If we reject null hypothesis, when actually it is true it is known as -

Ans. is 'a' i.e., Type I error Statistical errors o Statistical errors are used to describe possible errors made in statistical decision. o Before reading about the types of error you must know null hypothesis because these tests are related to null hypothesis. o Null hypothesis says -3 Any kind of difference or significance you see in a set of data is due to chance and not significant that means there is no variation (difference) exists between variables. o Null hypothesis testing (e.g., in Chisquare test) is used to make a decision about whether : - i) The data contradict the null hypothesis ---> That means there is true difference (which is significant) between variables and it is not due to chance. or ii) The data approve the null hypothesis ---> There is no difference between variables and the difference you see is due to chance. Now see types of error : ? There are two basic type of statistical errors : ? 1) Type I error 2) Type II error Type I error It is also known as an error of first kind or a-error or false positive. o This type of error rejects null hypothesis when it is true False rejection of null hypothesis. o That means in real there is no difference (as null hypothesis says) but we observe a difference (by rejecting the null hypotesis due to error). In very simple words "we observe a difference when it is not true" false positive. o One of the simplest example of this would be if a test shows that a women is pregnant when in reality she is not, i.e., she is false positive for pregnancy. o Probability of type-I error is given by '13-value' (probability of declaring a significant difference when actually it is not present). o Significance (a) level is the maximum tolerable probability of type I error. o Significance (a) level is fixed in advance and calculation of P value (probability of type I error) can be less than, equal to or greater than the significance (a) level. o If the probability of type I error (P -value) is less than significance (a) level, the results are declared statistically significant. Therefore, to declare the results statistical significant, type I error (a-level) should be kept to minimum . o Type I error is more serious that type II error. Type II error It is also known as an error or second kind or error or false negative. o This type of error accept/fail to reject the null hypothesis when it is false -->False acceptance of null hypothesis. That means we fail to observe a difference when in truth there is one --4 False negative. o An example of this would be if a test shows that a woman is not pregnant when in reality she is i.e., she is false negative.