Analysis Statistics (analysis + statistics)

Distribution by Scientific Domains

Kinds of Analysis Statistics

  • survival analysis statistics


  • Selected Abstracts


    Survival Analysis Applied to Sensory Shelf Life of Yogurts,I: Argentine Formulations

    JOURNAL OF FOOD SCIENCE, Issue 7 2005
    Ana Curia
    ABSTRACT: :Sensory shelf lives of Argentine commercial stirred yogurts of different compositions stored at 10 °C were studied. Variations were as follows: fat-free and whole-fat, and vanilla and strawberry flavors. Yogurts were tested between 0 and 84 d of storage by consumers who expressed their acceptance or rejection of each sample; yogurts also were measured overall, as well as their attribute acceptability, with a hedonic scale. Survival analysis statistics were used to estimate shelf lives. Considering 25% of consumers rejecting the product, shelf lives were between 28 and 41 d; thus, a unique shelf life for this product does not seem reasonable. A log-linear model and a direct quantile comparison formula were introduced to analyze the effect of formulation on rejection time distributions and shelf life values, respectively. Overall, fat-free yogurts had lower shelf lives than whole-fat yogurts. [source]


    Survival Analysis Applied to Sensory Shelf Life of Yogurts,II: Spanish Formulations

    JOURNAL OF FOOD SCIENCE, Issue 7 2005
    Ana Salvador
    ABSTRACT: Sensory shelf lives of commercial Spanish yogurts stored at 10 °C were studied. Yogurts were strawberry flavored and differed in fat content (free and whole-fat) and consistency (stirred and set-style). Yogurts were tested between 0 and 90 d of storage by consumers who expressed acceptance or rejection of each sample and measured overall and attribute acceptability on a 9-point hedonic scale. Survival analysis statistics were used to estimate sensory shelf lives. Considering 25% of consumers rejecting the product, shelf lives varied from 38 to 69 d, depending on the composition, so if useful life were to be established using sensory criteria, a single shelf life for yogurt would not appear to be very appropriate. A log-linear model and a direct quantile comparison formula were introduced to analyze the effect of formulation on rejection time distributions and shelf life values, respectively. Fat-free yogurts had shorter shelf lives than whole-fat yogurts. Acceptability of yogurts measured on a 9-point hedonic scale varied less than percentage rejection over the storage times. [source]


    CURRENT-STATUS SURVIVAL ANALYSIS METHODOLOGY APPLIED TO ESTIMATING SENSORY SHELF LIFE OF READY-TO-EAT LETTUCE (LACTUCA SATIVA)

    JOURNAL OF SENSORY STUDIES, Issue 2 2008
    MABEL ARANEDA
    ABSTRACT The objective of the present work was to develop a method for predicting sensory shelf life for situations in which each consumer evaluates only one sample corresponding to one storage time. This type of data is known as current-status data in survival analysis statistics. The methodology was applied to estimate the sensory shelf life of ready-to-eat lettuce (Lactuca sativa var. capitata cv."Alpha"). For each of six storage times, 50,52 consumers answered yes or no to whether they would normally consume the presented sample. The results were satisfactory, showing that the methodology can be applied when necessary. The Weibull model was found adequate to model the data. Estimated shelf lives ± 95% confidence intervals were 11.3 ± 1.2 days and 15.5 ± 0.9 days for a 25% and a 50% consumer rejection probability, respectively. PRACTICAL APPLICATIONS When considering shelf-life evaluations by consumers, the first idea is to have each consumer evaluate six or seven samples with different storage times in a single session. To do this, a reverse storage design is necessary, and in the case of a product such as lettuce, it would lead to different batches being confused with storage times. The methodology proposed in this article avoids this problem by having each consumer evaluate a single sample. Another issue with consumers tasting several samples in a single session is how representative this situation is of real consumption. The present methodology allows for a consumer to take home, e.g., a bottle of beer with an established storage time, and later collecting the information as to whether they found the beer acceptable or not. This is a situation much closer to real consumption. [source]


    CONSUMER PERCEPTION OF SANDINESS IN DULCE DE LECHE

    JOURNAL OF SENSORY STUDIES, Issue 2 2008
    ANA GIMÉNEZ
    ABSTRACT Sandiness, one of the most common defects of dulce de leche, is caused by lactose crystallization. In order to study consumer reaction to the presence of different levels of this defect, survival analysis statistics was applied to the consumer acceptance/rejection data of the samples. Limits for this defect were estimated by working with 10% and 25% consumer rejection probabilities. The consumers were also asked to score the sample sandiness according to their perception, using a 9-point scale. Cluster analysis and correspondence analysis performed showed the heterogeneity of the consumer responses toward sandiness in dulce de leche. Significant correlations were established between consumer sandiness and the number of crystals and sandiness as measured by a panel of trained assessors, the latter being the best indicator of sandiness as perceived by the consumers. It could be established that the consumers' and assessors' sandiness perception is clearly influenced by the presence of agglomerates, their size distribution and number. PRACTICAL APPLICATIONS Sandiness is an important defect for a segment of consumers who rejected samples with high levels of sandiness, suggesting the importance of avoiding the occurrence of this defect. Survival analysis methodology was used to estimate the maximum level of sandiness in dulce de leche before consumers reject it. As sandiness is a sensory defect that often limits the shelf life of dulce de leche, the calculated sensory limits could be used in future studies to estimate the sensory shelf life of dulce de leche. [source]


    Nested clade analysis statistics

    MOLECULAR ECOLOGY RESOURCES, Issue 3 2006
    DAVID POSADA
    Abstract Nested clade analysis (NCA) is a flexible and powerful method to study the phylogeography of species and populations, implemented in the software geodis. Despite the popularity of this method, an explicit description of the exact equations used to compute the NCA statistics has never been published. Given the importance of the methodology and increased interest in exactly how it works, here we describe the exact equations implemented in the program geodis for the calculation of these statistics. [source]


    Survival Analysis in Clinical Trials: Past Developments and Future Directions

    BIOMETRICS, Issue 4 2000
    Thomas R. Fleming
    Summary. The field of survival analysis emerged in the 20th century and experienced tremendous growth during the latter half of the century. The developments in this field that have had the most profound impact on clinical trials are the Kaplan-Meier (1958, Journal of the American Statistical Association53, 457,481) method for estimating the survival function, the log-rank statistic (Mantel, 1966, Cancer Chemotherapy Report50, 163,170) for comparing two survival distributions, and the Cox (1972, Journal of the Royal Statistical Society, Series B34, 187,220) proportional hazards model for quantifying the effects of covariates on the survival time. The counting-process martingale theory pioneered by Aalen (1975, Statistical inference for a family of counting processes, Ph.D. dissertation, University of California, Berkeley) provides a unified framework for studying the small- and large-sample properties of survival analysis statistics. Significant progress has been achieved and further developments are expected in many other areas, including the accelerated failure time model, multivariate failure time data, interval-censored data, dependent censoring, dynamic treatment regimes and causal inference, joint modeling of failure time and longitudinal data, and Baysian methods. [source]