Statistical tests of studies in psychology determine whether or not the results are significant (not due to chance) or not significant (due to chance)-note that to say ‘insignificant’ when answering an exam question is incorrect. Because of the nature of probability we can never be certain that results are 100% due/ not due to chance. This is why a level of significance is set. The level of significance is in the form of a p-value, which, in psychology, is usually set to p<0.05. This means that we can be sure that results are 95% not due to chance (accepted as significant). Type 1 and 2 errors occur when the p< value is set at the wrong level of significance. A type 1 error occurs when the value is set too high- for example, p<0.1, as this means that there is 10% probability that the results are due to chance. A type one error means that the researcher will accept that the results are significant, when they aren’t, and will therefore accept the alternative hypothesis instead of the null. A type 2 error occurs when the p value is set too low, for example, p<0.01. This level of significance is too strict, and therefore means that the researcher will think the results are not significant when they actually are (as this only allows for a 1% probability that results are due to chance)- meaning the researcher will accept the null hypothesis instead of the alternative. Note that for different research different levels of p<values are required. For example, when the study is required to be more specific or certain that the results are not due to chance, then the p-value is set lower/ stricter.