Collecting data

Types of data

Data is a collective name for information recorded for statistical purposes. There are many different types of data:

• qualitative data - data that can only be written in words, not numbers, for example, the colours of cars in a car park
• quantitative data - data that can be written in numbers, for example, the heights of children
• discrete data - numerical data that cannot be shown in decimals, for example, the number of children in a classroom
• continuous data - numerical data that can be shown in decimals, for example, the weights of 10 babies
• primary data - data that has been collected from the original source for a specific purpose, for example, if a school wanted to know what their students thought of the school canteen service they would question the pupils directly
• secondary data - data that is not originally collected by a group for a specific purpose, for example, finding out the average cost of cars in a car park by using national statistics

Questionnaires

Questionnaires are a common way of discovering and recording statistical information.

There are many ways to conduct questionnaires, such as over the phone, face-to-face, by post or over the internet. The way in which questionnaires are conducted can have an effect on their reliability.

For example, a questionnaire that is collected face-to-face may give a lot of well-understood information, but this is a costly and time-consuming way to collect data. Data that is collected via post may be cheaper and quicker to collect, but many people may not post their questionnaires back so the sample size may be smaller.

Writing questionnaires

Questionnaires need to be easy to understand and unbiased. Bias is when one answer is favoured over another and can lead to unreliable results.

The way questions are worded is very important. All questions must:

• be easy to understand
• be unbiased
• be non-offensive
• allow every person to answer

Response boxes are the boxes on questionnaires that allow people to indicate their answer to a question. These boxes make it easier to collect data from the questionnaire once it's finished.

Examples

Here are some poorly worded questions.

1. How much pocket money do you get per week?

• £1 to £4
• £5 to £8
• £8 to £10

This is not a good question to use as not all amounts are accounted for. Some people may get no pocket money and some people may get more than £10 per week. There is also a gap between the amounts in the first two responses, and an overlap between responses two and three. To make this question more suitable, name the first box '£1 to £4.99', the second '£5 to £7.99', the third to '£8 to 10.99', and include either a response box for '£0' and a response box for '£11 or more', or include a response box for 'any other amount'.

2. How many films do you watch?

• a few
• a lot
• not many

This is a bad example of a question for two reasons:

• There is no time period given in the question, for example, 'per week' or 'per month'. This means people may answer the question differently depending on their interpretation.
• The response boxes are very vague. What represents a lot of films to one person may not be a lot to another. Use numerical amounts instead.

3. Experts agree that Maths is the best subject at school. Do you agree that Maths is the best subject at school?

This is not a good question as it is biased towards Maths. Many people will not want to disagree with the person asking the questions, so the results may be unreliable. This is called a 'leading' question.

4. In your opinion, what is the best way to improve our school?

This is an 'open' question. Think carefully about using this style of question in questionnaires. Inviting the respondent to write a sentence answer means it will be very difficult to collect, compare and analyse responses. This question could be improved by providing a small list of suitable answers to choose from and an 'other' box for any options not included.

Data collection sheets

Once questionnaires have been filled in and returned, the data that has been collected from them needs to be represented in either tables or diagrams so it can be easily understood. A data collection sheet makes this easy to do.

A data collection sheet has three columns. The first are the options from the questionnaire. The second column is for a tally so that the answers can be filled in directly from the questionnaire and the third column is for the total frequency.

The following questionnaire question can be represented using the data collection sheet below:

What colour is your car?

• white
• black
• grey
• red
• other