Six Sigma Green Belt Training Part 11

Skillogic Knowledge Solutions is one of the top training institute for six sigma training courses. If you are looking for six sigma green belt or black belt, visit skillogic and schedule your classes. Skillogic classroom training centres: HYderabad, Bangalore, Chennai
of 10
All materials on our website are shared by users. If you have any questions about copyright issues, please report us to resolve them. We are always happy to assist you.
Related Documents
  • 1. Six Sigma – Green Belt Workshop © 2016 Skillogic Knowledge Solutions. All Rights Reserved Part 11
  • 2. 2 Sampling Sampling is the process of collecting subset or portion of data from population and predicting population characteristics Why Sample ? When to sample The cost associated with data is very high We are measuring a high volume process When not to sample When the subset of data may not be able to predict population characteristics. E.g.. If each unit of data is unique Apart from other reasons to do sampling, one of the critical reasons is the time required to collect population data. Sampling is an efficient way to collect data for any kind of project or analysis. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 3. 3 Representative Sample Sample is Representative: When the sample has same statistics as of the population How to guarantee a representative sample: Suitable sampling strategy based on the process Understand the nature of process Understand the characteristics of population Sample must be “representative” of the population, as the data collected otherwise would not deliver any results and might give misleading inferences about the population. Sampling Bias Bias occurs when systematic differences are introduced into the sample as a result of the selection process.  A sample that is biased will not be representative of the population  A sample that is biased will lead to incorrect conclusions about the population A biased sample would have incorrect information about the population and will lead to biased conclusions. A bias in the sample can not be eliminated with increasing the sample size. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 4. 4 Sampling Bias Types Convenience sampling: This is also called as accidental bias. It occurs we use the data what is available instead of making as effort to collect data. E.g. interviewing the first person you met, pick friends and neighbors for survey. Systematic sampling: Collecting data at a particular time, or following a pattern in collecting data which has interference with underlying process. E.g. sampling process on Sunday when only one person works in the process. Judgmental sampling: When the data collector or surveyor collects data using his judgment or opinion. Bias by Environment: This type of bias is introduced when the environmental conditions surrounding process have changed since the sample was collected. E.g. When the call handle time data was collected it was tax season. Measurement Bias: Measurement bias could arise if the operational definitions are not correct or the data collectors have interpreted the operational definition differently. Non-Response Bias: Non-response bias happens when the respondents to a survey tend to differ systematically from respondents to the survey. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 5. 5 Sampling Strategy – Random Sampling Random Sampling: This is the most commonly used method of sampling. Use random sampling when information about stratification is unknown. Random sampling is a population approach and so care must be taken when the process is cyclical or if the data can be stratified. In random sampling each unit has equal probability of being selected in the sample. Using random sampling method avoids bias being introduced in the sampling process. For practical purpose one can number the data coming out of process and generate random list in excel or on minitab and accordingly sample data. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 6. 6 Stratified Random Sampling Stratified random sampling is used when the population has different groups (strata). In such situation it is necessary that both groups are represented in the sample and samples are collected from each group (it is like doing random sampling for each group). The size of the sample depends on population size of each the group. E.g. To sample from a assembly line preparing nuts of two sizes A and B respectively. The two sample sizes for nuts sized A and B would be calculated based on production of size A and size B nuts respectively. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 7. 7 Systematic Sampling Random sampling and stratified sampling are done with historical data. When we have real time data coming in systematic sampling is done. Unlike random sampling the frequency of collecting data is fixed in systematic sampling. E.g. selecting every fourth call in the call centre for call barging, selecting 2 application every alternate hour for quality check. Care must be taken and process must be studied for any underlying structures. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 8. 8 Random Sampling Rational sub-grouping is a process based sampling strategy. The rational subgroups depend on the nature and type of process from where the data is being selected. Rational sub-grouping assists us to understand the shift, which is the difference between the long term variability and short term variability of the process. We will study this in capability analysis under Analyze phase. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 9. 9 Sampling Strategy -Tips Use following pointers for sampling strategy for a given process:  It is always better to collect small sample spread over longer time period than one large sample over a shorter time period.  Sample more frequently for unstable process and less frequently for stable process  Sample more frequently for process with short cycle time and less frequently for process with long cycle time To understand the sampling frequency one should understand the objective of data collection The most important issue to remember when considering sample frequency is the data collection objective. The sampling frequency is driven by the objective of data collection, e.g. if the data collected is for monitoring process one might want to sample data daily. However if the objective is to collect data for the same process to study capability one might want to collect data for few months by sampling few data points each week or month. Measure © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • 10. 10 Skillogic Knowledge Solutions Call Us @ 901-989-9000 If you are looking for Six Sigma Green Belt training in Chennai City along with certification then visit: certification-chennai/ © 2016 Skillogic Knowledge Solutions. All Rights Reserved
  • We Need Your Support
    Thank you for visiting our website and your interest in our free products and services. We are nonprofit website to share and download documents. To the running of this website, we need your help to support us.

    Thanks to everyone for your continued support.

    No, Thanks

    We need your sign to support Project to invent "SMART AND CONTROLLABLE REFLECTIVE BALLOONS" to cover the Sun and Save Our Earth.

    More details...

    Sign Now!

    We are very appreciated for your Prompt Action!