Statisical methods for Customer Service Quality Assurance



Hello all,

I work in a customer service center and we are attempting to decide on the right sampling plan for our Quality Assurance program. I am not quite sure which one is appropriate or how to justify the method once chosen.

Basically, we have several different touchpoints (web based chat, email, phone) and low volume but many clients. We want to give a 95% confidence level, with 4% margin of error on both the client (external) and rep (internal) levels.

Any advice and/or directions to resources would be much appreciated.



Thank you for the statistical information - it helps out a lot. Well personally, I wanted to go with a straight 10% but my boss wanted to use sampling.

What other methods would you suggest we use?

Thanks again for the information


Fully vaccinated are you?
Rick! Thank you for helping out with this fellow's question and the others you have helped with as well. Your help is greatly appreciated!

Rick Goodson

The question is difficult to give a simple answer to. Statistically based samples are always more reliable than straight percentages. If you develop the Operational Characteristic (OC) curve for the sampling plan with a straight percentage you will see that as the population size decreases, the protection afforded by the sample gets worse. If you do not have a strong background in statistics I would recommend you look at a basic text on sampling or a basic quality control book with a good section on sampling before proceeding. My favorite is rather old but does have a current revision:

Quality Control by Dale Besterfield, ISBN 0-13-745232-2

Getting back to the original issue. If you are sampling as part of an ISO internal audit, you can not economically use statistical based samples unless you have an army of internal auditors. I am sure that Marc and some of the other contributors would agree. When I teach internal auditing I explain that there is not enough resource (auditors) to go around and therefore you have to take samples that are extremely small and not statistically significant. However, if you find a problem from a sample that is extremely small, it is usually an indicating of a problem worth investigating as the odds of your finding that problem were also extremely small.


Rick, thanks for your reply.

I have done some research into statistics and I admit that some of it goes way over my head.

I agree that as population decreases, the company will have to sample a LOT more to get the sort of accuracy we want.

Because our population is fairly low, I decided to use a longer time frame. As I stretch it out over a month and longer, the sessions to be reviewed decreases to a point where it is feasible to QC. Of course, we can't QC at the end of the time frame so we're using historical data to forecast and break up the QC on a daily basis.

That's been my solution so far, what do you think?

Thanks again for your input.


Fully vaccinated are you?
I teach my course the same way. I explain that there are so many specifics you have to set a sample but that they should understand that it would be overwelming to even begin to define what a statistically valid sample would be. As an example, for documents I tell them I suggest a typical sample size of 3 to 5 documents. No problems, go on your way. If you find 1 'reject', increase your sample size by 5. If you find another problem you are at a point where you will have to decide on the spot - can't be predicted as it will be a judgement call based on the specifics at hand. I emphasize that the sample size I recommend does NOT have a true statistical foundation.

Rick Goodson

Whether the use of statistical sampling is the right thing to do in this situation is a matter for debate. Never the less, the statistical side is relatively straight forward.

The formula for finding the sample size (assuming a continuous process that is in control) is:

n = sample size.
p = estimate of process percent defective.
Zcl= Z score of confidence level (remember
that this is a two sided estimate so
you have to use half the confidence
factor on each side, for 95% confidence
level you use 97.5% to find the Z
E = Allowable error of the process percent

Zcl x p x (1-p)
n = ---------------

In essence, the sample size is equal to the Z score squared times the percent defective time 1 minus the percent defective divided by the allowable error squared.


Process Quality Control by Ellis Ott, ISBN 0-07-047923-2, pages 76 - 79.

Modern Methods for Quality Control and improvement by Wadsworth, Stephens, and Godfrey, ISBN 0-471-87695-X, pages 173 - 176.

Hope this helps.

Rick Goodson

I hope you can make out the formula I just posted. Unfortunately the software makes it hard to accurately post a formula. Hopefully the text makes it clear.


Hi there ,
I need to understanding your objective of your question. What do you want to achieve with the sampling ? Are you looking for most preferred touchpoint ?

I am woking with several operating companies within my organization in their quality journey modelled after Baldrige Criteria. One of the area we focused on is "Customer Service" which deal with access mechanism (similar to your touchpoint). However, so far, we have not used any staistical method to determine the most preferred access mechanism but the following methods :-

1) Customer survey, though time consuming and subjected to realibility. This is to determine customer most preferred access mechanism (normally designed into the questionaire). Then do a Pareto chart
2) Data collection when customer call in and do a Pareto chart for most frequently used access mechanism
3) "do what others do" i.e. follow the market trend or competitor

However, the decision to provide which access mechanism depends on company's strategy and affortability. There is not standard way but to meet customers needs.

I could share more of my experience when I get a better understanding of your objective.

Hope this help

Thanks and Best Regards


[This message has been edited by lmfoong (edited 23 November 2000).]

Ray Culver

Good afternoon,
I have extensive experience in this area which perhaps I could share.
#1. For a customer service call center you must first start with a sample plan that is ALL trasactions, to get going on the project. You do this to determine the next stage which is understanding the "regular" sampling plan. This approach is Statistical Quality Control not Statistical Process Control. To sample your entire transaction base you need technology: The phones should be hooked to an ACD system, you web page should have a CMR engine driving it, your fax order transaction must be tagged as "fax" in your order entry modules of your legacy system, etc.
#2. I agree with Imfoong that you also must do customer surveying to determine their "touchpoints".
#3. Look at the wall where the company mission statement is hung. Half your touchpoints are probably implied in the statement.

In our company we handle about 650 tele calls a day, receive 1,000 faxes, 400 on-line orders.
We have all the technology as mentioned above to gather data on an hourly basis so we are at an advatage here...
We used customer surveying to find out what our customers wanted in service and we used QFD to structure the department(s), and determine our "touchpoints".
Here's some data to think about, because I think that your customers may be somewhat the same ours;
1. Customers want to make contact easy, fast, and user-friendly.
2. they want prompt, timely & responsive service.
3.They want their request to be handled once and only once.
4. Service must be error free.

We measure the call center on # in-coming/out-going calls, # adandoned calls, # Overflow calls, average time per call, # input errors, # abandoned webpage hits, etc, etc. This is done daily but also the data is used for strategic planning therefore is charted by month, quarter and annual.
We have found that we have violated customer requirement when:
a. There are more than 5 abandoned calls,
b. There are more than 1 Overflow calls (these are calls that are bounced out of the que to receptionist)
c. A call takes longer than 2min 50 seconds.
d. There is a mistake on 10 orders out of 1,600 per day.
e. We don't communicate back to them about ambiguous information from our webpage within 2 hours of receipt of request and within 3 hours of receipt of fax request.

What I'm suggesting is that in your original message you had a margin of error of 4%, which you may find is quite liberal! Did you mean .004%. We have found by listening to customers that the margin of error in most industries today is almost zero, due to technology, competition, and the demographics of society....

hope this helps.

P.s.Rick Goodson...great response for sample plan!!! This approach is quit necessary in a controlled customer service environment. But control in a dynamic department like C/S and Sales takes time, determination and's one of the hardest things to control and measure. Only now are we reading about pioneers in the area of quality and sales i.e Paul Seldon, Cas Welch.
Top Bottom