Research design and approachs
1 like614 views
This document discusses research design and approaches. It begins by distinguishing between research design and research approach, with research design being the broader plan for conducting a study and research approach being an important element within the design. The key elements of a research design are then outlined, including the approach, population/sampling, data collection methods, time/place of collection, and data analysis method. The document goes on to classify and describe different types of research approaches, with a focus on quantitative and qualitative approaches as well as experimental and non-experimental designs. Specific experimental designs like true experimental, quasi-experimental, and pre-experimental are defined.
Research design and approachs
- 1. RESEARCH DESIGN AND APPROACHS Ms Sudharani Banappagoudar
- 2. Introduction • Research design and research approach are two terms that are frequently used interchangeably; However research design is a broader plan to conduct a study, and research approach is an important element of the research design, which governs. • The research design spells out the basic strategies that the researcher adopts to develop information that is accurate and interpretable. • The research design incorporates some of the most important methodological decisions that the researcher makes in conducting a research study. • It provides an overview of various considerations in selecting a research design.
- 3. Definition • Research design is the blue print to conduct a research study, which involves the description of research approach, study setting, sampling size, sampling technique, tools and method of data collection and analysis to answer the specific research questions or for testing research hypothesis. • It is an overall plan of the researcher for obtaining answers to the research questions or for testing the research hypothesis
- 4. Qualities of a good research design • It should be properly structured to suit the research problem • should be free from any kind of bias • should enable a researcher to achieve the highest possible precision • Should be able to establish trustworthy relationships between the variables
- 5. Elements of Research Design Elements of research design Method of data analysis Population, sample and sampling technique Tools & methods of data collection Time & place of data collection The Approach Qualitative Quantitative Or both with/without
- 6. Classification of research Approaches • Quantitative research Approach • Qualitative research Approach • Quantitative research Approach: is a systematic and objective process where numeric or numbers are used to obtain information.
- 7. Classification of Quantitative research Approach • Experimental • Non Experimental Experimental Research Design: Experimental Research design is defined as observation under controlled condition. It is description and analysis of which will be or what can be made. It occurs under careful condition. Experiment is the most scientific research method.
- 8. AIMS AND OBJECTIVES OF EXPERIMENTAL RESEARCH To provide scientific proof of etiology, risk factors may permit modification or control of those disease. To provide a method of measuring effectiveness and efficiency of health. To provide services for prevention, control and treatment of disease and improve the health of the population
- 9. MAJOR STEPS IN EXPERIMENTAL RESEARCH DESIGN 1. Select a sample from population by random sampling. 2. By random assignment, subdivide the sample into two sub-samples. 3. Specific one sub-sample, the experimental group and other the control group. 4. Before introducing the independent variable observe and record all important characteristics of the two groups. 5. Introduce the independent variable into the experimental group but with holds it from the control group.
- 10. 5. Introduce the independent variable into the experimental group but with holds it from the control group. 6. After introducing the in-dependable variable, observe the dependent variable in both experimental and control group. 7. Compare the changes that occur in experimental group with those that may have occurred in the control group. 8. Record the difference. 9. Compare these values with statistically computed values that judge the significance of the difference, and indicate whether of not the observed differences could have occurred by chance.
- 11. TYPES OF EXPERIMENTAL DESIGN 1. True or classical experimental design. 2. Quasi-experimental design. 3. Pre- experimental design
- 12. TRUE OR CLASSICAL EXPERIMENTAL RESEARCH CHARACTERISTICS 1.Manipulation It is a process by which the researcher manipulates the independent variables by administering an experimental treatment to one group of the subjects, called experimental group & observe the effects of this experimental treatment on the dependent variables.
- 13. 2.Control • It refers to the use of control group and controlling the effects of extraneous variables on the dependent variable in which the researcher is interested. • The subjects in the control and experimental group are similar in number and characteristics, but the subject in the control group receive no experimental treatment or any intervention at all. The experimental group receives the planned treatment or intervention, and a comparison is made with the control group to observe the effect of this treatment or intervention.
- 14. 3.Randomization • Means that every subject has an equal chance of being assigned to experimental or control group. Also known as random assignment of subjects, which involves the placement of study subjects on a random basis. Through random assignment of subject under experimental or control group, chances of systemic bias is eliminated.
- 15. 3things should be noted in random assignment 1. it takes place before the experiment begins 2. it is a process of assigning or distributing students to groups. 3. The use of random assignment allows the researcher to form groups that, - right at the beginning of study are equivalent - is intended to eliminate the threat of additional, or extraneous variables (aware or not aware by researchers), that affect the result of study.
- 16. Symbolic presentations Some Symbols used are: • R= Random assignment of the subject to groups • O= Observation or measurement of dependent variable • X= Experimental treatment or intervention Subscript number appearing after X(X1,X2, X3…) indicates the treatments such as first treatment, second treatment, third treatment, and so on.
- 17. Types of True Experimental Design • True Experimental Design Post test only Pre test Post test only Solomon 4 groups Factorial Randomized block Crossover True Experimental Design
- 18. Post test only control design Random assignment Exp. group Control group Treatment Post test Post test
- 19. Pretest- post- test- only design Random assignment Exp. group Control group Treatment Post test Post test Pretest Pretest
- 21. • Involve two or more independent variables, called factor, in a single design. • Extend the number of relationships that may be examined in an experimental study. • Allow to study the interaction of independent variables with 1 or more other variables called (Moderator variables) • It maybe a treatment variables or subject characteristics variables • It can be posttest only or pretest-posttest control group (with or without random assignment)
- 22. • a modification of the pretest-posttest control group design • it involves 1 treatment variable having 2 levels (X1 and X2) • one moderator variable also having 2 levels (Y1 and Y2) • 2 groups receive a treatment (X1) • 2 groups weren’t (X2) • both groups receiving a treatment where differ in Y, as well as not receiving a treatment • hence both variables or factors has 2 levels it is called 2 by 2 factorial design
- 23. Diagram of Factorial Designs • Treatment R O X1 Y1 O • Control R O X2 Y1 O • Treatment R O X1 Y2 O • Control R O X2 Y2 O
- 24. Randomized block design • When there are a large number of experimental comparison groups, the randomized block design is used to bring homogeneity among selected different groups. E. g., a researcher wants to examine the effects of three different antihypertensive drugs on patient with hypertension. To ensure the homogeneity among the subjects under treatment, researcher randomly places the subjects in homogenous blocks like patients with primary hypertension, D M with hypertension, renal patient with hypertension. In this only the type of drug is manipulated & the type of patients with hypertension are simply grouped in different blocks with similar characteristics to ensure homogeneity.
- 25. Crossover Design In this, subjects are exposed to more than one treatment, where subjects are randomly assigned to different orders of treatments. Also known as “repeat measures design”.
- 26. • Advantages • Most powerful design to establish causal relationship between independent and dependent various. • Variables are more easily controlled than in human studies. • can yield a greater degree of purity. • Can create conditions in a short period of time. Disadvantages • Most of the times, the results can not be replicated due to ethical problem. • Not possible to impose control over extraneous variables when study conducted in natural settings. • Very difficult to gain cooperation from participants
- 27. QUASI EXPERIMENTAL RESEARCHDESIGN Quasi Experimental Design is may be a quantitative research Design in which there is a ways manipulation of independent variables and control measured is applied. Quasi means similar to or resembling. Quasi Experimental Design: There are several quasi experimental design, but two are more important in nursing research. When randomization is not used to create group of subject the researcher can not be confident that the group and comparison group are equivalent, because there is no randomization, e.g. suppose we wish to study the effect of introducing the problem oriented method of charting of nursing staff, the system is to be implemented in a six bedded hospital. Therefore, we decide to use as a comparison, nurses in another hospital, that is similar, but that is not instituting the problem method of charting. We decide to gather data on staff moral in both hospitals, prior to implementing the new charting system.
- 28. Types of Quasi experimental Design • Two most frequently types are: • Non Randomized control group design: also known as non equivalent control group design. In this, experimental and control groups are selected without randomization & dependent variables are observed in experimental as well as control groups before the intervention. Later, experimental group receives treatment and post test observation of dependent variables is carried out to assess the effect of treatment on experimental group.
- 29. Time series Design • Useful when the experimenter wants to measure the effect the treatment of over a long period of time. • The experimenter would continue to administer the treatment and measure the effects. • Generally it is a single- subject research, researcher carries out an experiment in a small number of individuals, by alternating between administering and then withdrawing the treatment to determine the effectiveness of the intervention.
- 30. Advantages 1. Practicality:- (Can use in practice). 2. Feasibility:- benefit for everybody. 3. Generalizability:- In general use. Disadvantages: There are several generally alternative explanations for observed result e.g. the case in which we administer certain medications to a group of infants whose mothers are heroin addicts and gets a weight gain and low weight infant and do the comparison non-addicted mothers.
- 31. Pre experimental research • Is considered very weak because the researcher has the very little control over the experiment. Types: One shot case design No random assignment of subjects to the experimental group and no control group at all. A single experimental group is exposed to a treatment and observations made after treatment. One group pre test post test design
- 32. One group pre test post test design • Only the experimental group is selected as the study subject. Pretest observation is made before implementation of the treatment, the treatment is administered and finally the post test observation of dependent variables is carried out to assess the effect of treatment. Advantages • Very simple and convenient to conduct • Most suitable design for beginners Disadvantages • A very weak design. • Very little control over the research. • Higher threat to internal validity and biasness.
- 33. Non experimental Research Design • In this , no experimental manipulation is made during the course of the research work. Almost all the nursing research studies have the non experimental research design, as nursing deals with the human being such as with the patients and people where true experimental manipulation may not be possible with human behaviors. As the human nature lie at the core of nursing, the main interest of nursing research studies is on the human features which are frequently variable and which can, by no means, experimentally controlled or manipulated. Because the subjects of a sample, even if divided into groups and even though the groups may appear similar, may have there differences in personality traits, beliefs, mental, social and spiritual behaviors, where absolutely accurate discrimination between control group, experimental group, comparison group may not be possible at all. Further there may be several constraints and difficulties in terms of patient’s inconveniences where experimental studies are not possible.
- 34. Classification of non experimental design • Descriptive research design • Co relational research design • Survey research research design • Evaluation research research design • Methodological research design
- 35. Descriptive research design • Is designed to describe the characteristics of phenomena of researcher’s interest as they exist. Descriptive research studies make observation, description and documentation of various aspects of a situation or a phenomenon which occurs in a natural setting and how frequently it occurs. E.g., epidemics. E.g., in this study, the researcher may like to describe the family background of women, seeking medical termination of pregnancy such as what has driven them for taking such an act.
- 36. Types • Univariant : Univariant descriptive design are undertaken to describe the frequency of occurrence of a phenomenon rather than to study relationship • -Exploratory: used to identify, explore & describe the existing phenomenon & its related factors • Comparative: it involves comparing two or more samples of study subjects on one or more variables often at a single point of time. Used to compare two distinct groups on the basis of knowledge, perceptions & attitudes.
- 37. Co relational research design Co relational research studies are those which are designed to explain or describe relationships between two are more variables. This type of research studies, allows the researcher more flexibility in investigating natural and complex relationship amongst variables, in this possible to collect a large amount of data
- 38. Types of co relational Research Design • Prospective : researcher relates the present to future. Prospective studies start with a presumed cause and then go to presumed effect. These designs are often longitudinal but may also be cross sectional. E.g., data collected from pregnant women regarding any history of infection among women during their current pregnancies, next observes fetal development & pregnancy outcome and finally analyses the relationship of maternal infection during pregnancy and fetal development and pregnancy outcome.
- 39. Conti… •Retrospective : here the researcher studies the current phenomenon by seeking information from the past. In this the researcher links the present phenomenon with the past.
- 40. Conti… Advantages • increased flexibility • An efficient and effective method • A potential for practical application in clinical settings • A potential foundation for future • A possible framework for investigating relationship between variables that are not manipulable
- 41. Conti… Disadvantages • Variables of interest are beyond the researcher’s control • Researcher is unable to manipulate the variables of interest • Generalizability is decreased • Researcher is unable to determine a causal relationship between the variables because of the lack of manipulation, control and randomization.
- 42. Developmental Research design • Examining the phenomenon in respect to the time Types • Cross- sectional design: is one in which the researcher collects data at particular point of time. These studies are easier and more convenient to carry out. • Longitudinal: is used to collect data over an extended time period. Its value is in its ability to demonstrate changes over a period of time.
- 43. Epidemiological research • The investigation of the distribution &cause of diseases in a population is called epidemiology. Epidemiological studies are generally conducted to investigate causes of different diseases in either prospective approach ( cause to effect) or retrospective (effect to cause). However, in epidemiology different terminology is used for prospective and retrospective designs. Prospective studies are known as cohort studies and retrospective studies are called case control studies.
- 44. Cont… • Cohort studies: in this design, a longitudinal approach is used to investigate the occurrence of a disease in existing presumed cause. E. g., a researcher longitudinally observes the smokers for development of lung cancer. • Case control Studies: in this design, causes of a disease are investigated after the occurrence of a disease. E. E. g., a researcher investigates the history of smoking in patients diagnosed with lung cancer.
- 45. Survey research method • Survey research method is designed to obtain information from the population on various issues and aspects. such as about peoples personal characteristics, personality traits, people’s behaviors, feelings, attitudes, opinions, values, attitudes, likes, dislikes and so on. These informations are collected by asking people questions through personal interviews or telephonic interviews. .
- 46. Conti… Advantages • A great deal of information can be obtained from a large population in a fairly economical manner • Survey research information can be accurate Disadvantages • Information obtained tend to be superficial • The breadth rather than the depth of information is emphasized • Requires a great deal of expertise • Large scale surveys can be time consuming and costly
- 47. Evaluation Research Method • It is designed to assess or appraise the effectiveness of a practice or a program. • These studies evaluate the function of such a program or a practice as these were designed to perform in certain ways. These studies focus on collection of information on how the programs or practice are functioning, whether they are meeting the objectives effectively, with an aim to either modify, improve or alter certain programs & practices. E g., the researcher may be interested in investigating the effectiveness of certain patient care or nursing care practices. The researcher, after the evaluation study, may find that the present nursing care practices or the existing nursing care measures are not yielding to expected results. The practice need to be modified or to be improved upon.
- 48. Methodological Research • This type of research plan is designed to investigate the ways of obtaining information in developing, validating and evaluating research tools, study modules and procedure manuals which would serve as sound instruments or items in many nursing care practices.
- 49. Qualitative Research Approach • It is often associated with non scientific or naturalistic method of inquiry and investigation. The qualitative research approach attempts to inquire and explore the dynamic and holistic human experiences, emphasizing the human complexity in a natural setting. It provides an in- depth information which has the potentials to reflect multiple dimensions of various phenomena. Information is gathered directly from the people and is presented in a narrative descriptive or subjective form. Advantages It is flexible Disadvantages • This type is unstructured in nature.
- 50. Characteristics • Involves a merging together of various data collection strategies. • Flexible and elastic • Holistic, striving for an understanding of the whole. • Requires researcher to become intensively involved. • Requires researcher to become the research instrument. • Requires ongoing analysis of the data to formulate subsequent strategies and to determine when field work is done.
- 51. Classification • Ethnographic Research approach • Phenomenological • Ground theory • Historical • Case study Research
- 52. Ethnographic Research design • In this, the data is collected on cultural behavior of a group of people. It includes cognitive as well as materialistic behavior. It attempts to size the members beliefs, values, activities and knowledge of the people under study in depth. This information is collected through an intensive face to face interactions. • The researcher in this type, attempts to investigate cultural behavior such as how the culture is carried on, communicated and transmitted. • It aims at gathering information on 3 main aspects, such as: • Cultural behavior • Cultural aspect • Cultural speech
- 53. Conti… The factual information is collected by various methods such as observations, interviews and other evidences such as dairies, photographs etc. In ethnographic research, the researcher needs to build up a close relationship with the member of a particular group. Then the researcher needs to participate in the cultural activities and events and also needs to spend with them substantial amount of time- then only
- 54. Conti… • An ethnographic research study is conducted to acquire factual information of the life style practices with regard to food, hygiene, health, education, child birth etc. of an indigenous cultural group dwellings.
- 55. Phenomenology • An approach to discover the meaning of people’s life experiences. • Phenomenological inquiry typically involves four basic steps: • Bracketing :- process of identifying and holding preconceived beliefs & opinion one may have about the phenomenon under investigation. • Intuiting: when the researcher remains open to the meanings attributed to the phenomenon by those who have experienced it. • Analysis phase: categorizing & making sense of the essential meanings of the phenomenon. • Descriptive phase: when the researcher comes to understand and define the phenomenon.
- 56. Ground theory • An approach to the study of social processes and social structures. It is conducting in a naturalistic setting. Data collected is done through a series of intent observation, in depth interviews etc. • The research method has contributed to the formulation and development of middle range nursing theories.
- 57. Phases of Grounded Theory Writing Sorting Memoing Coding Note Taking Data collection
- 58. Historical Approach • Systematic collection of facts and trends or events of the recent past and also of the distant past, which are long lost but which are very important for the mankind. This approach may illuminate new facts which may lead to new discoveries of the past happenings. • information can also be obtained from the written records such as periodicals, biographies, personal letters, legal documents, encyclopedias, photo albums, newspapers etc.
- 59. Sources • Obtained from : • Primary sources • Secondary sources Primary sources: provides first hand information such as original documents which represent most natural and direct link. These are unbiased sources. Secondary sources: provide second hand, third hand or even fourth hand data, such as narration of historical events. Biased by the writer’s opinions which obscure the accuracy of the data.
- 60. Steps of conducting historical Research • Define and formulate a well defined and feasible problem • Formulate hypothesis or specific objectives • Outline the data collection methods, tools and sources • Collect data • Data evaluation • Interpret the findings • Analyze the results • Documentation , communication and findings for present status s
- 61. Case study Approach • It is in depth, intensive investigation of individual, a family, group, a community, institution or other social unit. It provide both quantitative and qualitative data. • It can be explanatory, descriptive as well as exploratory in nature. It provides evidence based data in detail. • The focus is typically on determining the dynamics of why the subject of the investigation thinks, behaves, or develops in a particular manner rather than what his or her status, progress, actions, or thoughts are. It clarifies concepts and variables.
- 62. Types of Broad categories quantitative Types of Research design Research design Main features I. Experimental Research design 1. True Experimental Design - Post test only control design - Pretest –posttest control group design - Solomon four group design - Factorial design - Randomized block design - Crossover design Manipulation of independent variable , in the presence of control group, randomization. 2.Quasi experimental design -Nonrandomized control group design -Time series design Manipulation of independent variable , but absence of either randomization or control group
- 63. 3. pre- experimental d design -one shot case design -one group pretest- posttest design Manipulation of independent variable , but limited control over extraneous variables, no randomization and control group II. Non Experimental Research design Descriptive design -univariate descriptive design -exploratory descriptive design -comparative descriptive design Accurate description of characteristics of individual situation, or group and the frequency with which a certain phenomenon occurs in natural setting without imposing any control or manipulation -Univariate descriptive: to describe the frequency of occurrence of a phenomenon rather than to study relationship -Exploratory: investigating the phenomenon & its related factors Comparative: comparing occurrences of a phenomenon in two or more groups
- 64. 2. Co relational/ ex post facto design -prospective -retrospective Examining the relationship between two or more variables in a natural setting without manipulation or control Prospective: examining relationship from cause to effect Retrospective: examining relationship from effect to cause 3. Developmental Research design -Cross sectional - longitudinal Examining the phenomenon in respect to the time Cross sectional: Examining the phenomenon only at one point in the time Longitudinal: Examining the phenomenon at more than one point in time
- 65. 4.Epidemiological design -Case control studies - cohort studies The investigation of the distribution &cause of diseases in a population is known as epidemiology 5. Survey research design These are investigation in which self reported data are collected from sample with the purpose of describing population on some variables of interest III. Other additional research designs 1. Methodological studies 2. Meta analysis Research conducted to develop, test and evaluate the research instruments & methods Quantitative combining & integrating the findings of the multiple research studies on a particular topic
- 66. 3. Secondary data analysis In this the data collected in one research is reanalyzed by another researcher, usually to test new hypotheses 4. Outcome research It involves the evaluation of care practices & systems in place. Used in nursing to develop evidence based practice and improve nursing actions 5. Evaluation studies 6. Operational research It involves the judgment about success of a programmes, practices, procedures & policies Involves the study of complex human organizations & service to develop new knowledge about institutions, programmes, facilities & personnel to improve working efficiency of an organization.
- 67. Types of qualitative Research design Phenomenological research It is examines human experiences through the descriptions provided by people involved Ethnographic research Grounded theory It involves the information collected from certain cultural groups, by living with people of those groups & from their key informants, who are believed to be most knowledgeable about the selected culture . Theory is developed inductively from a corpus of data acquired by a participant observer
- 68. Case study Research on a phenomenon by studying in depth a single case example. The case can be an individual person, an event, a group, or an institution Historical research Systematic collection and objective evaluation of data related to past occurrences in order to test hypotheses concerning causes , effects, or trends of these events that may help to explain present events and anticipate future events Action Research It seeks action to improve practices and study the effect of the action that was taken