T – Test

The idea of the T-test came into the phase at the point of finding the difference of mean from the plotted graph
The angle of kurtosis might change but the mean will remain constant like when kurtosis changes the variance and other dependent variables in order to get this issue out of the box

William Sealy Gosset developed the T-test

For instance -> Compare two fields named A and B and need to compare them by sampling
It won’t be a perfect normal distribution
It’s an outline of the histogram, we will get the mean of both fields from the shape of the histogram and we will get the average of both

The mean tells us so much because we could have different distributions, depending on the difference in distribution or variance within that sample we can say the statistical difference between two or not

At that point, the T value comes into the picture it is the ratio of the difference between the two mena BY variability of the groups

The Numerator is considered as SIGNAL (Difference of mean)
The Denominator is considered as NOISE (Variability of groups)

Using this T value we test it for for Null hypothesis stating There is no Statistically significant difference between the samples, by checking for the critical value if the value is less than that we Don’t Reject that value or Null hypothesis. If the value is higher than that value, then we reject the Null hypothesis value.