Parametric tests are useful and the most powerful tests for testing the significance or trustworthiness of the computed sample statistics. Their use is based upon certain assumptions. Which of this assumption is incorrect ?
1
When the variables described are expressed in nominal or ordinal scale and not in interval or ratio scales of measurement.
2
When the population values are normally distributed.
3
When the samples have equal or nearly equal variances and is particularly important to determine when the samples are small.
4
When the selection of one case in the sample is not dependent upon the selection of any other.