The introductions on pages 2 and 3 show clearly that there is a title, statement of task and a plan that outlines what is to come. Note enough detail and purpose to get to 3 and the project lacks some elements that would prohibit this too. There is a long preamble including large references that help demonstrate the candidate's interest in the project but which do not otherwise contribute a lot.

Page 6 shows us a snap shot of the data to give an idea. The raw data is included at the end. the candidate has collated data on a number of bands and the number of words used by that band. there is also data on the top three words used by the bands. The candidate has then generated an extra column that shows the percentage of the total words that is taken up by the top word. this is a helpful addition to the data that adds proportion since there is no other place where number of songs released is considered. The data, whilst interesting dies need careful handling to avoid irrelevant processes. the candidate was warned of this. It is possible though to do some useful analysis with this data and the candidate has tried. As such I am happy to conclude that data is organised in a form appropriate for analysis and sufficient in quality (just)and quantity (Only one of those required for 2 here) BUT does not meet enough of the criteria for 3. The data has limits, but the process was valid and had potential - although that potential was not realised.

I have tried hard to recreate the processes that the candidate performed here using their database but cannot reproduce the results. My conclusion, unfortunately is that there are not actually 2 correct processes required to get to 2/5 here. At least 2 processes are attempted to justify the 1.

There are attempts to conclude/interpret processes throughout to justify the award of 1 here. I have not found 2 conclusions that are consistent with the processes though. The box plots on page 7 are consistently interpreted.

On page 10 the candidate acknowledges the limits of the data. The top word is not the same for all bands, the word love may have appeared outside the top 5. The candidate recognises that this makes any conclusions unfair for the processes they chose. (this need not have been true for other processes)

There is certainly a logical structure to the project. the candidate has already been penalised for irrelevance and incorrectness, but has certainly attempted to tell a coherent story. Although I have been frustrated by the candidate's stubbornness I admire the determination to try and get a useful conclusion from the topic that interested them.

Example - although the chi squared test is incorrect, the notation and terminology used is correct. This along with other examples through the project makes 'Some' correct notation and terminology justifiable.