Analysing data and drawing conclusions
Looking for significance
Once you’ve collected your data and recorded it safely, you can start to make sense of it. At this point, data can start to become information.
When looking at quantitative data, scientists typically try to compare two datasets: a control set (data collected under ‘normal’ conditions) and a test set (data collected where one or more independent variables have been deliberately changed).
An important question is whether the two sets of data are significantly different. To answer this, you’ll need to use a statistical test. You should decide what test you will use at the start of your planning as it may affect what data you need to collect. It is not always possible to compare data in a meaningful way (for example, because too little is collected), so plan ahead.
Once you establish whether or not there is a significant difference, you can interpret what that difference (or lack of difference) means. Can you accept your hypothesis (or, more accurately, reject your null hypothesis)?
With qualitative data, you may need to look for patterns in people’s answers to questions. Consider ‘coding’ – using categories to classify particular elements of a response. For example, if you ask people what they find least enjoyable about school, they might mention school meals or the range of subjects on offer. Even though different people will not use exactly the same wording, the sentiment may be similar.
In this example, you would create a code for ‘dissatisfaction with school lunches’ and another one for ‘frustration at limited number of subjects available’ and count how many responses there are that fit each code.