MarketingProfs' Members Register for B2B Forum 2010 for just $695! (good until 11/30) »

Ask your question ... sign up today! It's FREE!
Research/Metrics     
 
This question has been closed, and points have been awarded.
Time Spent On Administration Between Phone Calls
Posted By: cathal.kerr* on 3/8/2005 5:07 PM (CST) 250 Points
I work in a call centre and need to conduct a survey to establish the amount of time agents spend on administration in between phone calls. The group I have targeted has 50 people working 40 hours each per week. Data is as follows:

Population 2000 hours
Confidence 95%

I would expect the answer to be something like 'Time on Admin' per agent per/day= 1 hr 30 mins +/- 10 mins

What is confusing me is that I am treating each hour as an event and want the confidence interval in minutes.

How should I model this survey. Should the population be measured in minutes or hours?

Posted by: holm Accepted Answer
3/8/2005 5:11 PM (CST)
I am not sure I understand the question. As a rule of thumb for consumer interviews - it takes as long to find a willing respondent as it takes to administer the survey. So if the survey itself takes 10 minutes and it takes 10 minutes to find a new respondent you can complete 3 surveys an hour. This is not a perfect formula and you will need to up the time to find a willing respondent if you are dealing with a low incidence audience.
 
Posted by: fredj5* Accepted Answer
3/8/2005 5:38 PM (CST)
I am a little confused on why a survey was chosen to determine a concrete number.

What is the actual call time for your 50 agents during a 40 hour week?

Other than calls and call administration, what else do you agents do? If yours is like any other call center I have been in, the answer is not much.
 
Posted by: ASVP/ChrisB Accepted Answer
3/8/2005 6:06 PM (CST)
Perhaps there is more to life than Call Time and Administration. I imagine there are visits to the water cooler, bathroom and discussions with the supervisor.

You need to break down all the activities undertaken and allocate the time spent to each.

Call time must be available as a system statistic... As must system log-in time. How bothered are you about tracking the other statistics?

WHY are you doing this exercise?

Is it to try to increase performance, or for disciplinary measures of some sort?

ChrisB
 
Posted by: cathal.kerr* Author Response
3/8/2005 6:33 PM (CST)
Chris B,

I am only focusing on Admin only Headcount for the centre HC = aCall Vol + bAverage Call Time + cTraining ......... We have a piece of software that calculates the Headcount for the centre but it needs a figure to be manually input for the administration parameter. I cannot trust people to give me an accurate figure so I must go out and estimate the figure if this answers your question Fredj. I therefore need to choose a sample size, and a confidence interval and then carry ot the necessary number of surveys. I will then calculate the sample mean for administration and put the resulting number into the software application.
 
Posted by: holm Member Response
3/8/2005 7:35 PM (CST)
I don't get what you are trying to do? It seems to me you are over complicating the situation. We run our call center based on some fairly simple parameters. The interviewers need to have 50 dials per hour excluding time spent on survey. The number of people we need to have in on any given day is a direct results of how many surveys we need to complete for that day. We know that attendance hits is about 30% so we over-staff by this factor. Could you be a little more specific about what you are trying to do?
 
Posted by: ASVP/ChrisB Member Response
3/8/2005 11:48 PM (CST)
Cathal

Why don't you take a sample employee (I would pick one you think is your best), monitor their calling & admin activity, and use that as a base model or initial benchmark.

Take that percentage for admin and input it into your system, then review the results you get out.

See how far the computed head count is from the true head count, and monitor, manage and adjust accordingly.

Good Luck

ChrisB
 
Posted by: Stokefire* Accepted Answer
3/9/2005 7:54 AM (CST)
Agree with Chris -

What statistics are best at is taking ACTUAL samples of the larger population and then extrapolating those to determine the composition of the whole.

You're likely going to need to sit down and watch a statistically significant sample as they go through their day. Unfortunately, this has a rather predictable way of skewing the sample - especially if they think their perfomance is being measured.

Could you set up a web cam or pc cam to track performance of your sample for a day or two?

Failing that, if you have a phone tracking or routing system you could compute admin time by assuming that all time not attributable to a live call was admin (minus breaks and lunch). Reviewing the phone records should enable you to back into the number.

Good luck!

Tate
 
Posted by: stevea Accepted Answer
3/10/2005 2:12 PM (CST)
Dear Cathal.Kerr

We seem to be in danger of suggesting some much better ways of measuring things than your company currently appears to provide, but without answering your question in the first case!

I think that you are putting the cart before the horse here as there do not appear to be enough measurements already taken to establish that which you want to measure in the way you state it. It doesn’t mean that you can’t come up with some useful figures through a survey though!

Firstly, 50 people, 40 hour each give you what you’ve termed a population of 2000 hours. You say confidence is 95%. I guess from your clarification that you mean Confidence Interval is 95%. But measuring what? The confidence interval simply states what % of a measured parameter will fall between two values. You can only know that once you’ve taken some measurements and set an upper and a lower limit!

Can I therefore assume then that the measured parameter is Time on Admin (Ta) that you wish to measure to give a confidence interval of 95%?

Should you measure in hours or minutes? Use Minutes, because you want to have uniform units of measurements and measuring in decimals of an hour is a pain and is hard to translate back into real life.

To take the form of your example of what you would expect an answer to look like, you would want to see something like, “95% of the measured user admin times (Ta) to include 90 minutes + / - 10 minutes.” i.e. 80 is less than or equal to Ta which is greater than or equal to 100

On the face of it, you might assume that by taking a sample of 5% of the hours worked in a week that you could have the level of confidence you are looking for, but this is a no-goer as far as statistical methods are concerned.

As you havn’t done any measurements yet, you have no idea of the range of values of Ta, thus you can’t know the mean or the standard deviation. That infers that you can’t calculate a confidence level.

If you set a confidence level you want, you can’t determine the sample size you need because you don’t know what the distribution of the values of Ta look like, so you have to start to take some measurements before you can start to approximate to the figures you’re seeking.

Sorry not to be able to give you a specific answer, but there isn’t one based on the information you have given. On the face of it, this seems to be a very difficult way of sorting out something which should be really very easy to do, if the parameters you need are recorded in the first place. That’s where the other postings are really useful – why set out to do something which is going to be a) difficult and very time consuming and b) Initially, statistically meaningless.

As I can’t print equations here, if you want to run through the problem in more detail, please email me directly and I can try to run through the base figures you need and the formulae you need to plug them into.
Regards

Steve
 
Posted by: ASVP/ChrisB Member Response
3/11/2005 2:18 AM (CST)
Cathal

Sounds like you are stuck in a forest and canot see the wood for the trees.

What is the objective you have?

i.e. What are you wanting to do with this information, once you have it?

Chrisb
 
Posted by: ASVP/ChrisB Member Response
3/11/2005 2:18 AM (CST)
Cathal

Sounds like you are stuck in a forest and cannot see the wood for the trees.

What is the objective you have?

i.e. What are you wanting to do with this information, once you have it?

ChrisB
 
Posted by: cathal.kerr* Author Response
3/13/2005 2:11 AM (CST)
Thanks everyone for your feedback. I would however like to reply to a couple of remarks.

1. I am not over complicating the issue - it is a problem I understand quite deeply

2. I can see the wood and I can see the trees

My original question related to the modeling of the problem from a statistical point of view NOT the parameters I was focusing on. ChrisB, you are right in pointing towards the Call Routing System to pull the information, however if agents do not use the correct phone codes when dealing with specific issues, the data will not be sound. I do have all of this data available to me. Taking the best employee as a sample is not a good idea. I am trying to quantify unnecessary or waste admin; the best agent will usually be the most efficient and will not waste much time. Stevea has answered my question.
 
Posted by: ASVP/ChrisB Member Response
3/13/2005 6:17 AM (CST)
Apologies if my "remark" was not taken in the friendly spirit in which it was intended. Perhaps the somewhat two-dimensonal qualities of a web forum do not always provide the perfect setting for the richness and multi-lingual diversity so often found here on KHE.

My point about measuring the best agent is this will give you an ideal - but real - benchmark from which the performance deviation of non-optimal personnel may be measured.

As far as agents using the wrong code is concerned - is there any procedure to audit and check the data to maintain its hygiene and integrity? Seems pointless to engage in deep statistical analysis if the data is incorrect...

ChrisB
 
Posted by: ROIHUNTER Accepted Answer
5/13/2005 12:02 AM (CST)
Your measurements should be in minutes. Start having your call center agents log in and out for admin (something your phone administrator should be able to assign to several phone pad keys) and then you can measure time in your CMS reports from the phone system. Since the log will be by call agent you can then analyse the agent, shift, day, etc.

Once you have the measuring tool, you can then tackle the question of population mean and standard deviation and can manage the call center accordingly.
 
Posted by: carrie77 Moderator Response
5/15/2005 1:20 PM (CST)
Hello all. I am closing this question since it's more than 2 weeks old. We do this to reward the contributions of participants in a timely manner + to give increased visibility to the newer questions.

Thanks for participating!

Carrie, Production Editor
 


Get more answers ... ReTweet this!

Would you like to post a response?
Welcome to Know-How Exchange!
This is a collaborative community. We welcome everyone's participation.
All you need to do is login. Enter your account info in the box above (top right).
Not a member? Not a problem. Register here (it's FREE and EASY).




Know-How Exchange powered by MarketingProfs


Sponsored Links

Buy a Link Now

Just Released ... Download Today!
Just Released ... Download Today!
Look inside
Included with Premium Membership
User Name:
Password:
Remember Me
Forgot your password?

Top 25 KHE Experts
(Research/Metrics)
ASVP/ChrisB (14554)
Jay Hamilton-Roth (11934)
jlevin (11599)
mgoodman (10158)
koen.h.pauwels (9157)
wnelson (7755)
DWomack (6993)
Frank Hurtte (6158)
stevea (6094)
skoobie99 (4979)
Peter (henna gaijin) (4267)
mbarber (4049)
Dawson (3995)
blanalytics (3883)
thinkmor (3634)
telemoxie (3021)
SteveByrneBranding (2755)
michael (2740)
darcy.moen (2727)
Michele (2419)
SRyan ;] (2396)
adammjw (2243)
holm (2169)
AndrewS (2081)
Wiglaf (2016)
Recently Posted Marketing Jobs
Director of Marketing and Communications
Demand Generation Manager
Marketing/Advertising Faculty
Director of Marketing
Market Analyst
Sr. Field Marketing Manager - Business Intell.
Associate Vice President of Marketing and Corporat
Marketing Manager
[more jobs]

Join over 355,000 members ... SIGN UP!

My email address is and I'd like my password to be .

Already a member? Sign In!

My email address is , and my password is .


HACKER SAFE certified sites prevent over 99.9% of hacker crime.