Download - Research Methodology unit 3
RESEARCH DESIGN
UNIT- 3
RESEARCH DESIGN
Research Design is the “framework” or “blueprint” for collecting the information needed for your project in the best possible way (Malhotra et al., 2002).
Research Design is the conceptual structure within which research is conducted; it constitutes the blueprint for the collection, measurement and analysis of data.
DEFINITION
FUNCTIONS OF RESEARCH DESIGN
According to Black and Champion (1976-77), the three important functions of research design are:
It provides blueprint.
It limits boundaries of research activity.
It enables investigation to anticipate potential problems.
FEATURES OF A GOOD RESEARCH DESIGN
It should be flexible.
It should be appropriate.
It should be efficient.
It should be economical.
It should minimize bias.
It should maximize the reliability of data collected.
It should give the smallest experimental error.
FEATURES OF A RESEARCH DESIGN It should yield maximum information.
It should provide the opportunity for considering different aspects of the problem.
It should provide the means of obtaining information.
It should be appropriate with respect to the availability and skills of the researcher and his staff.
It should be related to : the objective of the problem, the nature of the problem being studied, the availability of time and money for the research
work.
DIFFERENT TYPE OF RESEARCH DESIGNS• DESIGN OF EXPLORATORY OR FORMULATE STUDIES.
MAJOR EMPHASIS IS IN THOSE STUDIES IS THE DISCOVERY OF NEW INSIGHTS OR IDEAS. FOLLOWING METHODS ARE ADOPTED BEFORE THE INITIATION: -– SURVEY OF LITERATURE.– EXPERIENCE SURVEY.– ANALYSIS OF INSIGHT STIMULATING CASES.
• DESIGN OF DESCRIPTIVE STUDIES. MAY INVOLVES FOLLOWING STEPS: -– FORMULATING THE OBJECTIVES OF THE STUDY.– DEFINING THE POPULATION AND SELECTING SAMPLE.– DESIGNING THE METHODS OF DATA COLLECTION.– ANALYSIS OF THE DATE.– EXAMPLE – A DESCRIPTIVE STUDY MAY BE CONCERNED
WITH THE ATTITUDES OR VIEWS TOWARDS ANYTHING.
• DESIGN OF DIAGNOSTIC STUDIES. AIM IS TO FIND THE SOLUTION OF SPECIFIC PROBLEM BY THE DISCOVERY OF THE RELEVANT VARIABLES.
TYPES OF RESEARCH DESIGN
Design of investigation should stem from the problem.
Based on the fundamental objectives or purposes, research design has been classified into:
a)Exploratory or Formulative Research Design.
b)Descriptive and Diagnostic Research Design.
c)Experimental Research Design (Causal Research Design).
EXPLORATORY / FORMULATIVE
RESEARCH DESIGN
EXPLORATORY / FORMULATIVE RESEARCH
DESIGNExploratory studies are carried out to explore a Exploratory studies are carried out to explore a subject. subject.
Exploratory research is unstructured, informal research undertaken to gain background information about the general nature of the research problem.
Designed to generate basic knowledge, clarify relevant Designed to generate basic knowledge, clarify relevant issues, uncover variables associated with a problem, issues, uncover variables associated with a problem, uncover information needs, and/or define alternatives for uncover information needs, and/or define alternatives for addressing research objectives.addressing research objectives.
Uses/Objectives of exploratory research:
Gain background information
Define concepts more clearly
Develop operational definitions
Clarify and formulate a more precise research problem and hypotheses
Achieve new insights or ideas into a phenomenon
Establish research priorities
Methods of conducting exploratory research:
• Survey of related literature / Secondary data analysis
• Experience surveys• Case analysis
EXPLORATORY / FORMULATIVE RESEARCH
DESIGN
Survey of Related Literature • Refer conceptual literature,trade literature and published
statistics (secondary sources).
• Hypothesis stated by earlier researchers may be reviewed and their usefulness be evaluated as a basis for further research.
• In cases where hypothesis have not been formulated, review the available material for deriving hypothesis from it.
• In this way the researcher should review and build upon the work done by others.
EXPLORATORY / FORMULATIVE RESEARCH
DESIGN
Experience Surveys ( depth interviews)• Survey of people who have practical experience
with the problem to be studied.• Knowledgeable people with varying points of
view.• Unstructured and informal interviews.• It reflects an attempt to get all available
information from the people who have some knowledge of subject under investigation.
EXPLORATORY / FORMULATIVE RESEARCH
DESIGN
Analysis of Selected CasesAnalysis of Selected Cases•Intensive study of related cases or examples or past Intensive study of related cases or examples or past activities.activities.•It provides clues as to how other units or It provides clues as to how other units or companies have dealt with similar issues.companies have dealt with similar issues.•It is suitable for areas where there are few or no It is suitable for areas where there are few or no experienced persons to provide necessary experienced persons to provide necessary information.information.
EXPLORATORY / FORMULATIVE RESEARCH
DESIGN
DESCRIPTIVE AND DIAGNOSTIC
RESEARCH DESIGN
• Descriptive research provides answers to the questions of:–Who–What–Where–When– How
• We cannot answer the question Why? conclusively
DESCRIPTIVE RESEARCH DESIGN
Descriptive Research is designed to provide further insight into the research problem by describing the variables of interest.
The major purpose of descriptive research is the description of the state of affairs as it exist at present.
DESCRIPTIVE RESEARCH DESIGN
Descriptive research studies are aimed at Descriptive research studies are aimed at describing or portrayingdescribing or portraying the characteristics of a the characteristics of a particular individual, group or a situation. particular individual, group or a situation.
e.g. users of a product with different age, education, etc.e.g. users of a product with different age, education, etc.
It is also concerned with specific It is also concerned with specific predictions, with predictions, with narration of facts and characteristicsnarration of facts and characteristics concerning concerning individual, group or situation.individual, group or situation.e.g. sales of a company's product in each of the next five e.g. sales of a company's product in each of the next five yearsyears
OBJECTIVES OF DESCRIPTIVE RESEARCH DESIGN
The study offers the researcher The study offers the researcher a profile or a profile or description of relevant aspectsdescription of relevant aspects of the phenomenon. of the phenomenon.
To estimate the To estimate the proportion of peopleproportion of people in a specified in a specified population who behave in a certain way population who behave in a certain way e.g.: persons who buy from a particular shop.e.g.: persons who buy from a particular shop.
To determine whether certain To determine whether certain variables are associatedvariables are associated e.g.. income and usage of a product.e.g.. income and usage of a product.
OBJECTIVES OF DESCRIPTIVE RESEARCH DESIGN
Classification of descriptive research studies:
– Cross sectional studies: they measure the population at only one point of time.
– Longitudinal studies: they repeatedly measure the same population over a period of time.
DESCRIPTIVE RESEARCH DESIGN
Cross-Sectional Descriptive Studies
Most common and most familiar.
Uses a representative sample of elements from a population, often a sample survey.
Characteristics of the elements are measured once, i.e. it provides a snapshot of the variables under investigation.
Cross-Sectional Descriptive Studies
Disadvantages of sample surveys are:
High level questions, not very deep, which allow for statistical analysis.Expensive in terms of time and money.Technical skills are required for the researcher.Data may be outdated.Data may be outdated.It may draw an artificial picture of what was going on at a It may draw an artificial picture of what was going on at a particular point of time.particular point of time.It is possible that respondents were observed or questioned on a It is possible that respondents were observed or questioned on a bad day.bad day.
Longitudinal Descriptive Studies
Involves panel, i.e. a fixed sample of elements or respondents, which are repeatedly measured over time, i.e. it provides a movie of the variables under investigation.
Panel members are relatively constant over time.Panel may be of two types:
True panelOmnibus panel
Main disadvantage of panels is that they are non- representative.
Diagnostic research studies are carried out to determine the frequency with which something (variables) occurs or its association with something else.
All the studies that are aimed to find out whether certain variables are associated by testing the hypothesis is diagnostic in nature.
DIAGNOSTIC RESEARCH DESIGN
The design concentrates on in-depth analysis of data to identify the factors that contributed to the problem and examine their interrelationships from various angles by bringing as many relevant variables as possible.
The diagnostic design is concerned with the case as well as the treatment.
DIAGNOSTIC RESEARCH DESIGN
CHARACTERISTICS OF DESCRIPTIVE AND DIAGNOSTIC
RESEARCH DESIGN
Existence of a pre-planned research design,
Design should be carefully planned,
Design must be rigid and not flexible,
It should ensure minimization of bias and maximization of reliability of the data collected.
Done using rigid methods with clearspecifications of who, what, when, where,why and how of the research. Frequently use pilot studies to test the datacollection tool and analysis techniques.
Data collection often done through structuredinterviews or questionnaires.
CHARACTERISTICS OF DESCRIPTIVE AND DIAGNOSTIC
RESEARCH DESIGN
EXPERIMENTAL / CAUSAL
RESEARCH DESIGN
EXPERIMENTAL RESEARCH DESIGN
Experimental research design is concerned with making experiments to find out the cause-effect relationship of variables under study.
The main purpose of exp. design is to test a causal hypothesis. Causal hypothesis is a statement that states the cause and effect relationship between two or more variables.
Thus experimental research design is also known as hypothesis-testing or causal research design.
The premise of the design is that something (an independent variable) directly influences the behavior of something else ( the dependent variable).
The presumed cause is called the independent variable and the presumed effect is called the dependent variable.
An independent variable causes or explains variations in the dependent variable.
EXPERIMENTAL RESEARCH DESIGN
In experimental design, besides the terms control and experimental groups, some other terms are also important.
1) Experimental treatment: alternative manipulations of the independent variable that is being investigated or the different conditions under which experimental groups are put.
2) Test units: subjects which are exposed to experimental treatments or subjects whose response to the experimental treatment is measured or observed.
EXPERIMENTAL RESEARCH DESIGN
3) Extraneous variables: those independent variables that are not related to the purpose of the study, but may affect the dependant variable. It is therefore, essential that, extraneous variables should be controlled.
4) Randomization: It refers to the random selection of experimental units or subjects from the larger population without any bias. According to this technique, each member of the population or universe has an equal and independent chance of being selected as sample.
5) Repeated measure: When the same subjects are exposed to all experimental treatments, the experiment is said to have repeated measure.
EXPERIMENTAL RESEARCH DESIGN
• DESIGN OF EXPERIMENTAL STUDIES. PURPOSE OF EXPERIMENTAL STUDIES IS TO TEST A HYPOTHESIS OF CAUSAL RELATIONSHIP BETWEEN VARIABLES. BASIC PRINCIPLES OF EXPERIMENTAL DESIGNS GIVEN BY PROF FISHER.
– PRINCIPLE OF REPLICATION. IT IS REPEATED MORE THAN ONCE. REPLICATION IS INTRODUCED IN ORDER TO GET OR INCREASE THE ACCURACY.
– PRINCIPLE OF RANDOMIZATION. PRINCIPLE INDICATES THAT WE SHOULD DESIGN OR PLAN THE EXPERIMENT IN SUCH WAY THAT THE VARIATIONS CAUSED BY EXTRANEOUS FACTORS CAN ALL BE COMBINED UNDER THE GENERAL HEADING OF ‘CHANCE’.
– PRINCIPLE OF LOCAL CONTROL. WE FIRST DIVIDE THE COMPLETE EXPERIMENT INTO THE MANY PARTS (HOMOGENEOUS PARTS KNOWN AS BLOCKING).
The Principle of Replication:
The term replication has been derived from the fusion of two words – ‘repetition’ and ‘duplication’.
Replication refers to the deliberate repetition of an experiment, using identical procedure, which may sometimes be with a set of subjects in a different setting and at different time periods.
BASIC PRINCIPLES OF EXPERIMENTAL RESEARCH DESIGN
BASIC PRINCIPLES OF EXPERIMENTAL RESEARCH DESIGN
The Principle of Randomization:
Randomization refers to a technique in which each member of the population or universe has an equal and independent chance of being selected as sample.
BASIC PRINCIPLES OF EXPERIMENTAL RESEARCH DESIGN
The Principle of Local Control: A design to be statistically and experimentally sound must
possess the property of local control. According to this principle, we first divide the field into
several homogeneous parts, known as blocks (blocking) and then each such block is divided into parts equal to the number of treatments. Then the treatments are randomly assigned to these parts.
Causality tested through…
Lab experiments – Festinger and Katz (1953) have defined a laboratory experiment as one in which the investigator creates an artificial situation with the exact conditions he wants to have and in which the researcher controls some variables and manipulates other variables.
• All variables are controlled• Influence of external variables minimized• Internal validity maximized
TYPES OF EXPERIMENTS
Field experiments – It is a study carried out in a more or less realistic situation or field where the researcher manipulates one or more independent variables under maximum possible controlled conditions.
• Most credible results• Influence of ‘real world’ settings taken into account• External validity maximized
TYPES OF EXPERIMENTS
Concomitant & Extraneous Variable
• Extraneous Variable : The variables selected for analysis are called
explanatory variables and all other variables that are not related to the purpose of the study but may affect the dependant variable are extraneous.
An almost infinite number of extraneous variables exists that might conceivably affect relationship. Some can be treated as independent variables, but most must either be assumed or excluded from the study. The infinite number of variables has little or no effect on a given situation. Most can be safely ignored. Others may be important, but their impact occurs in such a random fashion as to have little effect.