Mastering Research Designs: Objectives, Definitions, Elements, and Criteria

RESEARCH DESIGNS Ms. Justy Joy Asst. Professor

OBJECTIVES Central objective At the end of the class students will gain knowledge on research design and able to apply this into practice with positive attitude Specific objective Students will be able to Define research design List down the need for research design Describe the elements of research design Enlist the elements of research design Describe the types of research designs Explain he criteria for quantitative design

DEFINITION Research design is the plan, structure and strategy of investigation conceived so as to obtain answers to research questions and to control variance Kerlinger A research design is the specification of methods and procedure for acquainting the information needed. It is the overall operational pattern or framework of the project that stipulates what information is to be collected from which source and by what procedures. Green and Tull

Research design is the master plan specifying the methods and procedures for collecting and analysing the needed information in a research study Research design is the researchers overall plan for answering the research questions or testing the research hypotheses.

NEED FOR RESEARCH DESIGN Maximum information with minimum effort, money and time Minimum bias and maximum reliability Serves as planning tool for data collection and analysis. Minimize error

ELEMENTS OF RESEARCH DESIGN Approach Variable Population, sample and sampling technique Time Setting Tool and method of data analysis

CRITERIA FOR SELECTING THE RESEARCH DESIGN Nature of the topic under study Purpose of the study Ethical implication and feasibility Availability of subject and facilities Validity of data Experience and knowledge of the researcher Interest and motivation

GUIDELINES FOR DESIGNING A STUDY Number and type of participants Selection and assignment of participants to one or more groups Number of observations needed Frequency of data collection Accuracy Control of the problem

TYPES OF RESEARCH DESIGN 1. Quantitative design Experimental design Non experimental design Other additional designs 2. Qualitative design 3. Mixed methodology designs

QUANTITATIVE DESIGN Experimental design design Non experimental Other additional designs True experimental design Quasi experimental design Pre experimental design Descriptive design Survey design Correlational design (Ex post facto design) Developmental design Epidemiological design Outcome research Meta analysis Methodological studies Secondary data analysis Evaluation studies Operational research

True experimental design Quasi experimental design Pre experimental design Post test only design (after only design) Pre test post test design Solomon four group Factorial design Randomized block design Cross over design (Repeated measure design) Non equivalent control group design Time series design Multiple time series design One shot case study One group pre test post test

QUALITATIVE DESIGN Phenomenological design Ethnographic design Grounded theory Historical method Case study design Action research

MIXED METHODOLOGY DESIGN Exploratory sequential design Explanatory sequential design Embedded research design Convergent design

COMPARISION OF DESIGNS IN SOCIAL SCIENTIFIC STUDIES AND MEDICAL RESEARCH Randomized control trial Randomized trial or controlled trial Observational study Case control study Cohort study Named Arm or intervention True experimental design Quasi experimental design Pre experimental design Retrospective study Prospective study Named - Control group

DIFFERENCE BETWEEN QUALITATIVE & QUANTITATIVE DESIGN Interactive, subjective and Systematic process Is concerned with qualitative phenomena It deals with questions related to human experience Studies in natural setting Formal, objective and systematic process It concerned with testing relationship and cause & effect between variables It deals with measurement of quantity Natural or artificial setting

CHARACTERISTICS OF TRUE EXPERIMENTAL DESIGN Manipulation Control Randomization

1. MANIPULATION Manipulate independent variable and study the effect on dependent variable Researcher manipulate a nursing intervention and applies it to some subjects while withholding the same from others Usual manipulations are exercise, teaching, counseling, nutritional intervention, stress reduction and implementation of protocol of nursing

EX.. Study on efficiency of progressive muscle relaxation exercise on level of pain among post operative patients Study on effect of teaching programme on dental caries attitude among children Effect of mouth wash on prevention of ventilator associated pneumonia

2. CONTROL To ascertain the validity researcher must control extraneous variable 3 types of control Negative control- control group neither receive any placebo or any other treatment Clear control- receives placebo Positive control- receives other treatment or experimental interventions

Measures of control Matching Counterbalancing An alternative intervention Placebo or pseudo-intervention Standard method of care Different doses Wait list control group Homogeneity by statistical test

THREATS TO INTERNAL VALIDITY Selection bias History Maturation Testing Instrumentation change Mortality Interaction with selection Diffusion or limitation of treatments compensatory equalization of treatments Compensatory rivalry by respondents receiving less desirable treatment

THREATS TO EXTERNAL VALIDITY Hawthrone effect Experimenter effect Reactive effect of the pre test Interaction of selection and treatment Interaction of setting and treatment Interaction of history and tratment

3. RANDOMIZATION It also called as random allocation or random assignment Each unit have a equal chance of selection It helps to reduce the bias

RANDOMIZATION PROCEDURES Random allocation or random concealment Cluster allocation Permuted random allocation Stratification Randomized consent or Zelen design Partially randomized patient preferences (PRPP)

STEPS OF CONVENTIONAL RANDOMIZATION Screen for eligibility of the study Eligible Ineligible Obtain informed consent Consent guaranteed Consent withheld Collect baseline data Randomly assign to condition Administer intervention Administer control conditions Collect outcome data

COUNTERFACTUAL MODEL It states that what would have happened to the same people exposed to a causal actor if they simultaneously were not exposed to the causal factor It represents an ideal that cannot be ever realized but it is a good model to keep in mind in designing a study to provide evidence about cause and effect.

CRITERIA FOR CAUSALITY First criteria is temporal: a cause must precede an effect in time Second is that there be an empirical relationship between the presumed cause and presumed effect Final criteria for establishing a casual relationship is that the relationship cannot be explained as being caused by a third variable

Other criteria's are Meta analysis Consistency Biologic possibility

ASSIGNMENT Write example for experimental and pre experimental design

Reference Polit D F & Beck C T, Nursing Research: Principles and Methods , Lippincott Williams and Wilkins Burns N. & Susan K Groove. Understanding Nursing Research building an Evidenced Based Practice. W.B. Saunders, St. Louis. Suresh Sharma. Nursing research and statistics. Elsevier