Chi-Square Test:
Statistical analysis can be used for examining and verifying whether the observed data of a cross-fit differs from the predicted or expected occurrences. This is called goodness of fit. The goodness of fit of the data to the predicted or expected values can be determined by a simple statistical test, known as Chi-Square Test.
By Chi-Square analysis, it can be determined whether the data fits exactly with the predicted data or differs from it and how much is the deviation. It also helps in determining the probability that the deviation of the observed ratio from the predicted ratio is due to chance and not to some other factors, such as experimental conditions, biased sampling, or the wrong hypothesis.
- If the probability (p) of the observed ratio is equal to or less than 5 in 100, i.e, p=5/100 = 0.05. The deviation between the expected and observed ratio is considered significant. The deviation isn’t only because of chance.
- If the probability is 1 in 100 or less, i.e, p = 1/100 = 0.01. The deviation is highly significant and some non-chance factor is certainly operating.
- If the probability is greater than 0.05, the deviation isn’t considered statistically significant and can be expected on the basis of chance alone.
The Chi-Square value x2 is used to estimate how frequently the observed deviation can be expected to occur strictly as a result of chance. The formula used in Chi-Square analysis is:
x2 = ∑ (o – e)2 / e
Where,
-
o is the observed value for a given category
e is the expected value for the same
∑ represents the sum of calculated values for each category of the ratio
(o – e) is the deviation in each case and can be represented by d
Therefore, the equation can be reduced to
x2 = ∑ d2 / e