[Pradeep Sharma]

I would like to share my data with you guys which I plotted on minitab:
As suggested i used wiebull distribution to calculate process capability as my data was non-normal. I got following Pp and Ppk (my LSL is 0 and ULS is 2880 mins)
Pp: 0.10
Ppk: -0.29
PPU: -0.29
PPL: 2.40
what all infrence can I make out from the above result. Please let me know if any body needs more infiormation.
Robert: I will appreciate if you could elaborate little bit more on the method you suggested. Do I need to calculate Z values for my data and get the Sigma level using Z-value, if yes then why use PPk to represent process performance, we can present that by Sigma level. Please help

0

[Pradeep Sharma]

In my opinion look at the time taken by each agent per form…even if you meeting the target, stil there will be scope of improvement. You might be requiring only 3 agents instead of 4 or you might process 300 forms instead of 250 per day per agent. Use DOE

0

[Pradeep Sharma]

I am also based out of Bangalore..mail me at [email protected]… we can take it forward from there.

0

[Pradeep Sharma]

Thanks for the link..now my next question is how do we calculate process capability if we have non normal data.

0

[Pradeep Sharma]

Hi,
When you have identified the root causes of your problem, you bulid action plans around it to tackle each root cause based on your analysis Then you go ahead and impliment your suggested action as per the plan. To ensure that process remains stable you put some controls like mistake proofing and track the performance of your process by using various control charts.
Regards,
Pradeep Sharma

0

[Pradeep Sharma]

One more example where in some body is doing project to get the certification and management is not supposrtive enough and not willing to drive Six Sigma. Not blaming you Vishal but thats the fact.I have been there and understand you completely. What will happen is you will waste lot of productive time in getting your stakehoders together and getting there buy in. Not demotivating you but giving you heads up of the issue which you will face in deploying six sigma. As per my understaing Six Sigma has 20% of politics involved in it (apart from stats knowledge, leadership skills, market knowledge etc etc). Be sure to get the buy in from your stakeholders else you will end up no where.
And apart from that you have been advised by champs how to proceed, best of luck
Pradeep

0

[Pradeep Sharma]

There are many, one of them is QAI, check http://qaiindia.com/, they charge around 35K for GB, you can also check for KPMG and TQMI, they charge little less.
 

0

[Pradeep Sharma]

Assuming your talking in minutes not in seconds, you can do following things for AHT
Break down your AHT into Average Talk time (ATT), After Call Work (ACW) and Hold Time per call. Try to get it from automated tool, if not possible then go for Time and Motion Study, ask your supervisor to do random monitoring and capture the data for you. Apart from this ask them to provide issue wise AHT, for ex. X issue takes y mins and so on. Your sample should cover all the polulation for all kinds of issues. Hope this helps…
Good luck

0

[Pradeep Sharma]

Hi IntelDesign,
Hi can I also get a copy, if you dont mind, my e-mail ID is [email protected]
Thanks,
Pradeep Sharma

0

[Pradeep Sharma]

I aplogize sir if I was not clear enough. I am looking at benchmarking for customer facing metrics, like subscriber retention %, increase in subscriber base per year, churn % and many other which are related to DTH industry. Let me know if am still not clear enough, i can aplogize again as what else a learner can do to the masters

0

[Pradeep Sharma]

Thanks,
As you said get your BB/ MBB and dont do project just for doing six sigma project. But then why these certification demands 2-3 projects to be done, which force a person to do project even if it is not required, else you will not get the certificate. Its easy to get trained but difficult to complete a project specially when your management is not ready to invest time and money on projects rather looking for quick resolution.One of the reason I am not able to get BB certificate :-(, I have seen people getting BB certificate by copying and pasting projects and calling themselves BB certified and getting good jobs within no time, and some people applying six sigma methodology for years and still not considered as six sigma professionals, at times its frustrating, atleast for me :-). Your thoughts….

0

[Pradeep Sharma]

I am new to this forum, I had same opinion about Darth what Ferry and others have. But after reading Darth’s earlier posts, I have changed my opinion. He makes dead topic interseting. Now I start by first looking for Darth’s comments.
Cheers
 

0

[Pradeep Sharma]

No Raj, I am not that Pradeep Sharma

0

[Pradeep Sharma]

Thanks Joe for your comments, I have job based on my little bit six sgima knowledge and fortunately in my current profile i am learning a lot about SS. This question was in my mind becuase where ever I have applied no body has asked for certificate “As proof of knowledge”. I was planning to go for BB certification wanted to know if it is actualy worth spending heavy amount for peice of paper. But after reading your comments I think I should go for certification, however focus on acquiring knowledge.
Thanks

0

[Pradeep Sharma]

Nitin, thanks for calirification, my next question would be:
What would be its siginificance in terms of sampling, Why do we need to look at 95% confidence with confidence interval of 2, when we are selecting sample size.

0

[Pradeep Sharma]

I dont think you will find these terms in this forum, RAG report is nothing but “Red Amber Green”. Mark the items red if they have not been done, Amber if they are in process, Green if the are completed. In heat map you rigrously follow up with your action item owner on the action item on daily basis, for ex. If you say you have increased the number of monitorings for focus group, track on daily basis how many agents monitored, how many calls monitored, was 100% feedback given or not, what is the effecitveness %age, measure effectiveness evaluator wise,how are you measuring your internal success and external success and so on. You can design a template in excel. And now since you have control plan in place, you can do FMEA on control plans

0

[Pradeep Sharma]

Assuming its an Indian call center, communication plays big role in driving your c-sat, but once you provide solution to the customer satisfactorily they ignore communication barrier. And we need to understand the fact that we can eliminate communication barrier, so our focus should be more on resolving the issue and side wise we can target communication barrier also. At time stats might act funny as in your case communication has -ve coefficient. But you cannot ignore it as well. And since you are taking your data as continous, you cannot run chi-square (its used for discrete). Rather go for ANOVA if you have multiple groups or 2 sample T- test if you are tesiting 2 groups.

0

[Pradeep Sharma]

Hi,
Apply heat map and RAG report to track the implimentation of your action plan (daily or weekly). Key to sucess is “DO NOT LOOSE THE RIGOUR”. Bring changes to hiring process and training process. I can understand hiring process is not under control, but training process is…start implimenting all your action plan from training itself. Make it a part of certification process. So that when new hires take calls they are upto the mark.
Pradeep

0

[Pradeep Sharma]

In our scenario,customer rates a c-sat questions on ” Strongly Agree”, “Agree”, “Disagree”, “Strongly Disagree” and “Don’t Know”. You take out the percentage of “Strongly Agree” and “Agree” to the total number of survey recevied to calculate your CSAT scores for the day, agent, team, call drivers etc…This how we consider it to be continous data rather than discrete.
I agree ” Strongly Agree”, “Agree”, “Disagree”, “Strongly Disagree” and “Don’t Know” is discrete scenarion, however, when you get 500+ survey for 500+ agents, can we consider it to be discrete and run analysis on it. Please clarify

0

[Pradeep Sharma]

Hi Romel,
CSAT scores are generally continous (not sure what is the data type in this case). However, if we assume it is continous, what else can be used apart from Chi-square (as per my understanding chi-squre is for discrete data). will it be T- test or ANOVA based on the number of groups.
Pradeep
Pradeep

0

[Pradeep Sharma]

Hi Rajesh,
Its me again, tempted to reply yous posts I have dealt a lot with CSAT. Generally FMEA does not help in case of CSAT. Probably you can use FMEA instead of doing 5 Whys to get to the root cause. But I will still not vote for FMEA in CSAT as there you will have to do FMEA for all the call drivers and then identify failure modes.
Best of luck

0

[Pradeep Sharma]

Hi Rajesh,
In this scenario keep following things in mind
1. Have standard number of calls monitored for all the agents
2. Align your QA form with your CSAT questions (mostly QA score does not corelate with CSAT scores as QA form is not alligned to CSAT questions. Foremost and important thing is to allign your QA form with CSAT questions)
3. Based on your CSAT or QA scores identify your focus group, increase the numner of monitorings for them, you can reduce number of monitorings who are consistently scoring good to tackle resource availability)
4. When you have identified focus group, you should have focus area identified for the focus group (again I will say based on issues you idetify which are driving DSATs), need not to do project for this simply map your DSAT with call driver, run pareto on it. Do root cause analysis for top 30% of the drivers, we use 30/70 instead of 20/80 in call center scenario (tried and tested).
5. Do focus on Issue Resolution and then soft skills
I hope this will help, if not then go for full fledge SS project

0

[Pradeep Sharma]

Hi Peppe, would like to know more about it. How do we do it?
Thanks in advance

0

[Pradeep Sharma]

In case of CSAT, focusing on agents is not advisable, focus should be on the process. Identify issues or calls which are getting you DSATs, focus on them. Because your agent population can change any time but your call type will remain same. Do root cause analysis on the calls/ issues which are driving DSATs. Tools used for such scenario can by
1. Pareto Analysis 2. Fish Bone 3. 5 Why Analysis

0

[Pradeep Sharma]

Sachin, start of with mapping your process in detail. List down all the process steps, list down all the potential failure modes (how that step can go wrong), list down all the potential cause against each failure mode (you can use cause and effect to know your causes), the list down all potential effect for each cause that is causing failure mode. Further list down current control against each potential effect. Get all the stake holders of the process, discus the potential failure modes, causes and effects you have listed down. Ask them to rate each potential defect, cause and effect in terms of Severity, Occurance and Detectibility. Calculate RPN. Prioritize RPN and discus recomended action plan for each potential failure modes. Design control plan based on your FMEA.

0

[Pradeep Sharma]

Hi Romel,
Can i get in touch with you on your e-mail ID, need to understand how do we calculate CPk for process in design stage?
Pradeep Sharma

0

[Pradeep Sharma]

I agree and to add, if you have historical data (say quaterly data), you can use that to set your own index number for severity and detectibility. You also need to consider human factor involved in call centers to decide on occourance and detectibility index

0

[Pradeep Sharma]

Hi,
We are almost about to launch our product in few days, will it really make sense to start QFD? Becuase as per my understandging its very time consuming excercise (correct me if I am wrong). Can we go ahead and rely on our control plan desgined through FMEA?
Regards,
Pradeep Sharma 

0

[Pradeep Sharma]

Hi Romel,
Thanks for the input, would appreciate if you could explain the productivity as ratio of efficieny to effectiveness in more detail with example.
Regards,
Pradeep Sharma
 

0

[Pradeep Sharma]

Thanks Nitin, things are taking shape now, but I am still confused, how the type of metrics depends on customer type. Customer might be internal or external, what matters is how efficiently or effectivly we have delivered. Sorry If I am acting dumb over here !!!

0

[Pradeep Sharma]

Nitin, thanks for your inputs. Ok lets take post a process where in we make a sale and get signed contract form from the customer. In this porcess we are measuring 1. Cycle time for Sales Order Closure 2. Subscriber Satisfaction Index 3. % of completed contracts and 4. % of missing contracts. Which one can we classify as Efficiency Materics and Effectiveness Metrics? My second question would be is it important that we have to classify all the metrics in terms of efficiency and effectiveness? How about measuring “Increase in number of sales”?

0

[Author]

Posts