Level of Significance:
In hypothesis testing, you seek to decide whether observed results are consistent with chance variation under the "null hypothesis," or, alternatively, whether they are so different that chance variability can be ruled out as an explanation for the observed sample. The range of variation of samples that are consistent with the null hypothesis is examined, and if the observed sample is "too far out," the null hypothesis is rejected. The line you choose to divide "too far out" from "not too far out" is the level of significance. If you decide that the observed results must be more extreme than all but 1% of the samples that might be generated by the null model, then the level of significance is 1%.