors), hard to handle by stores or QC personell and difficult to control.

Paul
What sort of ISO audit?

The fact is that not only is random sampling often impractical, it's sometimes unthinkable. There are times when there's just no feasible way to do it.

You have to think about risk, and ways to mitigate that don't involve you doing the suppliers' work for them. Do you have a lot of issues with NC things being accepted?
 
#3
Hi Jim,

Thanks for your reply. It was an ISO 9001:2008 audit with an observation against clause 8.2.4. I am happy to go back to the auditor and discuss limitations of implementing improvements against this observation, but I need to explore the complexity of possible solutions before I do so.

Paul
 

Jim Wynne

Staff member
Admin
#4
Hi Jim,

Thanks for your reply. It was an ISO 9001:2008 audit with an observation against clause 8.2.4. I am happy to go back to the auditor and discuss limitations of implementing improvements against this observation, but I need to explore the complexity of possible solutions before I do so.

Paul
What kind of ISO 9001 audit? CB, internal, customer? What does "observation" mean? Pinning that on 8.2.4 is a bit of a stretch.
 
#5
Hi Jim,

Our inspection process is working well. It is mostly AQL based and we have a QC team that is skilled to handle all required inspections. The issue is strictly on how to avoid 'judgement bias' in the selection of the sample to be inspected.

I was surprised to find elaborate ISO standards on the issue but almost no relevant discussions in forums on this topic.

Paul
 
#6
Hi Jim,

Let's say I am stuck for the moment with this observation from the ISO auditor. I have raised this question in this forum to get some help to explore the solution space. With that feedback I can decide to either discuss with the auditor or to start thinking about an implementation of random sampling.

Paul
 

somashekar

Staff member
Super Moderator
#7
Hi Jim,

Let's say I am stuck for the moment with this observation from the ISO auditor. I have raised this question in this forum to get some help to explore the solution space. With that feedback I can decide to either discuss with the auditor or to start thinking about an implementation of random sampling.

Paul
Statistics, sampling inspection and random sample will all work well, when you know that the parts for inspection are coming from a controlled process.
Some of the very good indicator for this controlled process are lot number / batch number / final packer details etc, that are present on your received parts label.
We always have parts in several bags, boxes, trays, cartons etc. We first identify such unique batch details and then pick random samples from any one pack if the consignment is from only one supplier batch. If there are more than one batch in the total supply, then random samples per the inspection plan are taken from one random pack of all such batches.
Please note that we apply the sampling plan as many times for one supplied lot when the lot consists of such many supplied batches.
This has worked for us and has detected defects in such bad batch supplied in a lot.
 
#8
Statistics, sampling inspection and random sample will all work well, when you know that the parts for inspection are coming from a controlled process.
Some of the very good indicator for this controlled process are lot number / batch number / final packer details etc, that are present on your received parts label.
We always have parts in several bags, boxes, trays, cartons etc. We first identify such unique batch details and then pick random samples from any one pack if the consignment is from only one supplier batch. If there are more than one batch in the total supply, then random samples per the inspection plan are taken from one random pack of all such batches.
Please note that we apply the sampling plan as many times for one supplied lot when the lot consists of such many supplied batches.
This has worked for us and has detected defects in such bad batch supplied in a lot.
We work in the same way. We do select our samples based on supplier lot and batch numbers using appropriate AQL tables. But this does not address the question. Allow me to quote from Juran (Quality Handbook, 46.16) under sampling bias:

Unless rigorous procedures are setup for sampling at random and/or by stratification, the sampling process can deteriorate into a variety of biases wich are detrimental to good decision making. The more usual biases consist of:
1. Sampling from the same location in all containers, racks, or bins
2. Previewing the product and selecting only those units which appear to be defective (or nondefective)
3. Ignoring those portions of the lot which are inconvenient to sample
4. Deciding on a pattern of stratification in the absence of knowledge of how the lot was made up
And one can easily see such biases at work: a stores person who always samples from the top layer of a pallet. A selection of corner boxes only. Selecting only even numbered trays etc etc.

I can setup a procedure that tells the operators to not do so, and develop guidelines and train staff. ISO 24153 however points us in a direction of using statistical methods to randomly select the samples.

So the question becomes: are the forum members aware of practical methods that can avoid the biases in sampling that Juran describes?

Thanks.

Paul
 
Last edited:

somashekar

Staff member
Super Moderator
#9
So the question becomes: are the forum members aware of practical methods that can avoid the biases in sampling that Juran describes?
People behavior is described in 3 of the 4 usual biases.
And one can easily see such biases at work: a stores person who always samples from the top layer of a pallet. A selection of corner boxes only. Selecting only even numbered trays etc etc.
Same here again.
There will be no any practical method for people behavior to avoid the biases in sampling except TRAINING and AWARENESS.
Keep blending this training and awareness with your daily practice to improve people behavior. When you do this well, then it becomes your rigorous procedures .......
 
#10
People behavior is described in 3 of the 4 usual biases.

Same here again.
There will be no any practical method for people behavior to avoid the biases in sampling except TRAINING and AWARENESS.
Keep blending this training and awareness with your daily practice to improve people behavior. When you do this well, then it becomes your rigorous procedures .......
Hi Somashekar,

Thanks for your answer. Your comments are spot on but I am going to be a bit stubborn here.

Wherever you look in literature you will find that we need to do RANDOM sampling in receiving inspection. And one can even find relevant ISO standards that describe how to randomize (a wide selection of methods is offered in this standard, I purchased it). When I search the internet and forums however, I can find close to nothing about a practical implementation of such methods!

Certainly, I need to train staff in the appropriate methods and assure that staff follows the governing procedure. But no training, in my view, can create a random sampling process such that all product in a lot have approximately the same chance of being selected. I would need some formal system to guarantee that.

I have been doing some searching in literature, Quality modules in e.g. warehouse management systems and ERP systems. I have not been exhaustive, but came up blank nevertheless.

So does this mean that we do not select random samples? Or that nobody has implemented ISO 24153? I do not want to assume that.

So the question remains: can forum members comment if they have implemented formal randomization methods (e.g. based on ISO 24153) in their receiving inspection?

Note: I understand the ISO procedure but am looking for experiences from other forum members on how to implement randomization when sampling from a wide variety of packing methods (boxes, pallets, bags, trays etc) that we see in daily life.

Paul
 
Thread starter Similar threads Forum Replies Date
M Stratified Random Sampling Calculations Statistical Analysis Tools, Techniques and SPC 1
A Random Sampling Statistical Analysis Tools, Techniques and SPC 10
G Sampling Question - Random Sample of 100 pcs and 11 pcs. have been rejected Inspection, Prints (Drawings), Testing, Sampling and Related Topics 30
S Random Sampling of Chickens Inspection, Prints (Drawings), Testing, Sampling and Related Topics 7
D How to perform Random Sampling Statement Inspection, Prints (Drawings), Testing, Sampling and Related Topics 10
A Random Sampling for in-process inspection Inspection, Prints (Drawings), Testing, Sampling and Related Topics 7
P Random Sampling vs. Thorough Review - Records to be Reviewed - Audit Finding Inspection, Prints (Drawings), Testing, Sampling and Related Topics 13
S Random Sampling question - taking samples from the same spot! Inspection, Prints (Drawings), Testing, Sampling and Related Topics 4
S Using AQL to get true random sampling using General Inspection Level II AQL - Acceptable Quality Level 4
Ron Rompen Random data generation in Minitab Statistical Analysis Tools, Techniques and SPC 2
L Do all non-random patterns apply to attributes and variable charts including R chart? Statistical Analysis Tools, Techniques and SPC 5
S Probability Density Function of a Function of a Random Variable Statistical Analysis Tools, Techniques and SPC 13
I Multiple Comparisons for a Random Factor Using Minitab Software 2
P Individuals Chart for Non-Sequential Data - Random Sample without Reference to Time Statistical Analysis Tools, Techniques and SPC 4
H Part Number Assignment, Should be coded or Random? Manufacturing and Related Processes 11
Marc Solving "Random" Puzzles Key To Scoring A-List Tech Jobs Career and Occupation Discussions 8
Ajit Basrur Random Insult Generator (RIG) Coffee Break and Water Cooler Discussions 2
M Random 'Normal Distribution' Numbers in Excel Excel .xls Spreadsheet Templates and Tools 26
M Creating a "random disturbance" for each observation via MINITAB Using Minitab Software 1
C Random Uncertainties - Can anyone explain "Random Uncertainties"? Gage R&R (GR&R) and MSA (Measurement Systems Analysis) 4
Marc Unannounced Random Audits General Auditing Discussions 1
J IVD sampling sizes for buyer Reliability Analysis - Predictions, Testing and Standards 0
S Which Sampling Plan(s) Should I Use? Inspection, Prints (Drawings), Testing, Sampling and Related Topics 7
C Sampling - ISO 16269-6 vs ISO 2859 Other ISO and International Standards and European Regulations 0
L Sampling Plan Risks AQL - Acceptable Quality Level 6
A Sampling plan for in-process QC (medical devices) Inspection, Prints (Drawings), Testing, Sampling and Related Topics 13
M Minitab Capability of the Population (no sampling) Using Minitab Software 11
W LTPD, AQL, Ppk and Cpk validation sampling plan table Inspection, Prints (Drawings), Testing, Sampling and Related Topics 0
Q Sampling method for Distributor verification activities EU Medical Device Regulations 1
E Change in control plan - Do I have to do sampling? IATF 16949 - Automotive Quality Systems Standard 1
S Is using ANSI/ASQ Z1.4-2008 the correct sampling plan to determine Pass/Fail of Apparel measurements? AQL - Acceptable Quality Level 4
N Sampling Plan for Internal Audits - ISO 2859 or 3951 - Or Neither? Internal Auditing 6
F Product audit sampling plans IATF 16949 - Automotive Quality Systems Standard 3
R Reduced sampling plan for sterial products APQP and PPAP 0
A ISO 2859-1 - 9.3.3.2 Switching score - Sampling Plans and PPM AQL - Acceptable Quality Level 0
R BS EN 12060:1998 - Zinc and zinc alloys Method of sampling Specifications Manufacturing and Related Processes 4
S High voltage testing - ISO 17025 - 7.2.2 Validation of methods and 7.3 Sampling ISO 17025 related Discussions 3
8 Activity Sampling Exercise Lean in Manufacturing and Service Industries 11
T Defining sampling plan for different AQL AQL - Acceptable Quality Level 3
B AS9100D Sampling Plan AS9100, IAQG, NADCAP and Aerospace related Standards and Requirements 2
R Design verification for interim design outputs - sampling rationale ISO 13485:2016 - Medical Device Quality Management Systems 2
Nicole Desouza Sampling plan for a customer who wants AQL 1.0 (per ANSI Z1.4) AQL - Acceptable Quality Level 5
V How to interpret AQL sampling tables AQL - Acceptable Quality Level 5
A AQL sampling bags of parts Inspection, Prints (Drawings), Testing, Sampling and Related Topics 5
C Applying Weibayes to Attribute sampling Reliability Analysis - Predictions, Testing and Standards 0
I Sampling processes - Who must define the AQL level? AQL - Acceptable Quality Level 9
E Sampling for capability studies for variables and attributes Capability, Accuracy and Stability - Processes, Machines, etc. 4
O Statistical justification of sampling size in V&V tests ISO 13485:2016 - Medical Device Quality Management Systems 5
M Sampling Plan for Alumin High Pressure Die Castings Manufacturing and Related Processes 0
E Sampling plan for orthopedic implant - Process Validation Inspection, Prints (Drawings), Testing, Sampling and Related Topics 4

Similar threads

Top Bottom