Final Exam ALHE 5500:

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.

Positivistic views are based on understanding natural laws and therefore supportive of quantitative research.  The three components of this view are manipulation, control, and randomization.  Manipulation is the process of “doing something to the subjects” (Bailey, 1991, pg. 43).  This is the part where one determines what will be done differently with the non-control group to make them different from the control group.  Control is the next element.  Control is simply the researcher’s ability to eliminate “interfering or irrelevant variables” (Bailey, 1991, pg. 44).  Lastly, randomization is the ability to set subject selection criteria, but must maintain random selection that is representative of the group.

I agree with this view because truth is truth.  My perception of something does not change truth.  If a control is manipulated and the results show one thing, yet I perceive or believe otherwise, that does not change the truth.  I may believe obesity is no caused by poor eating habits and therefore choose only to exercise when in reality, a combination of the two is best whether I believe it or not.

The positivistic viewpoint is congruent with my research thus far in that the change to the DPT, an enforced change in the level of an entry level PT, is the manipulation.  As a result of this manipulation, the control of the PTA will be affected.  Randomization can be seen as more DPTs graduate or convert from lesser degrees and work in the field with PTAs.  It will be interesting to see if there is a perceived versus real effect on the current preparation of the PTA. 

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?

Dependent variable is the variable being measured or observed.  The independent variable is the variable being tested.  The independent variable is believed to have a possible cause effect relationship to that of the dependent variable.   For my proposed study the dependent variable is preparedness of the entry-level PTA as it relates to the gap between the newly formed DPT.  The independent variable is the actual change to the entry-level PT to the doctorate level and the preparedness of the entry-level PTA.  This relationship helps me to see that one change can be the potential cause of another change. 

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 variables in my research dealt with the newly proclaimed goal of the entry-level for the physical therapist to be at the doctoral level and the preparedness of the entry-level PTA in light of this new change.  Variables that could be changed include adding a variable of the proficient PTA as identified by the APTA.  By adding this variable, it is likely to see a smaller “gap” and therefore better prepared PTA.

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?

-Doctor of Physical Therapy

-doctorate level physical therapist

-Foundation degree

These operational definitions are necessary to define to make terminology clear and to assure proper understanding not only for the reader, but even more importantly the investigator.  If one choose not to clarify operation definitions this can hinder the research itself.

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).

Nominal data are the numbers applied to nonnumerical data, for example 1=boy, 2=girl, etc.  Ordinal data are discrete numbers that are not ordered and with unknown intervals in between.  Interval data is in logical sequence and have equal intervals and the scale has no zero point.  Ratio data are numbers that are continuous with equal intervals between numbers.

The researcher has to determine the data to be collected and then see which of these catergories the collected data falls into.  I determined to use a Likert scale which in my case was based on strongly agree to strongly disagree.  These “measures” do not have a definitive equal interval between.  Therefore, it would be noparametric nominal data.

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

External reliability includes researcher status position, informant choices, social situations and conditions, analytic constructs and premises and techniques for data collection and analysis.  Research status position refers to the fact that each researcher holds various backgrounds and educational levels and are also in certain social groups with an particular status.  Informant choice is another issue when looking at external reliability.  Informant choice is “the problem of identifying the informants who provide the data” (Bailey, 1991, pg. 148).  Social situations and conditions can influence the manner in which data is collected, meaning depending on the social circumstances, an informant may provide a different data set than in another situation, for example a personal interview verses an anonymous written survey.  Analytic constructs and premises concern a researcher’s ability to document accurate reproducible aspects of research such as assumptions and terminology.  Finally, data collection technique and analysis may hinder external reliability if detailed information of these items is not well described or understood.

Internal reliability is where multiple observers would agree about observations.  In order to increase internal reliability low inference descriptions are needed to collect basic information with minimal inference.  Using multiple researchers is another method of increasing internal reliability.  It helps by providing interobserver reliability.  Using participants in the research by allowing them to review notes taken by the primary researcher to confirm or deny accuracy is another way to increase internal reliability.  Examination by peers helps as well.  If a study is occurring at multiple sites, each site can compare data for consistency.  Finally, data that is recorded via video, etc. can preserve data collected for later review or confirmation.

If a researchers study is deemed reliable, the study could be performed again and be reproduced.   This is also a form of credibility for the researcher.

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 basically the strength of the study.  There are several things that threaten internal validity.  History effect where significant events occur during testing can threaten internal validity.  Maturation of subjects overtime, testing effect where subject learn to test better, and instrument correctness and accuracy can also threaten internal validity.  Selection bias from nonrandom selection, selection maturation effect, normal mortality and attrition can affect internal validity as well.  The Hawthorne effect, where subject’s attitudes change based on being in the study, and the placebo effect where subject expectation precipitates change are effects that threaten internal validity.  Diffusion of treatment where one group exposes the control group to their treatment and the control group engages in the experimental groups’ treatment, difference in location, and implementation can threaten internal validity.  Threats to external validity are selection and setting of treatment interaction and historical treatment interaction.

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)?

Quantitative research design is based on the scientific model.  It is standardized, generalized and based on fact.  Qualitative researchers refer to quantitative research design as a “manipulation of numbers” (Cottrell & McKenzie, 2005, pg. 6).  The purpose of quantitative design is to test theories.  They are formal and specific and gather data in a quantifiable and statistical manner.  Samples sizes are usually large and are randomized.  There is a clear distinction between subjects and researcher.  Methods used in quantitative design include quasi-experiment, structured surveys, structured interviews, structures observation, data sets, manipulation, control, and statistical analysis.  At the end of data collection, analysis begins when the researcher seeks to prove or disprove a theory based on statistical evidence.

Survey research is a form of quantitative research design.  Data is collected via structured survey or interview with the goal of using the sample to represent the population.  This is a very common method in the health arena.  Ex post facto research looks at something that has already occurred and tries to identify a cause-effect relationship.

I would prefer this method due to it being based on objective data and the idea that it is meant to prove of disprove theory.  It is more of a black and white approach than qualitative research is.  It leaves little room for personal preference or bias.  It either is or it isn’t. 

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)?

Qualitative research designs purpose is to develop concepts a grounded theory.  They occur in a more natural setting and are able to change throughout the study based on “hunches”.  Data is descriptive and based on quality.  Subjects are usually in small groups and can be non-representative of the whole.  The research generally has close contact with the subjects.  Methods are based on observation, open-ended questions and narratives.  The tool for collection is the researcher which can be supplemented with recording devices.  Data is analyzed on an ongoing basis and drives the continuation of the research.  Qualitative outcomes are described in a lengthy manner with anecdotal, detailed write up.

Case studies are a form of qualitative design.  It involves looking a subject, environment, etc. in detail.  They can provide general support for a new theory but can not be generalized to an entire population or subset.  They are a good way to begin inquiry into an uncharted area.  Ethnographics is another form of qualitative research design.  It involves the researcher actually being a part of or in direct observation of an event, subject, etc.  Becoming one of the group being researched or being privledged into a group is how the researcher gathers data.

For me, case study is a big part of my profession and can be the starting point of introducing a new intervention to treat a particular ailment.  I learn a lot about PT practice review articles based on case study.  If I were in a more permanent job setting, this would be a great method for me.  I think ethnographics is a great way to gain true insight and gather data, but for me, this would be difficult to attain.

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 methoodology you used in your study?

Quantitative research is very focused on specific measurable data.  It is organized so that data collection occurs and there is then a clear point at which analysis begins.  Being more concrete, I prefer this method and see it as an advantage for there to be delineation from one phase to another.  I agree that quantitative research often stems originally from qualitative research.  In a sense, one is needed for the other to exist.  Disadvantages of this method are that if the researcher feels the outcome will be one way and the data proves quite the opposite, there is no denying the data.

Qualitative research is more loosely attained.  It develops as the research unfolds.  It can shift gears at anytime based on results.  It is focused often too few if not one subject which does not represent the whole, yet it is research that once conducted can be transferred to a bigger picture and reproduced as a quantitative study in a larger sampling.  Qualitative research is not my preferred method due to not having more structured boundaries.  I think I would prefer and do best with quantitative research design.  I do think it is great when used in the case study manner.