A short note on the effect of sample size on the estimation error in Cp

Process capability indices such as C_p are used extensively in manufacturing industries to assess processes in order to decide about purchasing. In practice, the parameter for calculating C_p is rarely known and is frequently replaced with estimates from an in-control reference sample. This article explores the optimal sample size required to achieve a desired error of estimation using absolute percentage error of different C_p estimates. Moreover, some practical tools are created to allow practitioners to find sample size in different situations.     

Consequence of chitosan treating on the adsorption of humic acid by granular activated carbon

In this work, equilibrium and kinetic adsorption of humic acid (HA) onto chitosan treated granular activated carbon (MGAC) has been investigated and compared to the granular activated carbon (GAC). The adsorption equilibrium data showed that adsorption behaviour of HA could be described reasonably well by Langmuir adsorption isotherm for GAC and Freundlich adsorption isotherm for MGAC. It was shown that pre-adsorption of chitosan onto the surface of GAC improved the adsorption capacity of HA changing the predominant adsorption mechanism. Monolayer capacities for the adsorption of HA onto GAC and MGAC were calculated 55.8 mg/g and 71.4 mg/g, respectively. Kinetic studies showed that film diffusion and intra-particle diffusion were simultaneously operating during the adsorption process for MGAC.     

The effectiveness of control structure diagrams in source codecomprehension activities

Recently, the first two in a series of planned comprehension experiments were performed to measure the effect of the control structure diagram (CSD) on program comprehensibility. Upper- and lower-division computer science and software engineering students were asked to respond to questions regarding the structure and execution of one source code module of a public domain graphics library. The time taken for each response and the correctness of each response was recorded. Statistical analysis of the data collected from these two experiments revealed that the CSD was highly significant in enhancing the subjects' performance in this program comprehension task. The results of these initial experiments promise to shed light on fundamental questions regarding the effect of software visualizations on program comprehensibility     

Analytically Unobservable Failure Events

Based on computational approximations, product designers routinely simplify algebraic expressions of complex transfer functions, which, in turn, simplify post-design analysis. This practice is justified because both the simplified and actual transfer functions yield approximately equal average performance values. However, utilizing the design of a switching regulator circuit, it is shown that such simplified expressions underestimate output variation. The discrepancy between the actual and underestimated output variation spans an analytically unobservable failure event. Since the observable portion constitutes a partial characterization of product unreliability and quality problems, only a partial solution is possible at the design stage. This severely limits the effectiveness of concurrent product design, reliability, and quality assurance methodologies that are based on variation modeling and analysis.     

Inspection Error Effects on Performance Measures of a Multistage Sampling Plan

The effects of inspection error on performance measures of single and double sampling by attributes are well known for certain combinations of sample by lot dispositions. This paper generalizes previous work on double sampling to multistage sampling. It provides expressions for the O.C. curves, average outgoing quality and average total inspection in the presence of inspection error for all combinations of sample by lot dispositions. Furthermore, the sensitivity analysis is carried out from a more general algebraic standpoint.     

On the Relationship of General Designs and Moments of Estimators in Simple Linear Regression

Methods are developed for determining sampling designs in simple linear regression (SLR) when residuals are non-normal that permit use of the classical normality-based analyses. General designs (such as asymmetrical), wherein both sample size and location of independent variable values are determined, are considered. The methods are based on behavior of standardized third and fourth moments of regression estimators. All other regression assumptions are assumed to be true.     

Experimental measurement and thermodynamic modeling of cyclopentane hydrates with NaCl,KCl, CaCl2, or NaCl‐KCl present

Consistent phase equilibrium data for cyclopentane hydrates in presence of salts are vitally important to many industries, with particular interest to the field of hydrate‐based water separation via cyclopentane hydrate crystallization such as desalination. However, there are very little experimental equilibrium data, and no thermodynamic prediction tools. Hence, we set up a method to generate a great deal of much needed equilibrium data for cyclopentane hydrates in diverse saline solutions with a wide range of salt concentrations. Our method does furnish verified, reliable and accurate equilibrium data. Plus, three thermodynamic approaches are developed to predict equilibrium, and provide tools for simulations, by considering the kind of salt and concentrations. All three models are in very good accordance with experimental data. One method, using a new correlation between occupancy factor and water activity, might be the best way to obtain consistent, quick, and accurate dissociation temperatures of cyclopentane hydrate in brine. © 2018 American Institute of Chemical Engineers AIChE J, 64: 2207–2218, 2018