Is there a method to calculate the sample Size to be audited where we receive approximately 200000 calls per month?

 

 

Hi Srinivasan, good question. 

 

Your sample size to be audited shall depend on various factors, some of these are - 

1. Are you going to collect data for something like handling time (continuous) or for accuracy (attribute data) for calls? Sample size is smaller for continuous data and bigger for attribute data. 


2. How the performance has been in the past? If you have information from the past, it might help in reducing sample size. 


3. What is the objective if taking samples? You might be comparing the performance with an external standard, for example or you may like to compare different sets of data. Size depends on this.


4. How much error you are willing to tolerate? Reducing error shall mean more samples needed. 


5. Finally, how much difference (from standard value or between sets of data) you wish to detect. If you are trying to detect smaller differences, you need more samples.   

Hi VK,

 

Process A : manual - 6 months data

Process B: Automatic - machine - 4 months

 

roughly 45 data points total

continuous 

 

turn around time is being measured as focus point- to be improved (reduced) by X% by designing something.

 

I have collected data, would like to share with  you - your email please.

 

probably use this for my BB belt.

 

Please confirm.

Dear Ashok, 

 

My email id is vk at benchmarksixsigma dot org. 

 

Best Regards, 

VK

hi mr. VK,

 

these are the information abt the process

1. To check accuracy of calls- its an attaribute data- Objective- audit to check process and prodcut adherence to resolve cutsomer queries
   
2. the performance is wavering at 80% and the benchmark by the client is at 85% and they have not advised on the specific sample size. thats why i want to arrive at a sample size and looking for a method.
   
3. no external standards are available at the moment. might look in to competition standards if possible.
   
4.  2% is acceptable error
   
5. we are receiving close to 200000 calls/ month and the head count averages between 100-120 per desk.
   

looking forward for your reply on the question.