• Join over 1.2 million students every month
• Accelerate your learning by 29%
• Unlimited access from just £6.99 per month
Page
1. 1
1
2. 2
2
3. 3
3
4. 4
4
5. 5
5
6. 6
6

# Statistical investigation into pupils at Mayfield high school

Extracts from this document...

Introduction

## AIM

In this investigation I have set out to explore two hypotheses regarding secondary data supplied to me concerning pupils at Mayfield High School in years 7 to 11.  The secondary data supplied included data on a range of issues including each pupil’s weight, their IQ and the average number of hours each pupil watched TV per week.  My hypotheses below explore specifically these elements from the secondary data supplied to me.

## Hypotheses 1 – Correlation between time spent watching TV and weight

My hypothesis is that there will be a connection between the average number of hours spent watching television and the weight of each pupil.  My prediction is that there will be a positive correlation: i.e. that the heavier pupils will be those who spend more hours watching TV.

The reason for my prediction is that I believe that more time spent in front of the television means that there is less time for activity and, therefore, TV watchers are more likely to put on weight.  I also think that TV watchers are more likely to eat snacks and junk food while watching TV, which would also result in weight gain.

In my conclusion below, I consider outside factors which I have not taken into account in the investigation of this hypothesis which may influence my results.  Such factors are: height, gender, age, method of travel.

## Hypotheses 2 – Correlation between time spent watching TV and IQ

Middle

131

131/1183x50

6

8

125

125/1183x50

5

9

143

143/1183x50

6

10

94

94/1183x50

4

11

86

86/1183x50

4

Boys

 Year No. in Year Calculation No. of pupils taken to create sample 7 151 151/1183x50 6 8 145 145/1183x50 6 9 118 118/1183x50 5 10 106 106/1183x50 4 11 84 84/1183x50 4

I created, from my secondary data, separate charts for each gender and year group and numbered each pupil within that group according to their alphabetical order. To ensure that there is no bias, the actual pupils selected were selected by a random number generator which was a function available in Excel.  The random number generated was always less than or equal to 1.  I, therefore, multipled each number generated with the number of pupils in each gender and year group to ensure that each pupil was capable of being selected.  If the same number in the same group was generated twice, which did happen once, I selected another random number using the random number button on my calculator and, again, multiplying it by the number of pupils in that gender and year group.

In this way I produced my stratified sample of 50 pupils which I have set out at Appendix 1.  The number column in appendix is the number of the pupil in that year and gender group, assigned through the random number generation process.

## Analysis of Stratified Sample

Because both of my hypotheses predict a connection between the two sets of data in each hypothesis, I decided that, for each hypothesis, I should present the data on a scatter graph.

Conclusion

It must be remembered that these results have been drawn from a sample only.  More conclusive results are likely to be obtained from a larger collection of data than the 50 in my sample.

I am surprised by my finding of a negative correlation in the TV v Weight comparison.  Possible explanations for such a correlation, if it is genuine (ignoring factors such as dirty data and limited sample), may include the fact that there is a lot of sport on television and it is possible that the more athletic pupils watch it.

However, my investigations into both hypotheses were limited and always unlikely to have proved a link between the two pieces of data in each case, and even less likely, a direct causal relation.  For instance, I did not take into account external factors which could have affected or improved my results.

External factors which I could have taken into account to improve both my investigations include factors like age, height, gender, method of travel to school and programmes watched.  Most of these factors were available to me in data form on the secondary data supplied to me.  I would have to have done further primary investigation (through e.g. questionnaires) into a breakdown of types of programme watched, if I wanted to discover further possible explanations for any correlations found.  A more conclusive investigation is likely to result if this additional material is used and taken into account, which may support a direct causal relationship.

This student written piece of work is one of many that can be found in our AS and A Level Probability & Statistics section.

## Found what you're looking for?

• Start learning 29% faster today
• 150,000+ documents available
• Just £6.99 a month

Not the one? Search for your essay title...
• Join over 1.2 million students every month
• Accelerate your learning by 29%
• Unlimited access from just £6.99 per month

# Related AS and A Level Probability & Statistics essays

1. ## Data Handling - Planning - I intend to investigate the relationship between the number ...

mean, mode, median and range of the KS2 maths results for males and females. Mean maths results Mean maths result for females = 4.06 Mean maths result for males = 4.66 Mode maths results Mode maths result for females = 4 Mode maths result for males = 5 Median maths

2. ## The mathematical genii apply their Statistical Wizardry to Basketball

The geometric model states that the events must be independent. No distribution could possibly account for the infinite amount of variables/influences that could occur e.g. improving skill as more shots are scored, fatigue etc. The variable would be different in each case.

1. ## Investigate the relationship between height and weight and how it changes between gender and ...

My findings defiantly agree with my hypothesis because of my using the different year groups it only proves that my hypothesis is correct my hypothesis was 'boys are taller and heavier then girls and the difference between boys and girls will increase as the students get older' The reasons why

2. ## AS statistics coursework - correlation coefficient between height and weight in year 11 boys ...

Weight in kg (y) x2 y2 xy 1.75 45 3.06 2025 78.75 1.66 70 2.76 4900 116.2 1.90 70 3.61 4900 133 1.60 49 2.56 2401 78.4 1.91 82 3.65 6724 156.62 1.54 57 2.37 3249 87.78 1.77 57 3.13 3249 100.89 1.65 64 2.72 4096 105.6 1.57 40 2.46 1600 62.8 1.55 54

1. ## Used Cars - What main factor that affects the price of a second hand ...

The box plot on the small engine sized cars shows that the range of prices of the cars is very compact and relatively small compared to the other sizes of cars. From looking at the median of the inter-quartile range it can be seen that most of the prices of

2. ## Telepathy Investigation

There could be several reasons for this. It could mean that the transmitter has some telepathic powers. It could mean that many of the people in the group to receive messages are telepathic. It could be a combination of both.

1. ## Estimating the length of a line and the size of an angle.

of the angle is closer to the actual size of the angle than the mode for year 10's estimations. This shows that year 11 is better at estimating than year 10. In addition year 11's mean is closer to the actual size of the angle than the mean for year

2. ## Design an investigation to see if there is a significant relationship between the number ...

same length would also be incredible time consuming, and so not ideal. I have decided to use a 1m x 1m quadrat as Fucus vesiculosus can grow up to 2m long, and at the time when I'm executing my investigation, it's likely that the seaweed will be at it's maximum length.

• Over 160,000 pieces
of student written work
• Annotated by
experienced teachers
• Ideas and feedback to
improve your own work