Capability Analysis (Binomial)

Overview | How to | Example

Overview

Capability Analysis (Binomial) generates process capability report for attribute data that follows the Binomial distribution. The report includes a

• P Chart to verify if the process is in statistical control

• Cumulative %Defective chart to verify if the data have a consistent estimate of %defectives

• Histogram of %Defective to help visualize the distribution of %defective of the sample data

• Defective Rate Chart to verify that the %defective is not affected by the sample size

• Binomial Plot (when subgroup size is constant) to verify that the expected %defectives are not affected by the observed %defectives

The most common types of Binomial data are records of defective output or Yes/No data. In order the use Capability Analysis (Binomial), you need to ensure that the following assumptions are valid:

• The outcome is binary or have only 2 possible result

• The probability of success is the same for all units

• The outcome of each unit is independent of each other

How to

At the Excel Menu (For Excel 2007, go to Add-ins first)

1. Choose ProcessMA > Quality Tools > Capability Analysis > Capability Analysis (Binomial)

2. In Defectives, select the column containing the data (Integer, >=0)

3. In Sample Sizes, select the column containing sample sizes (Integer, >Defectives)

4. In Constant Sample Size, enter the sample size if it is constant (Optional, Integer, >Defectives)

5. In Historical P, enter the historical proportion of defectives(Optional, Numeric, >0 & <1)

6. In Target Defective, enter the defective target (Optional, Numeric, >0 & <1)

7. Click OK

Example

You are working in a software company and you want to assess the responsiveness of the customer support service. You recorded the number of enquiries received and the number of enquiries unresolved after 2 days, for the last 30 days.

1. Open data worksheet by choosing ProcessMA > Tools > Data

2. Choose ProcessMA > Quality Tools > Capability Analysis > Capability Analysis (Binomial)

3. In Defectives, select AE - Unresolved

4. In Sample Sizes, select AF - Enquiries

5. Click OK

Results & Interpretation

The P Chart shows that the process is in control.  The Cumulative % Defective shows the overall defectives settles at 12.4%.  The rate of defectives seems to increase with sample size.  The process Z is only 1.15, which means that the process needs much improvement.

Copyright © ProcessMA