A mixed model applied to joint analysis in experiments with coffee blends using the least squares method
ABSTRACT The aim of the present study was to propose a mixed model for a sensory analysis of four experiments with blends of different standards of quality, including the species Coffea Arabica L. and Coffea Canephora. Each experiment differed in the proportions used to formulate the blends and the concentrations used in preparing the beverages, these being 7% and 10% coffee powder for each 100 ml of water. The response variables under analysis were the sensory characteristics of the beverage found in an assessment made by a group of trained tasters, considering taste, bitterness and a final score. Each description followed a numerical rating scale of intensity that ranged from 0 to 10. The model was implemented using the least squares method; this led to the conclusion that including random parameters in the model, represented by the experiments, made it possible to compare the effect of each component simultaneously for each of the experiments.
| Main Authors: | , , , , |
|---|---|
| Format: | Digital revista |
| Language: | English |
| Published: |
Universidade Federal do Ceará
2019
|
| Online Access: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1806-66902019000300345 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | ABSTRACT The aim of the present study was to propose a mixed model for a sensory analysis of four experiments with blends of different standards of quality, including the species Coffea Arabica L. and Coffea Canephora. Each experiment differed in the proportions used to formulate the blends and the concentrations used in preparing the beverages, these being 7% and 10% coffee powder for each 100 ml of water. The response variables under analysis were the sensory characteristics of the beverage found in an assessment made by a group of trained tasters, considering taste, bitterness and a final score. Each description followed a numerical rating scale of intensity that ranged from 0 to 10. The model was implemented using the least squares method; this led to the conclusion that including random parameters in the model, represented by the experiments, made it possible to compare the effect of each component simultaneously for each of the experiments. |
|---|