BAILEY FINAL

Amy Phillips

1. Your instructor has reviewed several strategies to conduct and report on scientific research.  Discuss the procedures in the positivistic, scientific method and the components of this research paper. List two reasons why you agree or disagree with this worldview and how you might utilize it for your future research agenda.

            In general, quantitative research methods are an outcome of positivist attitudes.  Scientists who search for the “truth” are called positivists. This view supports the idea that reality can only be proven through numerical values.  The goal of the quantitative researcher is to answer specific questions by providing statistical evidence that the data may be addressed in a certain way.  The purpose of quantitative research is theory-testing: to establish facts, show causal explanations and relationships between variables, allow prediction, and strive for generalizability.  The quantitative researcher begins the study with a theory and specific hypothesis that addresses one issue.  With quantitative methods, data is easier to measure and can be applied to a large group of subjects for the study.  In order to complete a research project, there is a logical sequence of steps.  These steps are:  identify a problem, review existing writing, formulate a hypothesis, design a procedure that will address the hypothesis, carry out the procedure, collect and interpret findings, and publish findings.  The components of this research paper include: introduction including hypothesis, review of literature, methods use to gather data, and an analysis.  For the analysis, the scale of measurement worksheet can be used.

            I agree with this positivist worldview.  It is easy to measure and provides more solid proof of your findings through the use of statistical findings.  However, in the relativistic way, scientists believe there is no one “truth.”  Instead, there are many ways to understand people and their culture.  Another reason why I like the positivist method is because it is very structured and well defined.  Researchers are trying to answer one specific question.  I will use this method in the future in order to provide statistical findings in studies with large groups.

                        2. We have stated that the researcher must remember the equation [dependent variables = independent variables]. Discuss the differences between independent and dependent variables and the influence one exerts upon the other.  How was this theorum influential in your study or project?

            The independent variable is sometimes called the experimental or treatment variable.  The boundaries are defined in advance by the researcher.  It is selected because it is seen as being causative or very important to the logical purpose of the research project.  The dependent variable determines the effectiveness of the manipulation or treatment.  It is also the item observed and measured at the beginning and end of the study.  In other words, the dependent variable is the variable being changed.  It can also be influenced by the independent variable.  This was influential because in my study, I engaged in ex post facto research.  This is where the independent variable cannot be manipulated because it is fixed or has already happened.

3. Create a list of the independent variables you identified in your study (Hint: these
are important client, institutional, environmental, or patient characteristics).  Give one example of a variable you could change or 'fix' in a departmental, governmental, or organizational policy.

            The independent variable in my research was adult leukemia.  Another independent variable was the fact that these patients could not find a bone marrow match and therefore relied on cord blood as their last resort.  Both of these variables are included under ex post facto research.  A variable that I would change is the use of a growth hormone after the transplant in order to speed up recovery.  Also, I would make sure each subject received the same after care following the transplant.  This would be considered a form of manipulation.

4. When creating a study, one must address the operational definitions for individual studies.  Give 3 examples of operational definitions you encountered in your project.  How does this process help or hinder the researcher?

            The purpose of operational definitions is to remove words that do not describe observable phenomena from the definition so that their meaning for a particular study cannot be misinterpreted.  I think this helps the researcher because it decreases the likelihood that the study will be misinterpreted. 

            My first operational definition is leukemia.  It is important for the reader to understand the severity of this disease and what happens to the body.  My second operational definition is a stem cell.  Unless the reader understands the importance of stem cells, the entire research project might not be understood.  My third operational definition is cord blood stem cells.  Since I am only focusing on cord blood stem cells, the reader must understand how this is different from the traditional bone marrow transplant.

5. Define the different scales of measurement (i.e. Ordinal, Nominal, Interval, Ratio). In each of these scales of measure, how would the researcher decide on which statistical analysis to use?  How did you decide what methodology to use (theoretically, you told me in METHODS chapter what you decided to do with all of the datum).

            Parametric data includes interval and ratio data.  Interval data are ordered in a logical sequence.  However, the intervals between the numbers are considered equal and represent actual amounts.  This would be considered continuous data.  The t tests, ANOVA, or ANCOVA tests can used with this data.  Ratio data are numbers that are also continuous with equal intervals between numbers.  Additionally, ratio data have a meaningful zero point.  The t-tests, ANOVA, and Pearson product moment correlation can be used. 

            Nonparametric data includes nominal and ordinal data.  Nominal data are the numbers applied to nonnumeric variables.  This type of data is referred to as “discrete” instead of “continuous.”  The Pearson’s Chi Square, Fisher’s exact, and Goodman and Kruskal’s can be used with this type of data.  Ordinal data are numbers that still are discrete but are ordered.  However, the intervals between the categories are not known and cannot be assumed to be equal.  The Pearson’s Chi Square, Spearman rho, and Wilcoxon rank sum and Friedman’s analysis of variance can all be used with ordinal data.  Since my study included more than one variable, an analysis of variance should be used.  It compares the mean scores of multiple groups within the study. 

6. Discuss the types of reliability. Why does a researcher in health care consider reliability an important component of their study?

            A study is considered reliable is, when it is repeated, similar findings are produced.  Whenever close agreement occurs among several measures of the same study, the reliability of the procedure, instrument, or research will be high and consumers may have confidence in that portion of the study.  There is external reliability and internal reliability.  There are three types of reliability.  These include test-retest reliability, split-half reliability, and interrater reliability.  Test-retest reliability is concerned with the reliability of scores over time.  Subjects are measured regarding some characteristic and time is allowed to pass.  The same subjects are remeasured and the scores should be similar.  Split-half reliability concerns the extent to which different parts of an instrument are measuring the same thing.  The test is divided into two parts and subjects’ scores on the two groups are compared.  The two scores should be similar in order for the test to be considered reliable.  Interrater reliability is the extent to which different raters or observers perceive the same person or characteristic similarly.  Once again, the scores should be similar in order to be considered reliable. 
 

7. Define validity. Examine internal and external validities and list attributes or problems associated with validity issues (think from the perspective of a potential patient or an informed peer reviewer of your study).

            Validity is concerned with the accuracy of scientific findings.  A study is valid only if investigators are truly addressing the constructs they set out to study and measure.  Internal validity deals with whether the investigator is actually observing and measuring what they think they are observing and measuring.  The effects of history, maturation, testing, instrumentation, subject selection, and subject mortality can all have an impact on the internal validity of a study.  External validity deals with to what extent are the ideas generated or tested by the investigators applicable to other groups.  This is much tougher and the reader is left to decide if the studies are valid or relevant to “real-life” situations.  If researchers want their studies to be useful in clinical situations, they must often compromise on the control subjects incorporated in the study design.  Some of the most common threats to external validity are the Hawthorne effect, replication, generalizability, multi-treatments, and researcher effect.

8. Discuss the characteristics of a quantitative research design. Name and discuss at least two designs from this worldview or viewpoint.  Why would you decide to use this worldview or research methodology (instead of qualitative)?

            The purpose of quantitative research is theory testing: to establish facts, show causal explanations and relationships between variables, allow prediction, and strive for generalizability.  Quantitative research designs are predetermined and structures, and do not change during the course of the study.  They are formal and specific according to a defined model and are used as a detailed plan of operation.   The data gathered in quantitative research designs are quantifiable and statistical, using counts and measure.  Variables are defined ahead of time and data is managed according to the procedures outlined in the research proposal.  The subject samples tend to be large and require random selection to yield defined subjects who will be typical of those in the population.  The researcher has circumscribed contact with the subject on a short-term basis.  Methods used include experiments and quasi-experiments, structured surveys, structured interviewing, structured observation, data sets, manipulation, control, and statistical analysis of data.  You might choose this methodology because there are several problems that can arise with the qualitative view.  These problems include the nonstandardization of procedures, the difficulty of managing large amounts of data and data reduction methods, and the difficulty of using naturalistic methods to study a large population.  One design of quantitative design is true experimental designs.  In this design, all three concepts- manipulation, control, and randomization, are required.  There must be an element of control, independent variables must be manipulated, and subjects are randomly selected or randomly assigned to groups.  The result is a class experimental design known as cause-and effect research.  A quasi-experiment design differs from true experimental design in that although is contains an independent variable that is manipulated in order to look for an effect on a dependent variable, either control or manipulation is missing.  The resulting design is still useful.  However, the researcher cannot generalize the outcome if there is no random selection. 

9. Discuss the characteristics of a qualitative research design. Name and discuss at least two designs from this worldview or viewpoint. Why would you decide to use this worldview or research methodology (instead of quantitative)?

            The purpose of qualitative research is to develop concepts that will sensitize readers to cultures, describe multiple realities and interpretations, develop grounded theory, and develop an understanding of the perspectives of the actors and of that particular setting.  Qualitative research designs are general in nature, evolving throughout the study and remaining flexible to allow for change.  They are used as a “hunch” as to how to proceed.  The data gathered in qualitative designs are descriptive and deal with qualities.  They may consist of field notes, artifacts, people’s own words, personal documents, or official documents.  Qualitative data are extensive and difficult to manage.  The study group is small and may be non-representative of the larger group.  Sometimes researchers stratify their participant selection in order to sample people with different roles or statuses in the community.  The investigator usually has intense contact with participants over an extended period of time.  Methods used include observation, participant observation, reviewing documents and artifacts, open-ended interviewing, coding, searches for patterns, pattern matching, and narrative and displays for portrayal of data. You might use this worldview over quantitative because there are several problems that can arise with quantitative.  These include the researchers having trouble controlling the variables, the study’s validity may be called into question, obtusiveness of the investigator and data collection methods, and the readers may be tempted to reify the topic variables.   One design is the ethnographic research design.  Ethnography deals with describing culture or aspects of culture.  The goal is to share the meanings that the participants take for granted and then to depict their new recontexualized understanding for outsiders.  Its writing is described as thick description.  Another design is the historical research design.  This design focus’ on a particular organization’s development.  The task would be to trace how and for what reason the organization came into being, what events and changes have happened, and what it would be like if it closed. 

10. Your instructor has stated that ??the best positivistic (quantitative) studies often arise from a relativist study or (qualitative) framework of inquiry.? Discuss advantages and disadvantages of qualitative and quantitative research designs.  If you had it to do over, would you change the methodology you used in your study?

            An advantage of qualitative designs is that the groups are small with issues that are typically judged from an insider’s point of view.  Also, one of the strengths of qualitative research is that the focus on naturally occurring, or ordinary events in natural settings gives us a good handle on what “real life” is like for the participants in the study.  Qualitative data places an emphasis on people’s lived experience and are thus well suited for identifying and locating the meanings people place on events, processes, and structures of their lives.  However, there are some disadvantages of the qualitative study.  These problems include the nonstandardization of procedures, the difficulty of managing large amounts of data and data reduction methods, and the difficulty of using naturalistic methods to study a large population.  Quantitative designs are more practical when it comes to human subject research.  Those who feel great satisfaction from tangible, countable data would like quantitative designs.  There is an obvious end point to the data analysis and they like the certainty of knowing when they are done. There are also some disadvantages of quantitative study.  These include the researchers having trouble controlling the variables, the study’s validity may be called into question, obtusiveness of the investigator and data collection methods, and the readers may be tempted to reify the topic variables.  I would not change the methodology in my study.  I simply would not have time to try a qualitative design.  Also, I feel the quantitative design fit my topic better (I like showing proof through numbers).