Specify control chart and capability settings for each measure

You can specify the control chart and capability analysis settings for each measure of a particular process for a particular product.

In This Topic

Control chart settings
Tests for control charts
Capability analysis options

Go to the Components page and select a product. Then select the process flow step of your product.
Open the process step and go to the Process Summary section.
Select Additional Settings to access the control chart and capability analysis options for each measure.

Note

These settings apply only to the control charts and capability analyses for this measure. To change the system default preferences, go to Control chart preferences and Capability analysis preferences.

Control chart settings

These control chart settings apply to each station of the measure and override the control chart settings for each station.

Subgroup size

Enter a value to use as the same subgroup size for all samples of the data collections.

Control chart

Select a control chart based on measure type and subgroup size.

Note

The control chart type and subgroup size must be the same at each station of the measure.

Continuous control charts

Continuous control charts plot continuous measurement process data, such as length or pressure, in a time-ordered sequence. The two main types of continuous control charts are charts for data collected in subgroups and charts for individual measurements.

Use an I-MR Chart to monitor the mean and variation of your process when you have continuous data that are individual observations not in subgroups.
Use an Xbar-R Chart to monitor the mean and variation of a process when you have continuous data and subgroup sizes of 8 or less.
Use an Xbar-S Chart to monitor the mean and variation of a process when you have continuous data and subgroup sizes of 9 or more.
Use an I-MR-R/S Chart to monitor the mean of your process and the variation between and within subgroups when each subgroup is a different part or batch.
Use an EWMA Chart to detect small shifts in the process mean, without influence by low and high values. The EWMA chart monitors exponentially weighted moving averages, which remove the influence of low and high values. The observations can be individual measurements or subgroup means.

Attribute control charts

Attribute control charts plot defects or defectives. Select your attribute control chart based on whether your data represent a count of defectives and follow a binomial distribution, or whether your data represent a count of defects and follow a Poisson distribution.

Use an NP chart to monitor the number of defective items where each item can be classified into one of two categories, such as pass or fail.
Use a P chart to monitor the proportion of defective items where each item can be classified into one of two categories, such as pass or fail.
Use a Laney P' chart (P' is pronounced as P prime) to monitor the proportion of defective items that are produced by your process and to adjust for overdispersion or underdispersion in your data.
Use a C chart to monitor the number of defects per unit, where each item can have multiple defects. You should use a C chart only when your subgroups are the same size.
Use a U chart to monitor the number of defects per unit, where each item can have multiple defects.
Use a Laney U' chart (U' is pronounced as U prime) to monitor the defect rate for your process and to adjust for overdispersion or underdispersion in your data.

Note

If you have a particular defective type that you want to monitor on its own control chart, you must set it up as a defective measure. If you have multiple defective types that you want to monitor together, aggregated on a single control chart, you must set it up as a grouped defective. For more information, go to Group quality attributes or monitor separately.

Control limit calculation method

Control limits are the horizontal lines above and below the center line that are used to judge whether a process is out of control. The upper and lower control limits are based on the random variation in the process. By default, the control limits are displayed 3 standard deviations above and below the center line.

Control limits are calculated from the process parameters. You can choose to use estimated process parameters or enter the known historical values to use to calculate the center line and control limits. For more information on control limit calculations, go to Control limit calculation details.

Calculate using recent data

You can specify how much data to use for the parameter estimates if you do not have known historical values.

Number of observations / Number of subgroups

For continuous measures, specify the number of observations; the default is 100 observations. For attribute measures, specify the number of subgroups; the default is 25 subgroups.
Using more data to estimate process parameters gives more accurate control limits.
Provide parameters

Enter the historical values for the parameters that Real-Time SPC uses to calculate the center line and control limits. If you do not have known parameters, use the Calculate using recent observations or Calculate using recent subgroups option.
Do not use control limits

You can suppress the display of control limits for any control chart. This setting affects the control charts for all the stations. Data are still plotted, but only Test 2, Test 3, and Test 4 are available.

Tests for control charts

Real-Time SPC provides eight tests for special causes for control charts with continuous data and four tests for special causes for control charts with attribute data. Use the tests to determine which observations to investigate, and to identify the specific patterns and trends in your data. By default, Real-Time SPC uses only Test 1. Select additional tests based on company or industry standards.

Note

To learn about the test options or to change the test preferences for all control charts, go to Control chart preferences.

Capability analysis options

This setting applies to each station of the measure and overrides the capability settings for each station.

Use the default normal distribution if your data follow a normal distribution. If you have nonnormal data, you can either transform the data to fit a normal distribution or select a nonnormal distribution that fits your data.

Normal distribution

Select to perform a normal capability analysis.

Normal distribution with Box-Cox transformation

Use the Box-Cox transformation if your nonnormal data are all positive (> 0) and you want to obtain estimates of within-subgroup (potential) capability as well as overall capability.

Select the lambda (λ) value to transform the data.

Optimal λ: Use the optimal lambda, which should produce the best fitting transformation.
λ = 0 (ln): Use the natural log of your data.
λ = 0.5 (square root): Use the square root of your data.
Specify λ: Other common transformations are square (λ = 2), inverse square root (λ = −0.5), and inverse (λ = −1). In most cases, you should not use a value outside the range of −2 and 2.

Fit distribution

Select the distribution that best fits your data and perform a nonnormal capability analysis.

Most often, it is best to use engineering and historical knowledge of your process to identify a distribution that fits your process data. However, Minitab^® Statistical Software has many tools, such as Individual Distribution Identification, that can help you assess the fit of various distributions.

Note

This setting applies only to the capability analysis for this measure. Changing transformation settings here will not affect the analyses preferences. To change the preferences for all capability analyses, go to Capability analysis preferences.