Purpose
Analyse results
from the A-not-A test.
- Discrimination_AnotA.xls
- Data type is binary.
Background
The A-not-A discrimination test is a
variation of the paired comparison test. It is an unspecified test
with a probability of guessing of 0.5.
The panellist is presented with the
first product (A), which is then removed after evaluation.
A second product is then presented,
and the panellist decides whether it is the same as A or not. As
part of the test design multiple products may be compared with A in a monadic
protocol. The order of the samples is randomized.
Options
- Reference
Product: Select which product should be your reference product. This is the
first product in the test(A).
- Correction:
If yes, apply the continuity correction
for 2x2 contingency tables.
- Number of Decimals for Values: Required number
of decimals for values given in the results.
- Number of Decimals for P-Values: Required number
of decimals for any p-values given in the results.
Results and Interpretation
- Contingency table: This is a n x 2
contingency table of the responses, where n is the number of products.
The first row totals the responses when the reference product (A) was tested.
Subsequent rows total the responses when the other products were tested.
- A chi-squared test is then performed on the
contingency table. The following values are returned:
- Chi-squared value
- The Critical Chi-Squared value at a 5%
significance
- Degrees of freedom
- P-value at 5% significance
If
the p-value is < 0.05 for the chi-squared test, it can be concluded that the
reference product (A) is significantly different to the other products. Note that
even if you conclude a difference, this does not imply similarity.
- D-prime.
D-prime indicates the size of the
difference between the products. The following values are returned:
- d-prime
- Lower and upper 95% confidence intervals for
d-prime
- P-value for Fisher’s Exact Test performed on
the contingency table.
Note that if one of the cells in the contingency table is zero, the d-prime cannot be calculated.
- The R package sensR (Rune Christensen and Per B.
Brockhoff) is used.
- The AnotA
function is used to calculate d-prime.
References
- ISO 8588:1987 – Sensory Analysis
– Methodology – ‘A’ – ‘not A’ Test
- Lawless, H.T. and Heymann,
H. (2010). Sensory Evaluation of Food – Principles and
Practices. Springer.