If you have decided that a large survey is the most appropriate method to use for your research, by now you should have thought about how you’re going to analyze your data. You will have checked that your questionnaire is properly constructed and worded, you will have made sure that there are no variations in the way the forms are administered and you will have checked over and over again that there is no missing or ambiguous information. If you have a well-designed and well-executed survey, you will minimize problems during the analysis.
If you have computing software available for you to use you should find this the easiest and quickest way to analyze your data. The most common package used by social scientists at this present time is SPSS for windows, which has become increasingly user-friendly over the last few years. However, data input can be a long and laborious process, especially for those who are slow on the keyboard, and, if any data is entered incorrectly, it will influence your results. Large scale surveys conducted by research companies tend to use questionnaires which can be scanned, saving much time and money, but this option might not be open to you. If you are a student, however, spend some time getting to know what equipment is available for your use as you could save yourself a lot of time and energy by adopting this approach. Also, many software packages at the push of a key produce professional graphs, tables and pie charts which can be used in your final report, again saving a lot of time and effort.
Most colleges and universities provide some sort of statistics course and data analysis course. Or the computing department will provide information leaflets and training sessions on data analysis software. If you have chosen this route, try to get onto one of these courses, especially those which have a ‘hands-on’ approach as you might be able to analyze your data as part of your course work. This will enable you to acquire new skills and complete your research at the same time.
For those who do not have access to data analysis software, a basic knowledge of statistical techniques is needed to analyze your data. If your goal is to describe what you have found, all you need to do is count your responses and reproduce them. This is called a frequency count or univariate analysis.
However, there is a problem with missing answers in this type of count. For example, someone might be unwilling to let a researcher know their age, or someone else could have accidentally missed out a question. If there are any missing answers, a separate ‘no answer’ category needs to be included in any frequency count table. In the final report, some researchers overcome this problem by converting frequency counts to percentages which are calculated after excluding missing data. However, percentages can be misleading if the total number of respondents is fewer than 40.
Finding a connection
Although frequency counts are a useful starting point in quantitative data analysis, you may find that you need to do more than merely describe your findings. Often you will need to find out if there is a connection between one variable and a number of other variables. For example, a researcher might want to find out whether there is a connection between watching violent films and aggressive behavior. This is called bivariate analysis.
In multivariate analysis the researcher is interested in exploring the connections among more than two variables. For example, a researcher might be interested in finding out whether women aged 40-50, in professional occupations, are more likely to try complementary therapies than younger, non-professional women and men from all categories.