Excluding the unwanted: Data that doesn’t belong

Matt SavageDo you have data that’s an anomaly or special cause that you want to exclude from your analysis? Do you want the ability to temporarily exclude certain data from your data set analysis? Special causes and outlying data can occur in any data collection process, learn how to easily handle these situations.

If you are calculating and charting average weekly temperature in a room, but find that one night the thermostat has been inadvertently set to 90 degrees, how will that data point affect your average? Clearly, the answer is that it would create a false sense of a higher temperature average for the week, and in effect create a misleading report.

There may be times that it is appropriate to leave out irregular data points such as this one, to be sure, without feeling that you’re “cheating” on the numbers. Additionally, there may be special causes that have been addressed and no longer apply to the calculations, and you’d like to remove these. Or perhaps you’d like to exclude certain pieces of data on a temporary basis, to analyze their effect on the calculations. Having the flexibility to remove or exclude anomaly data from your control chart can help you more easily focus on your process and remove any additional noise from the chart or the calculations.

Continue reading

The differences between control limits and spec (specification) limits

Matt SavageThe differences between control limits and spec (specification) limits may seem irrelevant or nonexistent to those outside process production, but the gulf between them is in fact huge. In fact, they are two entirely different animals.

Spec limits may be designated by a customer, engineer, etc., indicating the allowable spread of a given measurement. Control limits, on the other hand, emerge from the process. The process data will determine what control limits are and help determine the stability of the process.

If one is tempted to use spec limits as control limits, the advice from process engineers and statisticians as well is simple: Don’t.

For an X-bar chart, for example, such as the one illustrated below, all of the X-bar values are well within the designated spec limits. Things are fine, right?

Not so fast. Remember that an “X-bar” is an average. And as PQ Development Manager Steve Daum points out, if you put one foot in a bucket of ice water and the other into extremely hot water, the average water temperature may be perfectly temperate, indicating a comfortable situation. In fact, the average does not reflect the range of the separate data points, one of which might be 33 degrees Fahrenheit, and the other 180 degrees. Comfortable? Probably not.

A histogram of the same process offers a much clearer picture of the reality of this process (see chart), with some data values well outside the specification limits, indicating an unacceptable result.

Let your data do the talking, when it comes to control limits. Don’t confuse information from the process with requirements for the process.

Seeing your goals—with charts

Steve DaumWhile new year’s resolutions may already be long forgotten by many, those who are committed to personal goals continue to try to keep on the path to reach these goals early in the year. Good news: PQ Systems can help!

As we know from commercial applications of charting techniques, it is always far easier to garner information from numbers when they are illustrated visually, in charts or graphs. Even photos can help clarify meanings: A Melbourne, Australia, suburb trained volunteers to measure litter on the streets, giving them photos to support understanding of operational definitions of litter. (One cigarette butt in the gutter was not considered litter; two or more, or those on the sidewalk, were.)

So we have some ideas about supporting your personal goals for 2014 with visual use of data—a specialty of PQ Systems.

Charting data related to weight loss is commonplace, of course. Services such as Livestrong.com or Fitbit help to keep a running chart of weights entered daily, over a period of weeks, months, or years. Even crude hand-drawn charts make the point and demonstrate trends of weight loss or gain.

Continue reading

Taking your charting skills home: KPIs and health maintenance

Steve DaumCharting data is not just for the shop floor any more, as we have long discovered. Measuring outcomes for healthcare, banking, education, and other environments has become commonplace. What about taking your charting skills home? Key Process Indicators can help to evaluate weight gain/loss, exercise patterns, and more, as this piece by Steve Daum demonstrates.

Continue reading

Separate your charting and data analysis tools from your enterprise tools

Steve DaumOnline debate rages about whether potatoes and onions should be stored together, with the “no” side saying they both give off gases that accelerate spoilage, and the “yes” followers asserting that it makes no difference. Whether you agree or disagree, you can follow the underlying concept: some things do need to be separated in order to perform at their best. (Hence the practice of assigning twins to separate classrooms, perhaps.)

An important principle in software development is known as separation of concerns. The idea is that different concerns should be handled by different bodies of source code. For example, one body of source code should focus on saving and retrieving data from a database. A different body of code should focus on doing statistical calculations; these two concerns should never be mixed in the same body of source code. When this principle is violated, the source code is sometimes described as having a “code smell” which is not a good thing. Even worse than potatoes that smell like onions.

User requirements for software change all the time. They are dynamic. If you have source code nicely compartmentalized, you will be more nimble at stringing it together to meet some new user requirement.

Continue reading

The great divide: Creating silos with data analysis systems

Barb ClearyOnce upon a time, there was a manufacturing facility in Ohio that happily utilized Excel data in its quality management system, with some ten years of data organized in a way that was appropriate and useful to the quality manager and his department as they looked for correlations between problem metrics and other metrics that might have contributed to the problem.

In the same plant, a separate automation system was monitoring and recording data on metrics gathered throughout the facility. This system could bring up run charts from hundreds of metrics where data had been automatically recorded, and charts were available whenever anyone needed them.

Sounds fine, right? Unfortunately, this was not a happily-ever-after story, but an example of ways that different systems fail to speak to one another. But wait—there will be an answer to this dilemma.

The quality manager was looking for correlations. But he could look only at the Excel system that was used in his department. Meanwhile, on the other side of the data divide where the production manager and process engineers, in their own silo, used a different system for data analysis, a number of production-system metrics were in fact contributing to the problem metrics, but the correlation could not be identified. The two systems, sadly, could not talk to each other.

The happy accident lay in the quality manager’s discovery of CHARTrunner. Using CHARTrunner Lean, the quality manager removed the charting and data analysis from one of the systems—in this case, the quality department—and used CHARTrunner to create charts that visualized and compared metrics from both systems. So there was a happily-ever-after ending, after all.

In this example, there were only two systems separated by their approaches; in many organizations, there may be five or six different systems to be bridged with a CHARTrunner application.

How well do your systems collaborate and support each other? Check out CHARTrunner for help with bringing them together.

Bill Gates’ solution to the world’s biggest problems: Measure them!

Steve DaumLast weekend’s edition (Jan. 26-27) of The Wall Street Journal featured an article by Bill Gates (“My Solution to the World’s Biggest Problems: Measure them!”), in which he pointed out the importance of measurement systems. “From the fight against polio to fixing education, what’s missing is often good measurement and a commitment to follow the data. We can do better. We have the tools at hand,” he says.

Mr. Gates’ emphasis on measurement and data analysis is a nod to the quality movement – where many of the tools for tracking improvement were developed. SPC charting, SPC software, and other tools for continuous improvement share many of the aims of the Gates Foundation albeit in differing venues. Charting software, that can take the drudgery out of looking at vast amounts of data, makes it more likely that trends and problems are immediately apparent.

PQ Systems has been thinking about ways to make data easy to understand. If you find yourself “drowning in data but starved for information,”  SPC software solutions, such as CHARTrunner Lean and SQCpack, provide just the ticket to respond to the challenge.

Taming data demands statistical analysis: A control chart is worth a thousand numbers

Steve DaumData flows into spreadsheets and database tables at an astonishing rate. It is stacking up in personal computers, laptops, tablet computers, database servers, in the cloud, and even in smart phones. In these growing mountains of data there is insight to be found–insight that can lead to gains in quality and ultimately in profitability.

How do we extract the value in this data?

Continue reading