“Delivering Results with Measurement and Analysis”

15
Robin Hammers Fall 2010 1

description

“Delivering Results with Measurement and Analysis”. Robin Hammers Fall 2010. Overview. Change Purpose of Cause Analysis Charting Trend Charts Pareto Charts Root Cause Analysis. Change. In a universe of uncertainty, few things are more certain than change - PowerPoint PPT Presentation

Transcript of “Delivering Results with Measurement and Analysis”

Page 1: “Delivering Results with Measurement and Analysis”

Robin HammersFall 2010

1

Page 2: “Delivering Results with Measurement and Analysis”

Change Purpose of Cause Analysis Charting Trend Charts Pareto Charts Root Cause Analysis

2

Page 3: “Delivering Results with Measurement and Analysis”

In a universe of uncertainty, few things are more certain than change• This tool has the capability of changing the

way you: collect data trend data analyze data report data feel about data

3

Page 4: “Delivering Results with Measurement and Analysis”

4

Page 11 Page 14 Page 15Page 13

Page 5: “Delivering Results with Measurement and Analysis”

5

Cause: Admin 237Root Cause: Shipper numbers are 12 digits and very easy to transposeCorrective Action: Near term, buddy system will be utilized to have a verification of shipper numberPreventive Action: Install and train bar code systemWho: DaveDue: March 2009

Cause: Late Receipt 136Symptom: Shipments are delivered to shipping after the cutoff timeRoot Cause: Various and not quantifiable at this time. Corrective Action: A check sheet has been put in place to begin data collection and resolveWho: MarieDue: February 2009

Cause: Loader 28Root Cause: Trend continues downward as additionalstaff are trained on the new autoloaderCorrective Action: Continue to train staff and monitor resultsWho: MarkDue: Ongoing

211

423

321276 271

311 327

411

312

392 388 401

0

100

200

300

400

500

Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

2008 Quantity Late

213

63 62

Admin Loader Late Receipt

Avg Causes forJan-Dec 2008

237

136

28

Admin Late Receipt Loader

Dec 2008 Causes

9897

98 98 98 98 9897 97 97 97 97

Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

2008 Shipments % on Time

Cause Analysis Chart

Page 6: “Delivering Results with Measurement and Analysis”

6

Page 7: “Delivering Results with Measurement and Analysis”

7

Page 8: “Delivering Results with Measurement and Analysis”

8

Page 9: “Delivering Results with Measurement and Analysis”

9

Cause: Admin 237Root Cause: Shipper numbers are 12 digits and very easy to transposeCorrective Action: Near term, buddy system will be utilized to have a verification of shipper numberPreventive Action: Install and train bar code systemWho: DaveDue: March 2009

Cause: Late Receipt 136Symptom: Shipments are delivered to shipping after the cutoff timeRoot Cause: Various and not quantifiable at this time. Corrective Action: A check sheet has been put in place to begin data collection and resolveWho: MarieDue: February 2009

Cause: Loader 28Root Cause: Trend continues downward as additionalstaff are trained on the new autoloaderCorrective Action: Continue to train staff and monitor resultsWho: MarkDue: Ongoing

Page 10: “Delivering Results with Measurement and Analysis”

10

Cause: Admin 237Root Cause: Shipper numbers are 12 digits and very easy to transposeCorrective Action: Near term, buddy system will be utilized to have a verification of shipper numberPreventive Action: Install and train bar code systemWho: DaveDue: March 2009

Cause: Late Receipt 136Symptom: Shipments are delivered to shipping after the cutoff timeRoot Cause: Various and not quantifiable at this time. Corrective Action: A check sheet has been put in place to begin data collection and resolveWho: MarieDue: February 2009

Cause: Loader 28Root Cause: Trend continues downward as additionalstaff are trained on the new autoloaderCorrective Action: Continue to train staff and monitor resultsWho: MarkDue: Ongoing

211

423

321276 271

311 327

411

312

392 388 401

0

100

200

300

400

500

Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

2008 Quantity Late

213

63 62

Admin Loader Late Receipt

Avg Causes forJan-Dec 2008

237

136

28

Admin Late Receipt Loader

Dec 2008 Causes

9897

98 98 98 98 9897 97 97 97 97

Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

2008 Shipments % on Time

Page 11: “Delivering Results with Measurement and Analysis”

11

“Only the inquiring mind solves problems." -- Edward Hodnett

Page 12: “Delivering Results with Measurement and Analysis”

12

Check Sheet/Frequency Distribution Table

Check Sheets, or Frequency Tables, are often the first step in collecting data to make data-driven decisions. They begin the process of translating “opinions” into “facts”. A check sheet is simply an easy to understand form used to tally occurrences of events. The purpose of a Check Sheet is to enable you to answer the question “How often are certain events happening?” based on concrete data. Check sheets are simple to create and use. Follow these basic tips:

1. Decide exactly what event you plan to monitor and agree on how you will count the occurrences of the event. Everyone must be looking for the same thing and counting it in the same manner.

2. Decide on the time period during which you will collect the data. The time period should provide you with enough data points to draw a conclusion. This could require as little as an hour, as much as a month, or even longer.

3. Design a Check Sheet for collecting data, using the sample below as a guide. The form should be clear and easy to understand. Columns should be wide enough to enter plenty of data (tally marks).

4. Collect the data for the agreed upon period of time. Be consistent and objective in recording your observations and make sure that all people performing the data collection are following the same standards. Make sure sufficient time is set aside for the task of gathering data.

Check Sheet/Frequency Table for Material Defects Defect Week 1 Week 2 Week 3 Week 4 Week 5 Week 6 Total

Particle IIII II III I I III 14 Hole IIII II I II III IIII 16 Residual Material II I III I III I 11 Tear I I III I I II 9 Total 50

It is easy to see how much can be learned from this. You not only know precisely how many of each defect you have, you also know how many total on in which weeks they occurred. Now that you have actual frequency data, you next step might be to display the Check Sheet data in Pareto Chart to gain even more insights into the events you are monitoring.

Page 13: “Delivering Results with Measurement and Analysis”

13

Trend Charts

Trend Charts or Run Charts, are employed to visually represent data. They are used to monitor a system to see whether or not the long range average is changing. Run charts are the simplest tool to construct and use. Points are potted on the graph in the order in which they occur. It is common to graph the results of a process such as equipment downtime, yield, scrap, human error or productivity over time.

Run Chart of Travel Time

0

5

10

15

20

25

30

35

40

1/1 1/3 1/5 1/7 1/9 1/11 1/13 1/15 1/17 1/19

Date

Tra

vel T

ime

A danger in using a Run Chart is the tendency to see every variation in data as being important. The Run Chart, like the other charting techniques, should be used to focus attention on truly vital changes in the system. One of the most valuable uses of Run charts is to identify meaningful trends or shifts in the average. For example, when monitoring any system, it is expected that we should find an equal number of points falling above and below the average. Statistical analysis should be applied prior to making any changes.

Page 14: “Delivering Results with Measurement and Analysis”

14

Pareto Analysis/Pareto Charts

Pareto Analysis is a technique used to help you determine which sources of a particular problem are most important and should be attacked first. For example, Pareto Analysis might be used to determine which Planes have the most drawing redlines, or which Ground Control Stations have the most software revisions. By focusing attention on the major contributor(s) to a problem, we can get the greatest return for our efforts. Because Pareto Analysis helps to prioritize problem solving efforts it is to the Problem Solver what the Compass is to the Sailor.

The result of a Pareto Analysis is a special type of bar graph called a Pareto Chart. Pareto Charts display frequency data in an easy to understand format, showing you at a glance which problems occur most frequently. In the example below, the two largest causes of non conformances are clearly Redline changes and Workmanship. If we focus on reducing the occurrence of these issues we can expect to have the biggest overall impact on non conformances.

Pareto Chart of Non Conformances

0

1

2

3

4

5

6

7

8

9

Redline Workmanship Administrative Software Change Hardware Change

Fre

qu

ency

Page 15: “Delivering Results with Measurement and Analysis”

15

The 5 Whys

Asking "Why?" may be a favorite technique of your three year old child in driving you crazy, but it could teach you a valuable quality lesson. By repeatedly asking the question "Why", you can peel away the layers of symptoms which can lead to the root cause of a problem. Very often the professed reason for a problem will lead you to another question. Although this technique is called "5 Whys," you may find that you will need to ask the question fewer or more times than five before you get to the root cause.

Benefits of The 5 Whys Helps to identify the root cause of a problem Determine the relationship between different root causes of a problem One of the simplest tools; easy to complete

When Is 5 Whys Most Useful?

When problems involve human factors or interactions. In day-to-day business life; it can be used any time

5 Whys Example Problem Statement: You are on your way home from work and your car stops in the middle of the road. 1. Why did the car fail? - Out of gas 2. Why did you run out of gas? - Gas gauge said it was ¼ full 3. Why did you get stranded if it was ¼ full? - The gas gauge is broken 4. Why was the gas gauge broken? - Car is 15 years old 5. Replace the gas gauge. Had you simply filled up the car, it may happen again