Process Analysis Button

Click the button to display the Process Analysis Procedures (Startup Panel). In industrial settings, process analysis refers to a collection of analytic methods that can be used to ensure adherence of a product to quality specifications. These methods include cause-and-effects diagrams (Ishikawa charts), process (machine) capability analysis, fitting measurements to non-normal distributions, analysis of Gage repeatability and reproducibility, Weibull and reliability/failure time analysis, and options for generating sampling plans.

The Process Analysis module provides an option to compute cause-and-effect (Ishikawa, or fishbone) charts from data; all general graphics facilities for labeling, including drawings, bitmaps, symbols, etc. are supported in those charts, to provide the tools for producing highly customized charts specifically tailored to the process of interest. This module also includes a comprehensive selection of options for computing process capability indices for grouped and ungrouped data (e.g., Cp, Cr, Cpk, Cpl, Cpu, K, Cpm, Pp, Pr, Ppk, Ppl, Ppu), normal/distribution-free tolerance limits, and corresponding process capability plots; in addition, you choose estimates based on general non-normal distributions (Johnson and Pearson curve fitting by moments), as well as all other common continuous distributions. Repeatability/reproducibility experiments with single or multiple trials can be generated and analyzed; results include estimates of the components of variance (repeatability or equipment variation, operator or appraiser variation, part variation, operator-by-part variation, operators-by-trials, parts-by-trials, operators-by-parts-by-trials). Results can be computed based on the range method or the ANOVA table. Additional statistics for the variance components can include the percent of tolerance, process variation, and total variation. The Weibull analysis options provide powerful graphical techniques for exploiting the power and the ability of the Weibull distribution to be generalized; you can produce Weibull probability plots and estimate the parameters of the distribution, along with confidence intervals for reliability. Probability plots can be computed for complete, single-censored, and multiple-censored data, and parameters can be estimated from hazard plots of failure orders. Estimation methods include maximum likelihood (for complete and censored data), weighting factors based on linear estimation techniques for complete and single-censored data, and modified moment estimators. STATISTICA includes graphical goodness-of-fit tests, and the Hollander-Proschan, Mann-Scheuer-Fertig, and Anderson-Darling tests of goodness of fit. The options for generating sampling plans include fixed and sequential sampling plans for normal and binomial means, or Poisson frequencies; results include the sample sizes, operating characteristic (OC) curves, plots of the sequential plans with or without data, expected (H0/H1) run lengths, etc.

Comprehensive selections of methods for estimating variance components for random effects are also available in the designated STATISTICA Variance Components module, and the General Linear Models (GLM) module. The Power Analysis module also provides options for computing required sample sizes and power estimates for a large number of research designs (e.g, ANOVA) and data types (e.g., for binary counts, censored failure time data, etc.).