Janice Long, PhD, RN Patricia Hart, PhD, RN Definition of Design - PowerPoint PPT Presentation

RESEARCH DESIGNS Janice Long, PhD, RN Patricia Hart, PhD, RN

Definition of Design • Research design is the master plan that guides and holds together all the major parts of the research project to address the central research questions. • samples or groups • measures • treatments or programs • time elements

Choosing a Design • The research problem dominates the design. • The design you choose is based on the problem or research question you want to answer and how much you know about the problem. Research Problem/Question Methods Data

Basics of Design Quantitative Qualitative Objective Subjective Deductive Inductive Generalizable Not generalizable (transferrable) Uses Words Uses Numbers Mixed Methods Can use parts of both

Types of Design Causal Exploratory Descriptive • If the program or • Clarify the • Answers treatment is given, problem questions about then the outcome who, what, • Define terms occurs when, where • Get background Or and how. information • If the • Two basic types: program/treatment • Establish is not given, then • Cross- Sectional research priorities the outcome does • Longitudinal not occur • Answers question about why

Exploratory Design • May be quantitative or qualitative • Secondary Data Analysis • Focus Groups • Case Analyses • Surveys • Interviews

Descriptive Design • Does not include researcher imposed treatments • Examines variables in their natural environment • Time • Cross-Sectional Studies measure across one point in time • Longitudinal Studies measure across time • Correlation • Comparison across groups • Comparison within groups

Causal • Experimental • Examines cause and effect • Uses random assignment to groups • Quasi-experimental • Random assignment to groups is not used but a control group or multiple measures used Trochim & Donnelly, 2009

Threats to Validity in Quantitative Studies • Internal Validity • The extent to which it is possible to make an inference that the independent variable, rather than another factor, is truly causing variation in the dependent variable 1,p.244 • Meaning • Has to do with how the study was set up and conducted including how the participants were selected and “managed” once they were in the study

Threats to Validity in Quantitative Studies • External Validity • The extent to which it can be inferred that relationships observed in a study hold true over variations in people, conditions, and settings, as well as over variations in treatments and outcomes 1,p350 • Meaning • Has to do with our ability to say if the researchers’ findings would be useful with a similar group or people, This is called generalizability

Threats to Internal Validity What kind of study is Threat What it means most likely to be Strategies effected Temporal Ambiguity Is the independent variable really Comparative & correlational Understanding of coming before the dependent designs the variables under variable study Randomization History The occurrence of external events Longitudinal & Repeated Control group that take place concurrently with Measures studies. the IV, and that can affect the outcomes. Randomization Maturation Processes occurring within Longitudinal studies where the Control group participants during the course of participants are more likely to the study as a result of the change such as adolescents, passage of time rather than as a infants, or people who are quite ill. result of the IV. Participants get older, wiser, more depressed, more hungry, more tired.

Threats to Internal Validity What kind of study Threat What it means is most likely to be Strategies effected Testing Occurs when a pretest influences Repeated measures or a pre- Control group the way subjects respond on a test-post-test design post test. Instrumentation Changes made in the way the Physiologic instruments or Regular calibration, variable is measured, i.e, BP. those in which researchers use of multiple observers, Data collectors get better or worse are collecting the data in training of observers at what they are doing. person. establishment of reliability, validity, and objectivity of measurement procedures

Threats to Internal Validity What kind of study Threat What it means is most likely to be Strategies effected Random selection Selection Pre-existing differences Quasi-experimental studies Random assignment between the participants and convenience samples. Control group selected for a study or those who volunteer for the study & those not in the study. Mortality/Attrition Participants drop out of a Longitudinal studies. Subject matching & study or are lost to follow up omission

Threats to External Validity What kind of study is Threat What it means most likely to be Strategies effected Reactivity The influence of participating in a study on Any study with pre-test. Inform the subjects the responses of subjects. (Hawthorne of their roles, effect: Participants’ behaviors affected by Double-blind personal values or desires t please the experimental experimenter). designs Researcher may inadvertently affect how intervention conducted or how they interact with participants. Effects of Sample does not reflect the general Convenience samples Randomization Selection population

Threats to External Validity What kind of study Threat What it means is most likely to be Strategies effected Random selection Interaction of Treatment & Where the independent Convenience samples Random assignment Selection of Subjects variable might not affect Control group individuals the same way Subject matching Interaction of Treatment & When the intervention in Studies related to the same Use diverse sample Setting one setting cannot be phenomenon which used populations when generalized using the same similar types of hospitals conducting studies intervention Randomization Interaction of Treatment & When external events affect Studies in which the Control group History the intervention intervention is likely to have Replication studies changed or the targeted populations may have changed

QUESTIONS

References • Norwood, S. L. (2009). Research essentials: Foundations for evidence-based practice . Upper Saddle River, NJ: Pearson Education, Inc. • Polit, D. F., & Beck, C. T. (2012). Nursing research: Generating and assessing evidence for nursing practice. (9 th ed.). Philadelphia, PA: Lippincott, Williams, & Wilkins. • Schmidt, N. A., & Brown, J. M. (2012). Evidence-based practice for nurses: Appraisal and application of research (2 nd ed.). Sudbury, MA: Jones & Bartlett Learning • Trochim & Donnelly (2009) The research methods knowledge base . Retrieved from http://www.socialresearchmethods.net/kb/destypes.php