UNIT – III Research design Prepared by Gireesh G. R
LEARNING OBJECTIVES At the end of class the learner will be able to • Understand the meaning of research design • List the classification of research designs • Recall advantages and disadvantages of experimental research designs • Differentiate between experimental and non experimental research designs
Research design • Research design is a blue print for the conduct of a study that maximizes control over factors that could interfere with the study’s desired outcomes. -Nancy. B, 1995
Elements It includes • Description of subjects (Who) • Observations of variables (What) • Measures of time (When) • Selecting of setting (Where) • Role of the investigator.
Selecting a research design • Nurse researcher has to weigh many considerations while selecting research design in clinical practice. • They are as follows: • Experience of researcher and level of knowledge • Availability of subjects and faculty, equipment • Feasibility v Time v Cost v Control • Ethical consideration • Application
Parts of Research Design The sampling design: Deals with the method of selecting samples to be observed for study Observational design: Relates to the conditions under which the observations are to be made The operational design: Deals with techniques by which the procedures specified can be carried out-tools The statistical design: Concerns with the question of how many items are to be observed and how the data gathered are to be analyzed
Characteristics of Good Research Design • Appropriateness • Lack of bias - sampling, data collection and statistical procedures • Power - to detect relation between DV and IV • Precisions - control over variables
Need for research design To • Facilitate smooth sailing of various research operations. • Make the research as efficient as possible. • Provide maximum information with minimum expenditure of time and money.
Classification • Experimental : – True or Classical experimental design: • Pre test and post test control group design • Solomon four group design • After / post test only control group • Randomized • Factorial design • Crossover – Quasi experimental design • Non randomized control group • Time series – Pre experimental design • One shot case study • One group pre test and post test design • Static group comparison design
Contd…. Non experimental research design: – Descriptive design – Explorative design – Comparative design – Evaluative design – Correlation design
Experimental Design • Experiment is a scientific investigation that makes observation and collected data according to the explicit criteria. Investigation may be physiological, psychological or educational or combined. • It is called as methodological design or the quantitative design to test causality.
Uses of experimental design in nursing v. To determine cause and effect relationship and restoring wellness. v. Essential in developing effective approach to maintaining health. v. Evaluate the outcomes in terms of efficacy and cost effectiveness
True Experimental Designs Uses : • Obtain true representation of the cause and effect. • When greatest amount of control is required with least possible error. • Eliminate all factors influencing the dependent variable other than the independent variable under study. • Prevent other element to introduce during observation of the specific cause and the effect under study.
Quasi - experimental Design • facilitates the research for knowledge and examination of casualty in situations in which complete control is not possible. • control as many threats to validity as possible in a situation in which some of the components of true experimental design are lacking.
Characteristics of experiment research design • Randomization: Refers to random assignment of number of group. Participant has equal chance to be in control or experimental group. • Manipulation: It is the process of manipulating I. V. , so that its effect on the D. V. can be observed or measured. In experimental designs, the causative variable must be amenable to manipulation by the researcher that is “does something”, to subjects in the experimental condition. • Control: Experimenter introduces one or more controls over the experimental situation including the use of a control group. It means introduction of one or more constraints into experimental situation acquired by manipulating casual or independent variable, preparing experimental protocol and by using comparison to a group.
Essential Elements of Experimental Research v. Random assignment of subjects to groups v. Precisely defined independent variable v. Manipulation of the independent variable v. Researcher’s control of the experimental situation and setting, including a control or comparison group v. Clearly identified sample criteria v. Carefully measured dependent variables v. Controlled environment for conduct of study
True Experimental Designs A. Pre test – post test with control design Experiment group Pre test Experimental treatment Post test Random assignment control group Pre test Post test
Solomon four group design Experiment group Random control assignment group Experiment group control group Pre test Experiment treatment PRETEST Post test Experiment treatment Post test
Post test only control group design Experime nt group Experiment treatment Post test Random assignment control group Post test
RANDOMIZED BLOCK DESIGN Control of inherent differences between experimental subjects & differences in experimental conditions is one of the difficult problems faced by researcher in biological sciences. When there a large number of experimental comparison groups, the randomized block design is used to bring homogeneity among selected different groups. This is simple method to reduce the variability among the treatment groups by a more homogeneous combination of the subjects through randomized block design.
Contd… For example, a researcher wants to examine the effects of three different antihypertensive drugs on patients with hypertension. In this example, to ensure the homogeneity among the subjects under treatment, researcher randomly places the subjects in homogeneous groups (blocks) like patients with primary hypertension, diabetic patients with hypertension, & renal patients with hypertension.
Blocks Types of antihypertensive drugs Patients with primary hypertension (I) Diabetic patients with hyper tension (II) Renal patients with hypertension (III) A A, III B B, III C C, III
FACTORIAL DESIGN In factorial design, researcher manipulates two or more independent variables simultaneously to observe their effects on the dependant variables. This design is useful when there are more than two independent variables, called factors to be tested. For example, a researcher wants to observe the effect of two different protocols of mouth care on prevention of VAP when performed at different frequencies in a day.
Contd… This design also facilitates the testing of several hypothesis at a single time. Typical factorial design incorporates 2 X 2 or 2 X 3 factorial, but it can be in any combination. The first number (α) refers to the independent variables or the type of experimental treatments, & the second number (β) refers to the level or frequency of the treatment
Frequency of mouth care Protocols of the mouth care Chlorhexidine (α 1) Saline (α 2) 4 hourly (β 1) α 1…. β 1 α 2…. β 1 6 hourly (β 2) α 1…. β 2 α 2…. β 2 8 hourly (β 3) α 1…. β 3 α 2…. β 3
CROSSOVER DESIGN In this design, subjects are exposed to more than one treatment, where subjects are randomly assigned to different orders of treatment. It is also known as ‘repeat measures design’. This design is more efficient in establishing the highest possible similarity among subjects exposed to different conditions, where groups compared obviously have equal distribution of characteristics.
Contd… • Through crossover design is considered as an extremely powerful research design, sometimes it is not effective because when subjects are exposed to two different conditions, their responses of the secondition may be influenced by their experience in the first condition.
For example, when we are comparing the effectiveness of the chlorhexidine mouth care protocol on group I & saline mouth care protocol on the subjects of group II. Later, the treatment is swapped, where group I receives the saline mouth care & group II receives chlorhexidine. In such studies, subjects serve as their own control. Groups Group II Protocols of the mouth care Chlorhexidine (α 1) Saline (α 2) Chlorhexidine (α 1)
ADVANTAGES OF TRUE EXPERIMENTAL DESIGN Experimental research designs are considered the most powerful designs to establish the causal relationship between independent & dependant variables. Where the purpose of research is explanation, causal relationship may be established among the variables by experimentation, especially in studies involving physical objects, where the variables are more easily controlled than in human studies. In this studies, the controlled environment in which the study is conducted can yield a greater degree of purity in observation.
Contd… Conditions not found in a natural setting can be created in an experimental setting, where the independent variable is manipulated by investigator. In the experimental approach, we can often create conditions in a short period of time that may take years to occur naturally. For example, in genetic studies we can breed strains in very small time, which would take a long time in nature to occur. When the experiment is conducted in a laboratory, experimental unit, or other specialized research setting, it is removed from the pressure & problems of real-life situations & the researcher can pursue his or her studies in a more leisurely, careful, & concentrated way
DISADVANTAGES OF TRUE EXPERIMENTAL DESIGN Most of the times, the results of experimental research designs cannot be replicated in studies conducted on human beings due to ethical problems. For certain research problems, because of the danger to physical & psychological health of the human subjects, it is not possible to conduct experiments on human beings. Many of the human variables neither have valid measurable criteria nor instruments to measure them. For example, patient welfare or level of wellness cannot be measured on any scale or by any instrument. In these situations, if a refined experimental design is used, there may be a mismatch of research design & the variable- measuring instruments.
Contd… In experimental studies conducted in natural settings like hospitals or community, it is not possible to impose control over extraneous variables. Another disadvantage of the experimental research design is that it is very difficult to get cooperation from the study participants, because it may involve medical or surgical treatment or intervention, which may make the prospective subjects reluctant to participate in research study.
Quasi experimental design Non randomized control group Experimental group Pre test Experimental treatment Post test Control group Pre test No randomization Post test
Time Series Design E O 1 O 2 O 3 O 4 X C O 1 O 2 O 3 04 O 8 O : observation X : treatment O 5 O 6 O 7 O 8 O 5 O 6 O 7
ADVANTAGES OF QUASIEXPERIMENTAL DESIGN Quasi-experimental designs are more frequently used because they are more practical & feasible to conduct research studies in nursing, where in the absence of a large sample size, randomization &/ or availability of control groups are not always possible. This design is more suitable for real-world natural setting than true experimental research designs. It allows researchers to evaluate the impact of quasi- independent variables under naturally occurring conditions. It may be able to establishing casual relationship. Wherein some of the hypotheses are practically answered through this design only.
Disadvantages There is no control over extraneous variables influencing the dependant variables. The absence of a control group or lack of control over the research setting makes the results of this design less reliable & weak for the establishment of casual relationship between independent & dependant variables.
Pre experimental design One shot case study: X O One group pre test and post test O 1 X O 2
STATIC GROUP COMPARISON DESIGN X O 1 ----O 2 • In the static group comparison study, two groups are chosen, one of which receives the treatment and the other does not. • A posttest score is then determined to measure the difference, after treatment, between the two groups. • As you can see, this study does not include any pre -testing and therefore any difference between the two groups prior to the study are unknown.
ADVANTAGES OF PRE-EXPERIMENTAL DESIGN Very simple & convenient to conduct these studies in natural settings, especially in nursing. o Most suitable design for the beginners in the field of experimental research o
DISADVANTAGES OF PREEXPERIMENTAL DESIGN o o o Considered a very weak experimental design to establish casual relationship between independent & dependant variables, because it controls no threat to internal validity. It has very little control over the research. It has a higher threat to internal validity of research, & may have a selection bias, which can be very serious threats for in using this particular design.
According to the objective of survey, the survey research can be classified as follows: v Descriptive design v Exploratory design v Explanatory design v Comparative design v Evaluative design v Co relational design
Descriptive survey • Descriptive surveys are carried out for the purpose or providing an accurate portrayal of a group of subjects with specific characteristics. • Descriptive studies entail the precise measurement of phenomena as they currently exist within a single group. • The objectives of the descriptive survey is description only. • It does not mean that they can not be the basis of extensive implications and actions. • The main purpose of this research is to describe objectively the nature of the situation under study • Descriptive studies are often utilized by researcher to determine the extent or directions of attitudes or behaviours.
Exploratory survey • The word ‘explore ’implies scrutinizing unknown region for the purpose of discovery. • Exploratory studies serve this purpose and are particularly useful during the early stages of investigating the relationship , between phenomena about which not much is known
Explanatory research design These are conducted to provide casual explanation of phenomena or situations. v. According to warwick and lininger the following three condition as must be satisfied to establish a casual explanation: • The cause and effect must be associated with each other • The cause must precede with effect • The other possible explanation of effect should be ruled out.
Comparative survey This popular type of survey used to compare the two distinct groups based on the qualities such as knowledge level, perceptions, or attitudes
Evaluative survey In this survey more frequently today in conjunction with other data gathering technique to conduct evaluation research eg. Evaluate Nursing care given to patients
Correlation survey It is a research design that relates multiple variables measured at a single time point in a sample from a designated population
Critiquing research Design – What research design is used in the study and is it appropriate? – What are the most common threats to the validity of the findings of the design? – What are the possible alternative explanations, and have they been addressed. – What does the another say about the limitations of the study – Are these other limitations related to the design that is not mentioned?
CONCLUSION Thus it can be concluded that research design is essential for developing new strategies to bring out cost effective and cost benefit methods of nursing care through evidence based findings.
Evaluation • Write short notes on classification of research designs • Explain in detail characteristics of good research design • Non experimental research designs • Classification of pre experimental research designs