Quality Control

The Quality Control module is a core component of UNISTAT Standard Edition, offering powerful statistical process control (SPC) capabilities.

Variable Control Charts: R Chart, S Chart, Variance Chart, X Bar Chart, Moving Average Charts, Exponential Weights Moving Average Chart, CUSUM Chart, X Chart (Levey-Jennings).

Two types of data can be analysed: Raw Values and Samples or Summary Data. It is possible to specify the target level, control and warning lines as multiples of standard deviation, moving average or exponential weights moving average, and whether individual sizes or average sample size is to be used.

An Operating Characteristic Curve (or OC curve) can be drawn for X Bar chart.

Attribute Control Charts: C Chart, U Chart, Np Chart, P Chart.

It is possible to specify the target level, control and warning lines as multiples of standard deviation, moving average or exponential weights moving average. An Operating Characteristic Curve (or OC curve) can be drawn for all attribute control charts.

Pareto Chart: Cumulative percentages or cumulative values can be displayed. Output also includes a summary table.

Hotelling’s T-Squared Analysis: Chart summary, table of means and average within-sample covariance matrix are displayed.

Weibull Analysis

Weibull Analysis: Two or three parameter Weibull models can be estimated employing maximum likelihood or ordinary least squares (OLS) regression methods. The program reports the estimated parameters, their confidence intervals and the covariance matrix and features an interpolation facility.

If the method is OLS, then you can choose to regress Y on X (the default) or X on Y.

Weibull chart is drawn with a true gompit scale Y-axis. You can also generate what is called Weibull paper (or Weibull probability paper) using UNISTAT’s X-Y Plots procedure by selecting the Y-axis scale as gompit and the X-axis scale as log base 10.

Process Capability Analysis: Model parameters can be estimated with Johnson or Box-Cox transformation or without transformation. Most capability indices are reported with their confidence limits. Capability Indices with Overall Standard Deviation: Cp, Cpl, Cpu, Bissell Cpk, ZSW Eq 6 Cpk, ZSW Eq 8 Cpk, Chang Cpm, Boyles Cpm, NIST Cpm, Cpmk, Cs, Cpm+, Cjkp Capability Indices with Pooled Standard Deviation: Cp, Cpl, Cpu, Bissell Cpk, Ccpk Nonparametric Capability Indices: Median, 0.5% Quantile, 99.5% Quantile, Cnpk

Data Transformation: Box-Cox and Johnson transformations

Gage R&R Analysis

UNISTAT can perform Gage R&R Analysis employing Average and Range or Analysis of Variance (ANOVA) methods. Output includes ANOVA table, gage variances, standard deviations and confidence intervals. Range Chart and Average Chart can be displayed in Stacked or Unstacked form.

Gage R&R, Repeatability EV, Reproducibility AV, Part PV and Total TV statistics can be displayed with their variances, standard deviations, confidence limits and % tolerance. It is possible to include or omit the interaction term between parts and operators.