484

DESCRIPTIVE STATISTICS (Chapter 17)

BACKGROUND KNOWLEDGE IN STATISTICS

Before starting this chapter you should make sure that you have a good understanding of the necessary background knowledge. Click on the icon alongside to obtain a printable set of exercises and answers on this background knowledge.
BACKGROUND KNOWLEDGE

THE PEA PROBLEM

A farmer wishes to investigate the effect of a new organic fertiliser on his crops of peas. He is hoping to improve the crop yield by using the fertiliser. He divided a small garden into two equal plots and planted many peas in each. Both plots were treated the same except the fertiliser was used on one but not the other. A random sample of 150 pods was harvested from each plot at the same time, and the number of peas in each pod was counted. The results were:

Without fertiliser 4 7 6 6 6 5 3 6 5 5 7 6 6 6 6 4 5 4 8 7 6 8 3 6 4 5 3 6 6 3 4 5 4 7 4 3 9 5 7 8 5 3 6 6 3 6 5 7 6 4 6 6 8 7 4 8 5 5 5 6 4 6 7 7 6 5 3 6 8 7 7 6 6 5 7 6 5 7 6 8 6 6 7 4 7 7 7 4 4 5 4 8 6 4 6 6 5 7 6 6 2 5 5 2 8 5 6 6 6 5 7 5 5 6 6 7 65554446756 65675868676 34663767686 3

With fertiliser 6 7 6 9 7 9 9 7 7 4 7 7 4 4 6 4 9 9 8 7 5 6 3 5 5 8 9 7 5 5 5 4 8 8 7 7 9 7 6 6 8 7 8 4 9 4 7 6 7 7 9 7 7 8 7 7 5 8 7 6 6 7 9 7 7 7 8 9 3 7 4 8 5 10 8 6 7 6 7 5 6 8 10 6 10 7 7 7 9 7 7 8 6 8 6 8 7 4 8 6 8 7 3 8 7 6 9 7 84877766863858767496668478 6 7 8 7 6 6 7 8 6 7 10 5 13 4 7

For you to consider: Can you state clearly the problem that the farmer wants to solve? How has the farmer tried to make a fair comparison? How could the farmer make sure that his selection was at random? What is the best way of organising this data? What are suitable methods of display? Are there any abnormally high or low results and how should they be treated? How can we best describe the most typical pod size? How can we best describe the spread of possible pod sizes? Can a satisfactory conclusion be made?

DESCRIPTIVE STATISTICS (Chapter 17)

485

CONTINUOUS NUMERICAL DATA AND HISTOGRAMS

A continuous numerical variable can take any value on part of the number line. Continuous variables often have to be measured so that data can be recorded. Examples of continuous numerical variables are: The height of Year 11 students: The speed of cars on a stretch of highway: the variable can take any value from about 140 cm to 200 cm. the variable can take any value from 0 km h1 to the fastest speed that a car can travel, but is most likely to be in the range 60 km h1 to 160 km h1 .

ORGANISATION AND DISPLAY OF CONTINUOUS DATA

When data is recorded for a continuous variable there are likely to be many different values. We organise the data by grouping it into class intervals. A special type of graph called a histogram is used to display the data. A histogram is similar to a column graph but, to account for the continuous nature of the variable, a number line is used for the horizontal axis and the columns are joined together. An example is given alongside. Notice that: the modal class (the class of values that appears most often) is easy to identify from a histogram the class intervals are the same size the frequency is represented by the height of the columns.
data values

frequency

Histogram no gaps

SUMMARY: COLUMN GRAPHS AND HISTOGRAMS

Column graphs and histograms both have the following features: the frequency of occurrence is on the vertical axis the range of scores is on the horizontal axis column widths are equal and the height varies according to frequency. Histograms are used for continuous data. They have no gaps between the columns.
Column Graph Histogram

discrete data

continuous data