Bar Chart and Frequency Polygon Illustrating Frequencies from the Tabloid.
Broadsheet
Bar Chart and Frequency Polygon illustrating the frequencies for the Broadsheet
I will now construct another Frequency Polygon for Comparison.
Tabloid
Broadsheet
Comparative Polygon containing each set of Data.
Mini-conclusion.
This shows that both sets of data don’t have a balanced, steady pattern, as both lines have peaks either high up on the graph or low down, at several places in the Polygon. This also suggests the inconsistency of the newspapers, however, the Sun newspaper looked promising at the beginning with a steady rise.
Histograms
Instead of leaving the frequencies as they are, I will group them appropriately.
To find the frequency density, I will use the same formulae as before:
Frequency Density = Frequency
Width of Class Interval
Tabloid
Histogram displaying the Letters per Word in the Tabloid Newspaper.
Mini Conclusion.
This clearly shows that the majority of words are between 2 and 6 letters long. The two bar with the highest frequency density is the 2 < l ≤ 4, this shows that the Sun tends to use words that are of small sizes. However, I cannot cerify this as it is only the one article I am investigating.
Broadsheet
Histogram showing the Frequency Density of the Broadsheet’s word lengths.
Mini Conclusion
This clearly shows that the majority of word lengths are between 4 and 8. This is ever so slightly different from the Tabloid. This suggest to me that the Broadsheet uses words that have more letters in them, keeping the theory of broadsheet and Tabloid Papers correct.
I will now construct another Histogram with the two sets of data on as I can see if there is any relation to the word lengths.
Comparative Histogram for Word Lengths.
Pie Charts
I will use the same formula as before to work out the degrees needed. However, I will not group the frequencies together.
360 / 38 = 9.47 1º = 9.47
Tabloid
Pie Chart to illustrate the data from the tabloid.
Mini conclusion
From the above chart, you will notice that the most frequent word length is 3 letters long, with the longest word length being 10 letters. This sample shows that there were no words containing 9 letters.
Broadsheet
Jkljlkjlkjlkjlkjlkjkljlkjlkjlkjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjjj
Pie chart showing the data from the broadsheet
Mini conclusion
From the above pie chart, it is clear that the most frequent lengths are 5 and 7 letters long, in comparison to the 3 in the Tabloid. You will also notic that there are no frequencies for the two letter category.
Cumulative frequency
I now will find the cumulative frequency for each set of data.
Tabloid
Cumulative Frequency Polygon For Tabloid Newspaper
Box and whisker Plot for Tabloid.
Broadsheet.
Cumulative Frequency Polygon for the Broadsheet Newspaper
Box and Whisker Plot for the Broadsheet.
Comparison of the Newspapers
I will construct both a cumulative frequency polygon and Box and Whisker Plot to compare the data.
Comparative Cumulative Frequency Polygon and Box and Whisker Plot.
Mini-conclusion.
From the above two diagrams, you will notice that the data for the tabloid is positively skewed, whilst the broadsheet appears to have a normal distribution.
Also, the tabloid’s cumulative Frequency increases steeply and levels off at the 8 and 9 category, as there were simply no values for the 9 letters. The I.Q. Range was larger in the Broadsheet and both had the same minimal word length.
Standard Deviation
The final part of this extension will be on Standard Deviation. Again I will work out the standard deviation for each paper.
Total = 166
Mean = 166 / 38 = 4.36
= 105.63
= where ‘n’ is the sample size
Standard Deviation Standard Deviation
Standard Deviation = 1.66725428238. Standard Deviation = 1.67 ( to 2 d.p.)
Now I will do the same for the Broadsheet.
Broadsheet.
Total = 246
Mean = 246 / 38 = 6.47
= 140.74
= where ‘n’ is the sample size
Standard Deviation Standard Deviation
Standard Deviation = 1.92449583282. Standard Deviation = 1.92 ( to 2 d.p.)
Table of Comparisons.
Other Methods of displaying articles that were used are listed in the table below.
From the above table, you will notice that the Tabloid is easiest to read. It consists or larger text in comparison to the Broadsheet. The Tabloid also consisted of a Very large photograph, which reduced the text quite dramatically I would imagine, this also made the artile seen small and compact. The headline was considerably large also, compared to the Broadsheet. This would make a person reading the Broadsheet think the article is bigger than it actually is.
Conclusion.
For the extension task, I made numerous hypothesises. I was proved correct in the table above. The Sun was found easier to read on 5/7 accounts, leaving the Guardian with just 2/7 reads. The Guardian was harder to read as I had expected.
The broadsheet had a larger mean and median word length than the Tabloid and was just out on the range and the mode.
This means that all the data was very close compared to the previous investigation. The Broadsheet had longer word lengths but smaller sentence lengths and vice versa.
The Final hypothesis was quite difficult to prove as each newspaper used certain methods that reduced the amount of text, and I cant state which one had used a more effective method, as I have no proof.
Finally, when all the results are compared, you will see that the Tabloid – The sun is easier to read overall.