The level of significance is usually denoted as “a” or alpha and refers to the probability of having the null hypothesis rejected when it is accurate or true. When the level is at 0.05, it implies that the risk of determining whether that a risk exists is 5% when there is no actual difference (Greenland, 2019). A P-value that is equal or lower than the significance level influences the rejection of the null hypothesis. Similarly, a hypothesis test tends to evaluate and analyze mutually exclusive statements to explain the one that is more likely to be correct based on the provided data. This paper evaluates the truthfulness of rejecting a 5% significance level null hypothesis when there exists a 90% specific alternative statement.
Since the alternative hypothesis has a power of 90%, the conclusion rejected the null hypothesis. The probability that the null hypothesis is true is only 5%, while 90% true for the alternative statement. This means that there are more reasons to believe that the alternative hypothesis is true relative to the contrary argument (Greenland, 2019). The validity of the alternative hypothesis influences the rejection of the null statements since it lacks sufficient evidence.
A given test is usually considered significant statistically in case the facts of the sample are unusually sufficient based on the null hypothesis. The significance level is sometimes referred to as the error rate because it is difficult to determine the accuracy of a hypothesis 100% and results depend on the position of the sample mean in the critical region. The significance level presents a statistical way of explaining the confidence in the conclusion. The 5% level is too low in comparison to 90% power for the alternative hypothesis explaining the rejection of the null statement.
Reference
Greenland, S. (2019). Valid p-values behave exactly as they should: Some misleading criticisms of p-values and their resolution with s-values. The American Statistician, 73(1), 106-114. Web.