Research Design

Research

•A researcher overall plan for obtaining answer to the research question or for testing the research hypothesis is referred to the research design.

•A research design is a blue print for conducting the study that maximises control over factor that could interfere with the validity of findings.

•The research design guides the researcher in planning and implementing the study in a way that is most likely to achieve the intended goal.

Characteristics of a good research design:

•The criteria of internal and external validity represent one frame of reference for evaluating the quality of research designs.

1.Appropriateness for research question.: The research design should be appropriate for the questions being asked. Generally, a given research problem can be

2.Lack of bias: A second characteristic of good research design is that it results in data that are not biased. Bias can operate in a variety of ways. The most obvious source of bias is in allocation of subjects to groups. When groups are formed as a non-random basis, the risk of bias is always present.

3.Precision: The term precision as used in the present context refers to the appropriateness of the statistical procedures used to analyse data.

4.The time dimension:

•Cross-sectional design : Cross- sectional studies involve the collection of data at one point of time. The phenomena under investigation are captured, as they manifest themselves during one static time period of data collection.

•Longitudinal designs: Research designs intended to collect data at more than one point are referred to as longitudinal studies. The main value of longitudinal designs lie in there ability to shed light upon (1) trends or changes over time and (2) the temporal sequencing of phenomena which is an essential criterion for establishing causality-

Experimental research:

•An experiment is a scientific investigation in which observations are made and data are collected according to a set of well defined criteria.

•Characteristics of true experimental:

1.Manipulation : The experimenter does something to at least some of the subjects in study.

2.Control: The experimenter introduces one or more controls over the experimental situation, including the use of a control or comparison group.

3.Randomization : The experimenter assigns subjects to a control or experimental group as a random basis.

Advantages and disadvantages of the experimental approach :

•Experimental strength : True experiments are the most powerful methods available to scientists for testing hypotheses of cause and effect relationships between variables. Because of its special controlling properties, the scientific experiment offers greater collaboration than any other research approach that if the independent variable is manipulated in certain way, then certain consequences in the dependent variable may be expected to ensure. This 'if-the' type of relationship is important to nursing because of its implications for prediction and control.

•Experimental weaknesses : There are a number of interesting variables that are simply not amenable to experimental manipulation. A large number of human characteristics such as sex, height or intelligence or environmental characteristics such as weather cannot be experimentally controlled i.e. we cannot randomly confer upon infants at birth maleness or femaleness in order to observe the effect of gender upon, alcohol consumption.

•Symbolic presentation of research design :

– R - Random assignments of subjects to groups

– O - Observation or measurement of dependent variable

– X - Experiment treatment or intervention

• Example:

R O1 X O2 (experimental group)

R O1 - O2 (control group)

A. True experimental

•(1) Pretest-post test control group design :

–It is the most frequently used experimental design. In this design :

–the subjects are randomly assigned to groups

–the pretest is given to both groups

–the experimental group receives the experimental treatment and the comparison group receives the routine treatment or no treatment and

–post test is given to both groups.

•R O1 X O2 (experimental group)

•R O1 - O2 (control group)

•(2) Post test only control group design : In the post test only control group design :

–subjects are randomly assigned to groups

–the experimental group receives the experimental treatment and the control group receives the routine treatment or no treatment and

–post test is given to both groups

•R X O1 (experimental group)

•R - O1 (control group)

•(3) Solomon four-group design :

•In this :

–subjects are randomly assigned to one of the four groups

–two of the groups ; one experimental group one and comparison group are pretested

–two of the groups experimental group one and experimental group two, receive the experimental treatment, whereas two of the groups, comparison group one and comparison group two, receive the routine treatment or no treatment

–a post test is given to all four groups.

•RO1 x O2 (experimental group one)

•RO1 - O2 (control group one)

•R x O (experimental group two)

•R - O1 (control group two)

•B. Quazi Experimental

•Like true experiment, it involves an intervention. However, Quazi experimental design lacks randomization (the signature of true experiment). The signature of quazi experimental design, then, is an intervention in the absence of randomization.

•Quazi-experimental designs :_Some- times researcher are not able to randomly assign subjects to groups or for various reasons no comparison group is available for an experimental design. These designs are those in which there is either no comparison group or subjects are not randomly assigned to groups.

•There are many different designs that fall into the category of quasi-experimental designs :

(a) Non equivalent control group design.

–Non-equivalent control group design : The non-equivalent control group design is similar to the pretest post test control group design except that there is no random assignment of subjects to the experimental and comparison group.

01 x 02 (experimental group)

01 - 02 (comparison group)

(b) Time-series design.

–Time series design : In a time series design, the researcher periodically observes or measures the subjects. The experimental treatment is administered between two of the observations.

O1O2O3 x O4O5O6

•C. Pre-experimental design :

Pre- experimental design is the name applied to experimental designs that are considered very weak and in which the researcher has little control over the research. The two pre- experimental designs are :

–one shot case study

–one group pretest post test design

•(1) one short case study : In one shot case study, a single group is exposed to an experimental treatment and observed after the treatment [ x O ]

–A. group of patients with diabetes might attend a diabetic class (X) and can be tested on their knowledge of diabetes (O) after the class is completed.

•(2) One group pre-test post test design

–The one group pre test-post test design provides a comparison between a group of subjects before and after the experimental treatment. [O1 x O2]

•A group of patients with diabetes could be given a pretest of their knowledge concerning diabetes (O1). This group would then attend a diabetic class (X) and be post tested (O2) at the end of the class.

Non-experimental research design :

•Nurse researcher have made great use of the non-experimental research designs.

•Many times, experimental research cannot be conducted with human beings because of ethical reasons. At other times/ non-experimental research is the most proper type of research to obtain the needed data.

•In trying to determine clients perceptions of pain, the only way to obtain this information would be to ask these clients about their pain, an experimental study would not be appropriate.

•Types of non experimental design : There are many types of non experimental researches, four of the most common types are :

–Survey

–Correlational

–Comparative

–Methodological

•(1) Survey studies : Survey studies are the investigations in which self report data are collected from samples with the purpose of describing populations on some variable or variables of interest.

•Surveys can be conducted by phone, mail or through personal contact with the subjects. The most common data collection methods used in survey research are questionnaires, and interviews.

•(2) Correlational studies :

In correlational studies the researcher examines the strength of relationships between variables by determining how changes in one variable are associated with changes in another variable. A correlational indicates the extent to which one variable (X) is related to another variable (Y). As X increases, does Y increase, or as X increases, does Y decreases.

•The magnitude and direction of the relationship between two variables is indicated by a correlational coefficient. Correlational coefficients may be positive (+ve) or negative (-ve) and range from -1 (perfect negative correlation) to +1 (perfect positive correlation). A correlation coefficient of 'O' indicates no relationship between variables.

•A positive relationship or direct relation-ship, means that as the value of one variable increases, the value of other variable increases, e.g. height and weight of child.

•A negative relationship or inverse relationship means that as the value of one variable increases, the value of other variable decreases, e.g. stress and coping strategy.

•Zero relationship : The value increase or decrease of one variable will not effect to change in the other variable e.g. examination and beauty.

•(3) Comparative studies :

Comparative studies are those studies that examine the differences between two-or more groups on some dependent variable of interest. This studies, there is no manipulation of the independent variable, frequently the independent variable is some inherent characteristic of the subjects, such as personality type, educational levels or medical condition.

•One reason involves the ethics of research studies. When human subjects are studied the manipulation of the independent variable may not be possible. A researcher could not examine child abuse as an independent variable in an experimental study.

•Comparative studies are further classified as retrospective or prospective.

•In retrospective studies the dependent variable is identified in the present (a disease condition) and an attempt is made to determine the independent variable (cause of the disease) that occurred in the past.

•In prospective studies, the independent variable or presumed cause (high cholesterol r*cod levels) is identified at the present time and then subjects are followed in the future to observe the dependent variable (incidence of coronary artery disease).

•(4) Methodological studies :

Methodological studies are concerned with the development of testing and evaluation of research instruments and methods.

•Nurses frequently use tools developed by researchers in other disciplines. If these tools are appropriate for nursing research studies, they definitely should be used. But frequently, tools are used because of their availability rather than for their appropriateness to measure the variables of the research study.

Types of qualitative research :

•Phenomenological studies

•Ethnographic studies

•Grounded theory studies

•Historical studies

•Case studies

•(1) Phenomenological studies : Phenomenological studies examine human experiences through the descriptions that are provided by the people involved. These experiences are called "lived experiences". The goal of this type of research is to describe the meaning that experiences hold for each subject. This type of research includes the qualities of "human such as individualism, self-determination, wholeness, uniqueness and open system". Phenomenology is a philosophy as well as a research approach.

Phenomenological research would ask such questions as, "what is it like for a mother to live with a teenage child who is dying of cancer".

•Example of phenomenological research

•Chesla (2001) conducted a phenomenological study of Thai mothers’ experiences caring for a child with schizophrenia. Findings centered on the mothers’ attempts to smooth their hearts with lots of water.

(2) Ethnographic studies :

•Ethnographic studies involve the collection and analysis of data about cultural group. Ethnography is described as "encountering alien world and making some of them." Ethnographers try to show how actions in one world make sense from the point of view of another world. Ethnography means "learning from people".

•Ethnography can he defined as "the systematic process of observing, detailing, describing, documenting and analysing the life ways or particular patterns of a culture (subculture) in order to grasp the life ways or patterns of the people in their familiar environment."

•In ethnographic research, the researcher frequently lives with the people and becomes a part of their culture. The researcher explores with the people, their symbols, rituals and customs.

Ethnographers interview people who are most knowledgeable about the culture. These people are some times called "key informants". Data collection and analysis is occurring simultaneously.

•Example of Ethnographic studies

•Wittig (2001) conducted an ethnonursing study focusing on organ donation beliefs of African-American women living in rural Mississippi. Wittig made numerous visits to the site and conducted in-depth interviews with 10 African-American women.

(3) Grounded theory studies :

•Grounded theory studies are those studies in which data are collected and analysed and then a theory is developed that is "grounded" in the data.

•The grounded theory method uses both an inductive and deductive approach to theory development. Constructs and concepts are grounded in the data and hypotheses are tested as they arise from the research.

•In this purposive sampling will be used. The researcher looks for certain subjects who will be able to shed new light as the phenomenon that is being studied. Diversity rather than similarity is sought in the people that are sampled.

•Grounded theory tries to account for people’s actions from the perspective of those involved.

•Grounded theory researchers seek to understand the actions by first discovering the main concern or problem and then the individuals’ behavior that is designed to resolve it. The manner in which people resolve this main concern is called the core variable.

•Grounded theory is an approach to the study of social processes and social structures.

•Grounded theory methods constitute an entire approach to the conduct of field research.

•In-depth interviews and participant observation are the most common data source in grounded theory studies, but existing documents and other data sources may also be used.

Example of grounded theory

•Kearney (2001) developed a formal grounded theory of women’s response to violent relationships, based on 13 studies of women’s experiences with domestic violence. The formal grounded theory described women’s basic process of enduring love.

(4) Historical research :

•Historical research is the systematic collection and critical evaluation of data relating to past occurrences. General historical research is undertaken in order to test hypotheses or to answer questions concerning causes, effects or trends relating to past events that may shed light on present behaviours or practices.

•The difference between historical research and other research is that the data in historical research are events, situations or statements made in the past. The historical research is inherently non experimental. The researcher can neither manipulate nor control the variables, nor is there any possibility of random assignment.

Example of historical research

•Lusk (2000) analyzed images of nurses in advertisements from 1930 to 1950. She hypothesized that nurses’ relative status in advertisements would be higher in 1940 (when women were encouraged to enter nursing as a patriotic duty) than in 1930 or 1950. Her hypothesis was supported.

Page updated

Google Sites

Report abuse