Mayfield Coursework

Authors Avatar

        Page  of

Maths Coursework/Mayfield High School

In my Mayfield High coursework I am going to do three hypotheses. The first one is about the correlation between height and weight. I believe that the taller the person is, the heavier he is. My second hypothesis is a prediction to show that an older person is taller than younger people. Finally my third hypothesis will show that on average boys are taller than girls.

My hypotheses are:

  • A = There is a positive correlation between height and weight.
  • B = On average the students’ heights will become greater as they age.
  • C = On average boys are taller than girls.

Data

For both hypotheses I am going to use the Mayfield high school data. This specific data is secondary data as I have not personally taken it myself, another source ahs done it instead. It consists of the following:

  • Year Group
  • Surname
  • Forename
  • Age (Years and months)
  • Gender
  • Hair colour
  • Eye colour
  • Left/right handed
  • Favourites (colour, type of music, subject, TV programme)
  • Average number of hours TV watched per week
  • IQ
  • Height (m)
  • Weight (kg)
  • Distance between home and School
  • Means of travel to school
  • No. of siblings
  • No. of pets
  • KS2 results (Maths, English, Science)

 I am going to get rid of all the unnecessary data, such as IQ and Favourite colour, as they are useless in my work. To take a sample from the data I am going to use STRATIFIED sampling. I will RANDOMLY take 20% from the boys from each year group and another 20% from the girls from each year group. This is so I can get the least bias and most accurate sample. This is so the result will be more accurate and be as fair as possible. If I just used a quota sample, where the population is divided into groups (gender, age, sex etc) and given number (quota) is surveyed from each group, then that would not be very as it can be very biased.

The data I am interested in and I will use are:

  1. Weight – to find out the weight
  2. Height – to find out the height
  3. Year Group – to make sure that I take out all the outliers, for example there may be a year 7 who is 1.8m

Outliers

The Mayfield data I have received is secondary, therefore not mine. It may contain outliers. Outliers are values of data that are distant from the other pieces of data, as it can be really large or really small and does not look realistic. There is a method in which you can find outliers:

Q1 = first quartile

Q3 = third quartile

IQR = interquartile range

To find out if the data is small then it would be Q1 – 1.5 x IQR

To find out if the data is big then it would be Q3 + 1.5 x IQR

Now from the data I have a will remove any of these:

  1. Invalid data – e.g. wrong words, wrong units, no data
  2. Outliers – e.g. data that goes beyond a specific range for weight and height

To validate my data I will need to think about each data element in term:

Year Group – I will use people from yr 7 to yr 11 as to get a better and more accurate result.

Height – For each year, I will separate it into boys and girls and from there I will find out each of the data’s Lower Quartile, Median Value, Inter Quartile, Upper Quartile, Smallest Outlier and the Biggest Outlier.

Weight – I will use an acceptable range for the year groups, so I can eradicate any outliers.

Age – I will consider 20% of each sex from each year group to be in the result.

To work out the outlier from each sample I had to first work out the lower quartile, the upper quartile, median value and the inter quartile. To work out the quartiles I had to first click on a box, press equals, the click Fx at the top of the screen.

 

I then choose quartile from the selection. Then after that I highlight the data that I am using in the array box and then press 1 in the quartile box. To choose the upper quartile I would do the same thing but instead I would press 3 in the quartile box. I would also do the same to work out the median value but I would then press 2 in the quartile box. To work out the inter-quartile I would minus the upper quartile by the lower quartile.

Join now!

These are all of the samples’ outliers for all the years and the sexes that show the lower quartile, inter quartile, upper quartile and median value:

Year 7 Girls

Year 8 Girls

Year 9 Girls

Year 10 Girls

Year 11 Girls

Year 7 Boys

Year 8 Boys

Year 9 Boys

Year 10 Boys

Year 11 Boys

Graphs

For hypotheses A, the best graph to choose would ...

This is a preview of the whole essay