S A Jimenez-Marquez | Search PubMed

PubMed2002

Statistical data validation methods for large cheese plant database.

Production data of the cheesemaking process are used to monitor milk fat and protein recoveries in cheese, cheese yield, and composition and eventually to predict these parameters. Due to the large impact of these factors on cheese quality and plant profitability, it is very important to use reliable data for analysis, modeling, and control of the process. This paper tested six methods for detecting erroneous data in industrial cheesemaking databases. The data analyzed came from 4 yr of stirred-curd Cheddar cheese production in an industrial cheesemaking facility, comprising over 10,000 vats. Single vat outliers were detected using a simple statistical criterion of mean +/- 3.6 SD on single variable distributions, Fourier series modeling of seasonal variables (fat, protein, lactose, and total solids in milk, and protein in whey), and the multivariate Mahalanobis outlier analysis. Detection of outlier productions (corresponding to several vats) was done by applying the mean +/- 3.6 SD criterion to variables obtained through calculating the fat mass balance, fat retention coefficient, and yield efficiency. Data treatment enabled the detection of outlier data, but also pinpointed variables with a low reliability (manually registered times). Single variable and multivariable methods proved complementary, and the use of both types of methods is recommended when validating an existing database.

Analysis of Variance↗

PubMedDate not supplied

Variations of moisture measurements in cheese.

Data were accumulated during interlaboratory trials for cheese moisture determination from laboratories using officially recognized methods: AOAC; International Dairy Federation, and Standard Methods for the Examination of Dairy Products (SM). In one trial, ranges of means of 5 cheeses were 0.67, 0.56, and 0.19% for 5, 9, and 8 laboratories, respectively. The lower ranges for the SM method were typical of 3 other interlaboratory trials, with ranges of 0.27, 0.34, and 0.34% for 6, 7, and 5 laboratories, respectively. Within one laboratory, there were no significant differences among the 3 methods, but they all gave about 0.2% lower results than 2 other methods, one using freeze-drying, followed by drying in a vacuum, the other using cheese that was spread on sand and dried in a vacuum oven for 24 h. This finding indicated that none of the officially recognized methods removed all the moisture. Data showed that many laboratories tended to give either higher or lower results than the mean of all of them in a series of 7 interlaboratory trials. Constant results, free of biases or systematic errors, are important in application of formulas for prediction of yield of cheese for purposes of yield control, but are difficult to obtain. It is proposed that results by a laboratory in interlaboratory trials be compared with those obtained by one or more reference laboratories using a method that removes all the moisture from cheese. The difference would be applied as a constant in the predictive yield formula. That difference would likely be best as a running mean of differences in an ongoing series of trials. The reference laboratories would use frozen samples for quality control to ensure uniformity of results among trials. Mean moistures of 36.10 and 36.11% were obtained on subsamples before and after freezing for 7 months.

Cheese↗