Please enable JavaScript.
Coggle requires JavaScript to display documents.
Choosing a research method (Factors influencing choice of topic (The…
-
The process of research
Formulating an aim or hypothesis - Most studies have a general aim or a specific hypothesis. A hypothesis is a possible explanation that can be tested by collecting evidence to prove it true or false. We can collect evidence to test whether or not this is true. If the hypothesis turns out to be false, we must discard it. The advantage of a hypothesis is that it gives direction to our research. It will give a focus to our questions, since their purpose is to gather information that will either confirm or refute our hypothesis. Positivists favour a hypothesis as the starting point for research.
Operationalising concepts - Before we can test out hypothesis, we need an operational definition of our key ideas. We need a way of measuring fairly abstract concepts such as 'social class'. After operationalising concepts, we can start devising questions that measure it. Problems may arise when different sociologists operationalise the same concept differently.
The pilot study - Sociologists often carry out a pilot study before conducting their main survey. This involves trying out a draft version of the research on a small sample. The aim is to iron out any problems, refine or clarify questions and their wording, and give researchers practice, so that the actual survey goes as smoothly as possible. A pilot study may reveal that same questions are badly worded and hard to understand, or that the answers are difficult to analyse.
Samples and sampling - sociologists often aim to produce generalisations that apply to all cases of the topic they are interested in. They have to choose a sample; a smaller subgroup drawn from the wider group that we are interested in. The process of creating or selecting a sample is called sampling. The basic purpose is to ensure that those people we have chosen to include in the study are representative of the research population, including those who have not been included, If the sample is representative, generalisations can be made
Sampling techniques:
- Random sampling: the simplest technique, where the sample is selected purely by chance. For exam, names drawn out of a hat. Everyone has an equal chance of being selected. A large enough random sample should reflect the characteristics of the whole population. However, not all random samples are large enough to ensure this happens
- Quasi-random or systematic sampling: where every nth person in the sampling frame is selected
- Stratified random sampling: the researcher first breaks down the population in the sampling frame by age, class gender, etc. and then creates a sample in the same proportions
- Quota sampling: population is stratified (same way) and then each interviewer is given a quota which they have to fll with respondents who fit these characteristics
Non representative sampling: For both practical and theoretical reasons, not all studies use representative sampling techniques.
Practical reasons:
- the social characteristics of the research population, such as age, gender and class, may not be known. It would thus be impossible to create a sample that was an exact cross-section of the research population
- it may be impossible to find or create a sampling frame for that particular research population
- Potential respondents may refuse to participate
Theoretical reasons:
Even where it is possible to create a representative sample, some researchers may not choose to do so because of their methodological perspectives. Interpretivists believe that it is more important to obtain valid data and an authentic understanding of social actors' meanings than to discover general laws of behaviour. Because interpretivists are less concerned to make generalisations, they have less need for representative samples.
When it is not possible to obtain a representative sample, sociologists use snowball or opportunity samples.
- Snowball sampling: involves collecting a sample by contacting a number of key individuals who are asked to suggest others who might be interviewed, and so on, adding to the sample 'snowball' fashion, until enough data has been collected. Although not representative, this can be a useful way to contact a sample of people who might otherwise be difficult to find or persuade to take part, such as criminals
- Opportunity sampling: sometimes called convenience sampling, involves choosing from those individuals who are easiest to access. Examples include selecting from passers-by in the street or from a captive audience such as a class of pupils. In neither case is the sample likely to be representative.