Manchester City Council

The Council & democracy Manchester statistics in the Intelligence hub

Research advice




Research is used to produce new knowledge or deepen understanding of a topic. It consists of three steps: pose a question, collect data to answer the question and present an answer to the question.

There are two ways to conduct research:

  • Primary research, using original data, e.g. surveys; and
  • Secondary research, using secondary sources

There are two major research designs: qualitative research and quantitative research. Researchers choose one according to the nature of the research problem they want to observe and the research questions they aim to answer:

  • Qualitative research describes a population without attempting to quantifiably measure variables or look to potential relationships between variables. It is viewed as more restrictive in testing hypotheses because it can be expensive and time consuming, and typically limited to a single set of research subjects. Qualitative research is often used as a method of exploratory research as a basis for later quantitative research hypotheses.
  • Quantitative research asks a narrow question and collects numerical data to analyse utilizing statistical methods. Statistics derived from quantitative research can be used to establish the existence of associative or causal relationships between variables.

Research Framework

Manchester City Council has a research framework for commissioning research which runs until summer 2016.  

Guides to research surveys and consultation

Research Approaches: Qualitative Methodology

There are sections on:

  • the research steering group
  • drawing up focus groups
  • the structure of focus groups
  • sampling strategies
  • questions and wording
  • piloting the focus group
  • organisation
  • focus group team and participants
  • recording the focus group
  • analysis of the focus group
  • reporting

Research Approaches: Quantitative Methodology

There are sections on:

  • the research steering group
  • methodological design
  • data collection methods
  • types of sampling strategies
  • sampling frames and sample size
  • drawing a sample
  • questionnaire design and structure
  • types of questions
  • questionnaire layout
  • piloting the questionnaire
  • surveys by interviewer and by post
  • boosting response rates
  • data preparation and input
  • analysing the data
  • data interpretation
  • reporting

Using Surveys for Consultation (external website from Market Research Society (MRS) with LARIA) - a source of advice for those intending to use survey techniques to seek views of the public on an issue of local concern.  It highlights the key issues to consider and provides information on how and where to go for professional help.  Conducting survey research is a specialist skill.  A poorly designed and conducted survey may give unreliable or misleading results. It could breach the rights of individuals and the credibility of the consultation exercise may be compromised.

Sample size calculator - you can use a sample size calculator to determine how many people you need to include in your survey to obtain accurate results from your target audience or to find the level of precision from an existing sample.  Before using the sample size calculator, you need to understand  confidence intervals and confidence levels:

The confidence interval is the plus or minus figure usually reported in newspaper or television opinion poll results. For example, if you use a confidence interval of 4, and 47% of your sample picks an answer, you can be 'sure' that if you had asked the question of the entire relevant population, between 43% (47 minus 4) and 51% (47 plus 4) would have picked that answer.

Confidence level

The confidence level is the likelihood that the results of your test or sample are real and repeatable, not just completely random. The confidence level indicates how likely it is that you would receive similar results if you repeated your test. The 95% confidence level means you can be 95% certain; the 99% level means you can be 99% certain. Most researchers use the 95% confidence level.  In the example, when the confidence level and confidence interval are combined, you can say that you are 95% sure that the percentage of the population is between 43% and 51%. The wider the confidence interval you accept, the more certain you can be that the answer you receive would be within that range.

Factors that affect confidence intervals

The three factors that determine the size of the confidence interval for a given confidence level are: sample size, percentage and population size.

Sample size

The larger your sample, the more certain you can be over the accuracy of your results. This indicates that for a given confidence level, the larger the sample size, the smaller the confidence interval. However, the relationship is not linear - doubling the sample size does not halve the confidence interval.


The accuracy of your results will also depend on the percentage of your sample that picks an answer. For example, if 99% chose a particular answer, then there is a far smaller chance of an error than if only 51% had selected the answer. It is easier to be certain of answers towards the extreme (e.g. 99%) than those towards the middle values (around 50%).  When determining your sample size, at a given confidence level, you must use the worst case percentage of 50%. You should also use 50% if you want to find a general level of accuracy for a sample you already have.

Population size

The number of people in the group that your sample represents. Population size is only likely to be a factor if you are working with a relatively small or known group of people.  The confidence level calculations assume you have a genuine random sample of the relevant population. If your sample is not truly random, you cannot necessarily rely on the intervals.

Local Area Research and Intelligence Association (LARIA) - offer these research reports (external websites):

Back to the Intelligence Hub


Was this page helpful?

Was this page helpful?