Statistical Investigation Into Height and Weight of Students

Statistical Investigation Into Height and Weight of Students

My hypotheses are as follows: ~

1. Year 11 students are, on average, taller than year 9 students.

2. There is better correlation between height and weight in year 7

than there is in year 11.

3. The taller someone is the heavier they are.

Below are the sampling methods that I have used in my coursework:

Stratified

Simple Random

Stratified sampling can be defined as the process where the population

is divided into a number of sub-groups, e.g. males aged 45-65. These

subgroups are called strata, and the numbers sampled in the various

strata are proportional to the size of the populations. E.g. if males

aged 45-65 is known to compromise 13% of the total population in the

UK, in a sample of 1000, 130 should be males aged 45-65.

On the other hand, Simple Random sampling can be defined as the

process by which every possible sample of a given size is equally

likely to be selected. To ensure randomness and no bias, a random

number table or RAN# on a calculator is used, and the items in the

sampling frame are numbered.

These two sampling methods were not used in isolation but combined to

make full potential of both. [IMAGE]For this investigation I will use

a random stratified sample. This means that the data that I take the

sample from is first sorted into strata and then a random sample is

taken from them.

The advantage for me using this type of sampling method was that the

data was already in some sort of strata e.g. year groups, gender,

weight, IQ, ideal for collecting the type of data I need in answering

my hypotheses. The stratified sample method doesn't really have any

sort of disadvantages. This is because using this type of sampling

will use all of the data and none of the data will be biased unless

its numerical or alphabetic order has any relevance or affect on the