What are the factors that are considered by a researcher while choosing the type of research design?

Can you imagine doing research without a plan? Probably not. When we discuss a strategy to collect, study, and evaluate data, we talk about research design. This design addresses problems and creates a consistent and logical model for data analysis. Let’s learn more about it.

What is Research Design?

Research design is the framework of research methods and techniques chosen by a researcher to conduct a study. The design allows researchers to sharpen the research methods suitable for the subject matter and set up their studies for success.

Creating a research topic explains the type of research (experimental, survey research, correlational, semi-experimental, review) and its sub-type (experimental design, research problem, descriptive case-study). 

There are three main types of designs for research:

• Data collection
• Measurement
• Analysis

The research problem an organization faces will determine the design, not vice-versa. The design phase of a study determines which tools to use and how they are used.

Research Design Elements

Impactful research usually creates a minimum bias in data and increases trust in the accuracy of collected data. A design that produces the slightest margin of error in experimental research is generally considered the desired outcome. The essential elements are:

1. Accurate purpose statement
2. Techniques to be implemented for collecting and analyzing research
3. The method applied for analyzing collected details
4. Type of research methodology
5. Probable objections to research
6. Settings for the research study
7. Timeline
8. Measurement of analysis

Characteristics of Research Design

A proper design sets your study up for success. Successful research studies provide insights that are accurate and unbiased. You’ll need to create a survey that meets all of the main characteristics of a design. There are four key characteristics:

• Neutrality: When you set up your study, you may have to make assumptions about the data you expect to collect. The results projected in the research should be free from bias and neutral. Understand opinions about the final evaluated scores and conclusions from multiple individuals and consider those who agree with the results.
• Reliability: With regularly conducted research, the researcher expects similar results every time. You’ll only be able to reach the desired results if your design is reliable. Your plan should indicate how to form research questions to ensure the standard of results.
• Validity: There are multiple measuring tools available. However, the only correct measuring tools are those which help a researcher in gauging results according to the objective of the research. The questionnaire developed from this design will then be valid.
• Generalization: The outcome of your design should apply to a population and not just a restricted sample. A generalized method implies that your survey can be conducted on any part of a population with similar accuracy.

The above factors affect how respondents answer the research questions, so they should balance all the above characteristics in a good design.

Research Design Types

A researcher must clearly understand the various research design types to select which model to implement for a study. Like research itself, the design of your analysis can be broadly classified into quantitative and qualitative.

It determines relationships between collected data and observations based on mathematical calculations. Statistical methods can prove or disprove theories related to a naturally existing phenomenon. Researchers rely on qualitative research methods that conclude “why” a particular theory exists and “what” respondents have to say about it.

It is for cases where statistical conclusions to collect actionable insights are essential. Numbers provide a better perspective for making critical business decisions. Quantitative research methods are necessary for the growth of any organization. Insights drawn from complex numerical data and analysis prove to be highly effective when making decisions about the business’s future.

You can further break down the types of research design into five categories:

1. Descriptive: In a descriptive composition, a researcher is solely interested in describing the situation or case under their research study. It is a theory-based design method created by gathering, analyzing, and presenting collected data. This allows a researcher to provide insights into the why and how of research. Descriptive design helps others better understand the need for the research. If the problem statement is not clear, you can conduct exploratory research. 

2. Experimental: Experimental research establishes a relationship between the cause and effect of a situation. It is a causal design where one observes the impact caused by the independent variable on the dependent variable. For example, one monitors the influence of an independent variable such as a price on a dependent variable such as customer satisfaction or brand loyalty. It is an efficient research method as it contributes to solving a problem.

The independent variables are manipulated to monitor the change it has on the dependent variable. Social sciences often use it to observe human behavior by analyzing two groups. Researchers can have participants change their actions and study how the people around them react to understand social psychology better.

3. Correlational research: Correlational research is a non-experimental research technique. It helps researchers establish a relationship between two closely connected variables. There is no assumption while evaluating a relationship between two other variables, and statistical analysis techniques calculate the relationship between them. This type of research requires two different groups.

A correlation coefficient determines the correlation between two variables whose values range between -1 and +1. If the correlation coefficient is towards +1, it indicates a positive relationship between the variables, and -1 means a negative relationship between the two variables. 

4. Diagnostic research: In diagnostic design, the researcher is looking to evaluate the underlying cause of a specific topic or phenomenon. This method helps one learn more about the factors that create troublesome situations. 

This design has three parts of the research:

• Inception of the issue
• Diagnosis of the issue
• Solution for the issue

5. Explanatory research: Explanatory design uses a researcher’s ideas and thoughts on a subject to further explore their theories. The study explains unexplored aspects of a subject and details the research questions’ what, how, and why.

Conclusion

QuestionPro’s robust suite of research tools provides you with all you need to derive research results. Our online survey platform includes custom point-and-click logic and advanced question types. Uncover the insights that matter the most.

What are the theoretical, ethical and practical factors which influence a sociologist’s choice of research method?

1. Theoretical factors: Positivists prefer quantitative research methods and are generally more concerned with reliability and representativeness. Interpretivists prefer qualitative research methods and are prepared to sacrifice reliability and representativeness to gain deeper insight which should provide higher validity.

2. Practical factors: include such things as the amount of time the research will take, how much it will cost, whether you can achieve funding, opportunities for research including ease of access to respondents, and the personal skills and characteristics of the researcher.

3. Ethical factors: thinking about how the research impacts on those involved with the research process. Ethical research should gain informed consent, ensure confidentiality, be legal and ensure that respondents and those related to them are not subjected to harm. All this needs to be weighed up with the benefits of the research.

4. A fourth factor is the Nature of the Topic to be studied. Some topics lend themselves to certain methods and preclude others.

Remember this by using the most handy and memorable mnemonic: TPEN

Theoretical Factors Affecting the Choice of Research Method

Theoretical Factors include Positivism and Interpretivism, Validity, Reliability and Representativeness

Positivist and Interpretivist approaches to research are dealt with in this post: Positivism and Interpretivism: A Very Brief Overview, and a more detailed post on the Positivist approach to social research can be found in here: Positivism, Sociology and Social Research.

The three terms Validity, Reliability and Representativeness are are fundamental to evaluating the usefulness of research methods. They should appear in any essay you do on any research methods, without exception!

Validity

Research is valid if it provides a true picture of what is really ‘out there’ in world. Generally speaking, the more in depth the research, the fuller picture we get of the thoughts and feelings of the individuals acting, so the more valid the data and then more the researcher stands back and allows the respondents to ‘speak for themselves’ the more valid the data. In more quantitative research, such as social surveys, validity may be lacking because the researcher has decided on what questions should be answered by respondents, rather than letting the respondents decide on what they want to say for themselves.

Reliability

If research is reliable, it means if someone else repeats the same research with the same population then they should achieve the same results. In order to be reliable, research needs to be easily repeatable. Self-Completion questionnaires have high reliability because it is easy for another researcher to administer the questionnaire again. More in depth methods such as participant observation, where the researcher can spend several months or even years with a small group of respondents are not very reliable as it is impossible to replicate the exact procedures of the original research. More qualitative methods also open up the possibility for the researcher to get more involved with the research process, probing respondents for very detailed information.

Representativeness

Research is representative if the research sample reflects the characteristics of the wider population that is being studied. Whether a sample is representative thus depends on who is being studied. If one’s research aim is to look at the experiences of all white male AS Sociology students studying sociology, then one’s sample should consist of all white, male sociology students. If one wishes to study sociology students in general, one will need to have a proportionate amount of AS/ A2 students as well as a range of genders and ethnicities in order to reflect the wider student body.

Practical Factors and Research Methods

All Social Research must take place within the practical constraints of the real world. Social researchers need to plan, collect, analyse and publish their data with limited budgets; they need to secure funding from somewhere willing to fund their research; they need to publish their research within a realistic time frame, otherwise, the data they collect may be worthless because it is so out of date; they also need to manage their own lives at the same time, and a final constraint on choice of research methods is the choice of topic itself!

Five practical constraints on social research

Time – As a general rule, the more in-depth the method the more time consuming it is. Also, doing your own primary research tends to take longer than using secondary sources.

Money – As a general rule, the more in-depth the method the more money it costs. Also, doing your own primary research tends to be more expensive than using secondary sources.

Funding – There are numerous organisations that fund sociological research including charities and businesses, but the largest by far is the government. In the past the government has been far more likely to fund quantitative research than qualitative. Can you suggest why this might be the case? The government is also more likely to fund research that fits in with its present aims. What kind of research topics would be more likely to get funding in contemporary Britain?

Opportunity and Access to Respondents – Some research topics and some kinds of respondents are more difficult to gain access to. It will probably be more difficult to gain access to research pupils in schools compared to teachers for example, and some people may be less willing to engage with research than others – those engaged in deviant or illegal activity might not want to be researched because what they are doing is not socially acceptable.

Personal Situation, Characteristics and Skills of the researcher – Family and work commitments may prevent researchers from doing long term field work such as participant observation, and not everyone has the emotional intelligence or resilience required to engage in long-term empathetic field work. Some research topics might also be better suited to researchers with certain personal characteristics – girls in education might respond more openly to female researchers for example.

Ethical Factors and Social Research

Ethical behaviour helps protect individuals and communities and offers the potential to improve the quality of life of individuals within society. Much social research is designed to tackle social problems such as social exclusion, and so sets out to collect knowledge in order to make the the world a ‘better place’. Understanding the causes of poverty, for example, can help us to reduce poverty, and understanding how people come to be involved in crime can help us to figure out how to prevent this from happening.

However, the actual process of doing research involves interfering with people’s lives and so could potentially be harmful to those involved, and in order minimise harm, most research follows ethical guidelines laid down by The British Sociological Association. There are five ethical criteria which should inform sociological research.

• Respondents should be able to give informed consent
• Information which the respondents give should be kept confidential (if they ask for it to be kept confidential)
• Research should not involve law breaking behaviour
• Research should not involve harming the respondents or anyone else involved in the research process
• Research should, ultimately, aim to do more good than harm for society.

Respondents should give informed consent

Respondents should be able to give informed consent to take part in the research process. In order to do this, they should know that research is taking place, what the purpose of the research is and what the researcher intends to do with the results.

Informed consent can be difficult with young children, because they may not have the capacity to fully understand the purposes of the research. Informed consent can also be a problem because respondents might influence the results if they know the purpose of the research, and some experiments have deliberately misled respondents in order to ensure results are valid – Field experiments where actors act in a deviant way (vandalising property for example) in order to measure public responses are an example of this.

Informed consent is also not possible covert research – both in covert participant observation and in covert non-participant observation.

Respondents’ information should be kept confidential.

It is often important for some aspects of research to remain confidential, especially when it could harm the respondents or an institution if others became aware of their responses. For example a teacher might have their career affected if a senior manager became aware of any negative comments she may have made, or accounts of disruptive behaviour of pupils were made public. For these reasons, researchers often have to guarantee anonymity and they often change the names of respondents and institutions when writing up results.

However, where case-studies are concerned and there is a lot of in-depth information being published about just a handful of people, confidentiality is less likely as the chances of being able to guess who said what might be fairly high. Anonymity also compromises reliability, as it makes it more difficult for other researchers to verify the results from particular respondents.

Some sociologists have taken the issue of confidentiality to extremes. While undertaking research on a particular prisoner In the USA Keith Tunnel (1998) discovered that the prisoner had taken on the identity of someone else in order to avoid a much larger prison sentence. The prison authorities became suspicious and investigated the prisoner’s background. Thought Tunnel knew the truth, he felt he owed the prisoner confidentiality and deliberately lied, stating that he knew nothing about the ‘identity theft’. As a result the prisoner was released many years early.

Research should avoid harming respondents

Research can often have an effect on the people being studied, and researchers need to think of this impact before they begin their research. When researching victims of crimes such as domestic abuse, or bullying in schools, this could bring up painful memories which could result in trauma in the respondents, and, if the abusers find out that respondents have spoken up to researchers this could result in further victimisation. Within the context of education, even researching something such as reasons for educational underachievement need to be treated sensitively, as people who have a past history of failing in school probably won’t be happy about being reminded of it.

Research should not involve law breaking behaviour

Research should also take place within the boundaries of legality. This is only really an issue when researching criminal and deviant behaviour using participatory methods where researchers may have to take drugs to fit in with the group, or witness or even commit crimes in order not to blow their cover. A classic case of where this happened was with Sudhir Venkatesh’ study Gang Leader for a Day where he participated in beating up a member of the gang he was studying as a form of punishment.

The social impact of research: research should, ultimately, aim to do more harm than good.

As mentioned earlier, much research aims to make society a better place, and choice of research topic is sometimes based on this ethical decision to generate knowledge in order to improve society. The problem is that there are many competing (subjective) ideas about the kind of topics, the kind of data (quantitative or qualitative) and the kind of research process which are the best suited to improving society.

Positivists would argue that quantitative research which collects ‘objective’ and generalisable data about the causes of social problems such as crime, unemployment, educational underachievement is the best suited to improving society because governments can use this data to enact large scale social changes.

Marxists and Feminists would not necessarily agree, however, because people in power would not necessarily fund the type of research that could harm them, and would not act on any research which was done but was harmful to their interests. If research found that high levels of inequality is what causes educational underachievement among the lower classes, they would not expect those in power to adopt social policies to reduce inequality because that would mean the rich and powerful becoming poorer. For this reason some Marxist and Feminist researchers engage in smaller scale research and focused on highlighting social injustices in order to galvanise people into political action and make more radical changes. Some Marxist inspired sociologists have focused on issues such as Corporate Crime for example to highlight the extent to which this often hidden crime harms society, while a major focus of Feminist research has been to do with issues such as Domestic Violence and the persistence of sexist attitudes in social media.

Feminists and Interactionist researchers also believe the most ethical research is qualitative in nature – where the researcher co-creates the data on an equal basis with the respondents – using methods such as the unstructured interview – such methods are seen as ethical because they empower the respondents, allowing them to speak for themselves, which is especially useful when researching the powerless, or the voiceless, the kinds of people who are invisible (victims of domestic violence for example) or who are typically talked about in a negative way by people in power (criminals for example).

The nature of the topic to be studied

The methods chosen will vary with the topic being studied. If one wishes to find out more about criminal gangs, for example, these will not respond well to survey based research and other methods of study will need to be used. Similarly, if one wishes to do research on sensitive issues such as domestic violence, a closed question questionnaire may be a little ‘cold’ for such emotive issues.

Other topics lend themselves very naturally to survey based research, such as voting intentions in the run up to an election, or market research to glean people’s feelings about new products.

The nature of the topic will also influence the way in which the research is administered. The British Crime Survey asks about people’s experiences as victims of crimes, and so lends itself to a structured interview, given the sensitive nature of the topic and the possible need for clarification of the definitions of certain crimes.

Related Posts: