From Wikipedia, the free encyclopedia - View original article
|This article's tone or style may not reflect the encyclopedic tone used on Wikipedia. (January 2013)|
A research design is a systematic plan to study a scientific problem. The design of a study defines the study type (descriptive, correlational, semi-experimental, experimental, review, meta-analytic) and sub-type (e.g., descriptive-longitudinal case study), research question, hypotheses, independent and dependent variables, experimental design, and, if applicable, data collection methods and a statistical analysis plan. Research design is the framework that has been created to seek answers to research questions.
There are many ways to classify research designs, but sometimes the distinction is artificial and other times different designs are combined. Nonetheless, the list below offers a number of useful distinctions between possible research designs.
Sometimes a distinction is made between "fixed" and "flexible" or, synonymously, "quantitative" and "qualitative" research designs. However, fixed designs need not be quantitative, and flexible design need not be qualitative. In fixed designs, the design of the study is fixed before the main stage of data collection takes place. Fixed designs are normally theory driven; otherwise it is impossible to know in advance which variables need to be controlled and measured. Often, these variables are measured quantitatively. Flexible designs allow for more freedom during the data collection process. One reason for using a flexible research design can be that the variable of interest is not quantitatively measurable, such as culture. In other cases, theory might not be available before one starts the research. However, these distinctions are not recognized by many researchers, such as Stephen Gorard who presents a simpler and cleaner definition of research design
The choice of how to group participants depends on the research hypothesis and on how the participants are sampled. In a typical experimental study, there will be at least one "experimental" condition (e.g., "treatment") and one "control" condition ("no treatment"), but the appropriate method of grouping may depend on factors such as the duration of measurement phase and participant characteristics:
Confirmatory research tests a priori hypotheses—outcome predictions that are made before the measurement phase begins. Such a priori hypotheses are usually derived from a theory or the results of previous studies. The advantage of confirmatory research is that the result is more meaningful, in the sense that it is much harder to claim that a certain result is statistically significant. The reason for this is that in confirmatory research, one ideally strives to reduce the probability of falsely reporting a non-significant result as significant. This probability is known as α-level or a type I error. Loosely speaking, if you know what you are looking for, you should be very confident when and where you will find it; accordingly, you only accept a result as significant if it is highly unlikely to have been observed by chance.
Exploratory research on the other hand seeks to generate a posteriori hypotheses by examining a data-set and looking for potential relations between variables. It is also possible to have an idea about a relation between variables but to lack knowledge of the direction and strength of the relation. If the researcher does not have any specific hypotheses beforehand, the study is exploratory with respect to the variables in question (although it might be confirmatory for others). The advantage of exploratory research is that it is easier to make new discoveries due to the less stringent methodological restrictions. Here, the researcher does not want to miss a potentially interesting relation and therefore aims to minimize the probability of rejecting a real effect or relation, this probability is sometimes referred to as β and the associated error is of type II. In other words, if you want to see whether some of your measured variables could be related, you would want to increase your chances of finding a significant result by lowering the threshold of what you deem to be significant.
Sometimes, a researcher may conduct exploratory research but report it as if it had been confirmatory ('Hypothesizing After the Results are Known', HARKing); this is a questionable research practice bordering fraud.
A distinction can be made between state problems and process problems. State problems aim to answer what the state of a phenomenon is at a given time, while process problems deal with the change of phenomena over time. Examples of state problems are the level of mathematical skills of sixteen year old children or the level, computer skills of the elderly, the depression level of a person, etc. Examples of process problems are the development of mathematical skills from puberty to adulthood, the change in computer skills when people get older and how depression symptoms change during therapy.
State problems are easier to measure than process problems. State problems just require one measurement of the phenomena of interest, while process problems always require multiple measurements. Research designs like repeated measures and longitudinal study are needed to address process problems.
In an experimental design, the researcher actively tries to change the situation, circumstances, or experience of participants (manipulation), which may lead to a change in behavior or outcomes for the participants of the study. The researcher randomly assigns participants to different conditions, measures the variables of interest and tries to control for confounding variables. Therefore, experiments are often highly fixed even before the data collection starts.
In a good experimental design, a few things are of great importance. First of all, it is necessary to think of the best way to operationalize the variables that will be measured. Therefore, it is important to consider how the variable(s) will be measured, as well as which methods would be most appropriate to answer the research question. In addition, the statistical analysis has to be taken into account. Thus, the researcher should consider what the expectations of the study are as well as how to analyse this outcome. Finally, in an experimental design the researcher must think of the practical limitations including the availability of participants as well as how representative the participants are to the target population. It is important to consider each of these factors before beginning the experiment. Additionally, many researchers employ power analysis before they conduct an experiment, in order to determine how large the sample must be to find an effect of a given size with a given design at the desired probability of making a Type I or Type II error.
To read more about experimental research designs, See Experiment.
Non-experimental research designs do not involve a manipulation of the situation, circumstances or experience of the participants. Non-experimental research designs can be broadly classified into three categories. First, relational designs, in which a range of variables is measured. These designs are also called correlational studies, because correlational data are most often used in analysis. It is important to clarify here that correlation does not imply causation, and rather identifies dependence of one variable on another. Correlational designs are helpful in identifying the relation of one variable to another, and seeing the frequency of co-occurrence in two natural groups (See correlation and dependence). The second type is comparative research. These designs compare two or more groups on one or more variable, such as the effect of gender on grades. The third type of non-experimental research is a longitudinal design. A longitudinal design examines variables such as performance exhibited by a group or groups over time. See Longitudinal study.
Famous case studies are for example the descriptions about the patients of Freud, who were thoroughly analysed and described.
Bell (1999) states “a case study approach is particularly appropriate for individual researchers because it gives an opportunity for one aspect of a problem to be studied in some depth within a limited time scale”.
This type of research is involved with a group, organization, culture, or community. Normally the researcher shares a lot of time with the group.
Grounded theory research is a systematic research process that works to develop "a process, and action or an interaction about a substantive topic".
Gorard, S. (2013) Research Design: Robust approaches for the social sciences, London:SAGE, ISBN 978-1446249024, 218 pages