# Sampling/Data

### The Importance of Sample Size

What do Goldilocks and statistical analysis sample size have in common? A razor-sharp focus on “just right.” A sample size that is too big or too small leads to inaccurate data and wasted resources (although hopefully not three bears).

### A Study of Estimates of Sigma in Small Sample Sizes

This paper looks at some of the methods of estimating standard deviation (which I will usually refer to as ‘sigma’). Additionally, I propose a new formula for estimating sigma for small sample sizes and also present a means to mathematically evaluate these competing estimates of sigma. The question was posed to me: “I have five…

### Use a Classification and Regression Tree (CART) for Quick Data Insights

In the Analyze phase of a DMAIC (Define, Measure, Analyze, Improve, Control) Six Sigma project, potential root causes of variations and defects are identified and validated. Various data analysis tools are used for exploratory and confirmatory studies. Descriptive and graphical techniques help with understanding the nature of data and visualizing potential relationships. Statistical analysis techniques,…

### Using Censored Data in Transactional Processes

Censored data is commonly used in reliability studies to determine the mean time to failure in order to establish warranty and maintenance periods for products. A large number of samples are subjected to either normal-use or accelerated-use conditions. Failure modes and occurrences are logged. Plotting the distribution of the sample failures over time allows the…

### TaaG Analysis – Fast and Easy for Comparing Trends in Large Data Sets

TaaG (trends at a glance) analysis is a fast way to compare trends of subsets of data across large data sets. It is an ideal tool to use in the Measure and Control phases of DMAIC (Define, Measure, Analyze, Improve, Control) projects. The value of TaaG analysis is best understood by way of example. Suppose…

### How to Avoid The Evils Within Customer Satisfaction Surveys

When the Ritz-Carlton Hotel Company won the Malcolm Baldrige National Quality Award for the second time in 1999, companies across many industries began trying to achieve the same level of outstanding customer satisfaction. This was a good thing, of course, as CEOs and executives began incorporating customer satisfaction into their company goals while also communicating…

### VOC: Comparing Reactive Data and Proactive Data

Collecting data – be it voice of the customer or otherwise – requires a plan. Details of the plan should include what data to collect, how to get the information, where the information will come from and so on. Before any of these details are defined, however, the first step is to identify what a…

### Mind Mapping: A Simpler Way to Capture Information

Reducing wait times is a perennial challenge for the service industry, particularly if you haven’t rooted out all the causes for the delays. The mind mapping visualization tool can help you make sense of large volumes of interconnected data and fast-track implementation of Lean Six Sigma.

### Process Data Mining: Partitioning Variance

Manufacturing facilities can be faced with major challenges when it comes to process improvement, largely because practitioners don’t always know enough about the underlying process factors (x’s) are that drive the improvement metric (Y). Practitioners might have a brainstorming session to tap into the collective experience of experts involved in the process, and design experiments…

### Reducing Sampling Costs: Implementing a Variable Sampling Interval Strategy

Most manufacturing processes are controlled by sampling a product at some regular interval. Often, when a process is running normally, this interval is once every shift. It is not too surprising that in today’s economic climate, where cutting cost is of paramount importance, reducing sampling to save money is inviting, especially at large manufacturing facilities,…

### Rounding and Round-off Rules

When performing statistical data analyses, quality professionals are always challenged to maintain data integrity. When should you round up the answer; when should you round down? How many significant figures are appropriate for the data set that has been taken? Below are a set of simple rules that should help you traverse the perils of…

### Is There Bias In Your Random Sample?

By definition, a sample of size n is random if the probability of selecting the sample is the same as the probability of selecting every other sample of size n. If the sample is not random, a bias in introduced which causes a statistical sampling or testing error by systematically favoring some outcomes over others….

### Actionable Information from Soft Data

Engineers, Six Sigma practitioners and other researchers often work with “hard” data – discrete data that can be counted and legitimately expressed as ratios. But what of “soft” data, things like opinions, attitudes and satisfaction? Can statistical process controls (SPC) be applied here? Can process variation in customer satisfaction, for example, be measured and then reported to…

### GE’s Six Sigma Focus On Span

We have heard about GE being one of the biggest proponents of Six Sigma, both for their own processes and for their customers. We’ve also heard how much GE has saved by implementing Six Sigma. This article is not a regurgitation of the existing rhetoric. Instead, I’d like to focus on an aspect of how…

### How To Turn Process Data Into Information

A repeated series of actions and variables is a process. A collection of processes is a system. Virtually perfect Six Sigma quality results from an optimal interaction of all the variables in a given system. Process and system questions we all face at work include: Which variables are the most important to the customer? Am…

### Building a Sound Data Collection Plan

Black Belts and Six Sigma practitioners who are leading DMAIC (Define, Measure, Analyze, Improve, Control) projects should develop a sound data collection plan in order to gather data in the measurement phase. There are several crucial steps that need to be addressed to ensure that the data collection process and measurement systems are stable and…

### Digging for Data: Insurance Companies Strive to Improve

Based on experience with property and casualty insurers (P&C), one of the biggest profitability drivers is the expense incurred staffing and settling claims. Many P&C insurers struggle with timely and efficient claims processing. In working with P&C companies consulting groups found three common challenges that project teams must address to improve the overall claims settlement…

### Enlist Process Owners to Survive an Absence of Data

The beauty of Six Sigma, over other decision-making strategies is that it is, by nature, data driven – it involves making decisions backed by evidence. In the absence of data, then, what good is Six Sigma? A Black Belt without data is like a navigator without a compass; finding north becomes complicated, but not impossible….

### How to Determine Sample Size, Determining Sample Size

In order to prove that a process has been improved, you must measure the process capability before and after improvements are implemented. This allows you to quantify the process improvement (e.g., defect reduction or productivity increase) and translate the effects into an estimated financial result – something business leaders can understand and appreciate. If data…

### Eliminating the Fear About Using Confidence Intervals

One of the pleasures of teaching Green Belts is helping to eliminate the fear of statistical analysis. One technique is to place an emphasis on not only when and why a tool or methodology is used but also what the data says in “plain English.” Memorizing complex formulas may be the goal of many Master…

### Statistics Do Three Things – Describe, Compare and Relate

Fear of statistics is often a barrier to learning and applying Six Sigma methods. One way to minimize this fear is to remember that only three things can be done with statistics – describe, compare and relate. Many people are skeptical when they first hear this statement. “It couldn’t be that simple,” they think. However,…

### Basic Sampling Strategies: Sample vs. Population Data

Information is not readily found at a bargain price. Gathering it is costly in terms of salaries, expenses and time. Taking samples of information can help ease these costs because it is often impractical to collect all the data. Sound conclusions can often be drawn from a relatively small amount of data; therefore, sampling is…

### Improving Staff Scheduling at Providence Health System

As with most hospitals, labor is the largest budget expense at the Providence Alaska Medical Center (PAMC) in Anchorage. But benchmarking indicated that staff utilization at PAMC, a part of the Providence Health System, was above the 75th percentile of the national average. To remedy this, in October 2003, a multidisciplinary team (nursing, leadership, finance…

### Attribute Data: Making the Most of What’s Available

Many times in software development and information technology, attribute data is what is available. Thus, it is valuable to look closely at the nature of attribute data and explore some tips for making the most of it.

### Sample Correctly to Measure True Improvement Levels

Many companies spend considerable amounts of money on customer surveys every year. They then use those survey results to amend strategies, design new products and services, focus improvement activities and to celebrate success. But can practitioners always rely on the results they see? Here is a fictional example: MyInsurance, a life insurance company with worldwide…

### Stratification Leads to Specialized Improvements

Many times Six Sigma practitioners start projects or analysis at a broad level. These projects may include processing a patient through a clinical procedure, transferring medical records, registering a patient, or analyzing lab or equipment usage. In healthcare, the number of processes and their complexity can be very high; there may be thousands of processes…

### Six Sigma Tools Still Fit in Projects Lacking Data

No data? No problem! The Lean Six Sigma process provides an excellent framework for all types of projects, even when there is little or no data.

### Analytical Treatment of Discrete Ordered Category Data

Ordered category data is discrete data representing appraiser or client perception against a rating scale such as a survey or questionnaire. Black Belts learning to apply the Six Sigma methodology to ordered category data are traditionally taught analytical methods that include normal and Poisson distributions. This is probably due to Six Sigma’s beginnings in manufacturing….

### Implementing a Data-Driven Methodology Without Data

Six Sigma is a data-driven approach for eliminating defects in any process. The use of data is a key foundation of Six Sigma. Yet, when Six Sigma is being implemented organization-wide, the use of data diminishes, almost to the point of disappearing.

### Data Management Plans Can Improve Collection/Validation

Companion Article This is one of two articles by David Wetzel that explore the value of developing a data management plan as the intial step in the Measure phase of the Six Sigma DMAIC methodology. The other article is “Data Management Plans Can Reduce Project Cycle Time.” Understanding data and defining process paramaters (input) or…

### Data Management Plans Can Reduce Project Cycle Times

Companion Article This is one of two articles by David Wetzel that explore the value of developing a data management plan as the intial step in the Measure phase of the Six Sigma DMAIC methodology. The other article is “Data Management Plans Can Improve Collection/Validation.” Long project cycle times, frequently cited as an impediment to…

### Using Lean Six Sigma Measurement Tools in Maintenance

Lean Six Sigma is widely used in production, but it can just as easily be applied to maintenance. Here’s how to implement a measurement system using data to identify root causes, prioritize workloads and drive improvements in a maintenance operation.

At the Measure phase, improvement project leaders are confronted with the question: What is the most effective, efficient way to identify the data needed and to perform analysis of the data during the Measure and Analyze phases of the DMAIC method?

### Margin of Error and Confidence Levels Made Simple

A survey is a valuable assessment tool in which a sample is selected and information from the sample can then be generalized to a larger population. Surveying has been likened to taste-testing soup – a few spoonfuls tell what the whole pot tastes like. The key to the validity of any survey is randomness. Just as…

### Estimating Sample Size for Process Capability with Special Causes (with Template)

Six Sigma team members often ask, “How much data do I need to establish the baseline?” for a process that is unstable. There is no valid statistical calculation for sample size in this situation, but that is not much comfort when you are trying to develop a sampling plan in the early stages of your…

### Using Vector Analysis for Turbo-Charged Data Mining

Data mining via vector analysis is a powerful, flexible process observation tool. With due regard for the possibility of correlation/causation fallacies, data mining can be used by almost anyone.

### 3 Ways to Speed Up Data Collection in Financial Service Processes

In any financial service process that is being studied for the first time, it’s common for Six Sigma teams to spend one-third to one-half of their project time on data collection alone. Here are three tips that can help you get off to a faster start.

### Use Cases and Measures: Strengthening the Six Sigma Link

“Use cases,” a term coined by Ivar Jacobson early in the evolution of object-oriented thinking, have been widely accepted as a helpful way to understand and document the functionality that is important in all kinds of software or business systems. Anyone within miles of object-oriented design will be familiar with the typical application of use…

### Why You Cannot Depend Totally on Statistical Software

The proliferation of do-it-yourself statistical software can give some Six Sigma practitioners, who may not be strong in statistics, a false sense of confidence. For the most accurate results, follow these eight tips before you begin collecting and analyzing data.