6Sigma Intermediate Graphical Analysis

Creating a Bar Chart on Excel

1. Enter data within correct labels 2. Highlight the cells that you want to chart as well as the labels for the data/cells 3. Select Insert > Chart > Bar Chart 4. Select appropriate bar charts 5. Use Excel formatting tools to customize the chart title, colors, and labels

Creating A Pie Chart

1. Must have ordinal or nominal data that is broken into categories 2. Highlight the cells containing the data plus cells containing the data labels 3. Select Insert > Charts > Pie Charts 4. Use Excel formatting tools to customize the chart title, colors, and labels

Creating a Scatter Diagram

1. Must have ordinal or nominal data that is broken into categories 2. Highlight the cells containing the data plus cells containing the data labels. Must highlight two sets of data that you want to compare 3. Select Insert > Charts > Scatter 4. Use Excel formatting tools to customize the chart title, colors, and labels

Creating a Stacked Bar Chart

1. Must have ordinal or nominal data that is broken into categories 2. The categories must be the same for each data set so that the total sub-category numbers equals the total of the main category. ex: 3 bags broken into numbers of marbles, the number of marbles are broken further down into categories of colors 3. Highlight the cells containing the data plus cells containing the data labels 4. Select Insert > Charts > Bar Charts > Stacked Bar Chart 5. Use Excel formatting tools to customize the chart title, colors, and labels

Ordinal Data

1. A higher form of data than nominal data. The numbers provide meaning, the numbers are qualitative in nature, but they are also ranked in an order that makes sense 2. data exists in categories that are ordered but differences cannot be determined or they are meaningless. (Example: on a scale 1 to 10, Suzy rated movie A as a 10 and movie B as a 9, the conclusion is Suzy likes movie A better, but exactly how much more she liked the movie is not discernible using ordinal data.)

Pie Chart Limitations

1. Don't always carry the weight that a more advanced statistical representation might because business employees are so used to seeing them 2. Can also be easily manipulated like bar charts 3. Usually fail to easily display changes over time 4. Can be difficult to visualize exact values when presented with a pie chart.

Pie of Pie Chart

A pie chart with a slice that is further broken into a separate second pie chart

Pie Chart

A visual tool that shows the relationship of a part to a whole.

Nominal Data

1. Nominal is considered to be the lowest data classification level and simply involves applying number labels to a qualitative description so statistical analysis programs and tests can be applied to the data. The numbers assigned to each category don't provide any information about whether the data is better or worse than other data in the listing - in nominal data, numbers don't reflect a scale. 2. data of categories only. Data cannot be arranged in an ordering scheme. (Gender, Race, Religion)

Scatter Diagram Drawbacks

1. Not as familiar to employees as bar, pie, or line charts 2. There is also a risk that individuals who don't have an understanding of statistical analysis will mistake correlation for causation, which can lead to incorrect decisions.

Pie Chart Benefits

1. The ability to summarize large amounts of specific data types in a visual format 2. simplicity, pie chart is one of the simplest types of graphs 3. The ability to identify obvious problems with data or calculations 4. Pie charts usually require very little extra explanation when labeled correctly 5. Display the relevance of subset data within a total data set.

Why are 3-D charts helpful?

3-D charts are helpful when presenting similar charts, assisting in differentiating between information in the teams' presentation.

What is the reason teams use graphs?

A graph is visually appealing and quicker to read than data tables.

Why would teams require a more complex analysis?

A more complex analysis may be required to discover outliers, relationships, and trends.

What is the downside to using a bar chart?

Bar charts fail to reveal key information about trends that are not part of the specific design of the chart and rarely provide detailed data.

What does a bar chart require?

Bar charts require nominal or ordinal data that is classified according to qualitative information.

Visual Depictions

These are tools that make it easier for 6Sigma professionals or sponsors to retell the story to others, which can be helpful for training, building cultural buy-in for a process change, or even resource requests.

Stacked Bar Charts

Lets you display the total nominal or ordinal data for each category while also breaking that information into color coded category ex: a category of sports also have bar charts split between win percentages of home team vs visiting team

X-bar Control Chart

One of the most commonly used control chart to plot the mean of a sample over time - or the mean of samples taken over time, in the case of an active process

Graphical Analysis Tools

Pareto Charts (ch. 5 & 14) Run Charts (ch. 13) Box Plots (ch. 14) Introduction to Control Charts (ch. 16) Introduction to Scatter Diagrams (ch. 14)

What is the biggest benefit of using a bar chart?

They are recognizable and easy to read.

Bar Chart's Limitation

Rarely on their own provides detailed data about causes or patterns in data, easy to manipulate colors, order, and layout of a bar chart to influence the intended message

Bar Charts

Recognizable and easy to create and read. Uses both nominal or ordinal data. Other benefits: 1. the ability to summarize large data sets in a simple visual format 2. the ability to clarify trends 3. a well-formatted chart allows most people to easily estimate important values 4. the ability to visually check data and identify areas where data might be skewed 5. the ability to easily display data sets that range above and below zero on the same chart

Why are scatter diagrams beneficial?

Scatter diagrams are beneficial because they can help teams visually see the relationship between two factors in a process

How do scatter diagrams assist teams?

Scatter diagrams typically help teams see whether there is no correlation, weak correlation, or positive or negative correlation.

Creating an X-bar Control Chart

See pg. 262-269

3-D Bar or Column Chart

Similar to the 2-d column chart, but with added visual appeal to a presentation. 3-d charts are helpful if you are presenting a number of similar-looking charts in a row, as it helps to differentiate between information in your presentation.

Which is a benefit of using a pie chart?

Simplicity; the pie chart is one of the simplest types of graphs.

Column Chart

The basic and most common bar chart, the visual columns representing each data category rise vertically or horizontally.

What are the benefits of statistical analysis software?

The software reduces the chance of calculation errors and increases the accuracy of analysis and conclusions offered by experts.

How is a stacked bar chart created?

The teams must have ordinal and nominal data that is broken into categories.

XY Scatter Diagrams

Visual aid that help teams see the relationship between two factors in a process, whether there is no correlation, weak correlation, or positive or negative correlation. It's important to realize that correlation as depicted on a scatter diagram doesn't necessarily mean causation. Two variables can be closely related without one causing changes in the other.

Why is visual analysis extremely helpful?

Visual analysis is helpful to those that are not trained in statistics.

Negative Correlation

When variable 2 is related to a decrease in variable 1, or vice versa

Positive Correlation

When variable 2 is related to an increase in variable 1, or vice versa.