The teacher continued: just Was she unfortunate enough to have auditioned in the room with a higher cut-off?
No. That would be making the assumption that if she had auditioned in Room B, the room B judges would have given her the exact same numeric score the room A judges did. It is reasonable to assume that different judges will judge differently, and some judges will score “easier” than others. When the judges in room A heard an “average” singer (the ‘mean’, or 50% percentile), they scored it as a 190. In contrast, when the judges in room B heard an “average” singer, they scored it as a 180.5; almost 10 points lower. The conclusion that can be drawn from this is that the judges in room B scored “tougher” than the judges in room A. The only way to compare scores between different judges is to statistically “standardize” their scores, adjusting each score so it fits on a scale of 0-100 with an average of 50. These are the percentile, or comparison, scores. In this specific instance we could see by looking at the percentile scores from the two soprano rooms that having taken the top 30 singers
