Choosing a Research Approach RCS 6740 52404 Review

Choosing a Research Approach RCS 6740 5/24/04

Review of Quantitative Research ► Quantitative research: Collecting and reporting observations numerically. ► The researcher may use questionnaires, tests, and other measures to record frequency of behavior, occurrence of behavior and/or duration of behavior. ► After data is collected, it is analyzed statistically. ► Example: The mean GPA of students who work over 20 hours a week is. 50 points lower than students who do not.

Review of Qualitative Research ► Qualitative Research: Data is collected from observations and interviews. Can be conducted in a lab or in the field. ► The qualitative approach yields data expressed in non-numerical terms using language and images. ► The qualitative approach would include summaries of discussions, interviews, and video or audio-taping of behaviors.

Review of Qualitative Research Cont. ►A qualitative description of observations would focus on patterns and themes (Grounded Theory) that emerge from language or images. ► Example: A common theme that emerged from talking to the students was that they needed to work and would continue to do so even if their grades suffered.

Quantitative and Qualitative Designs Quantitative Research. Designs: Experimental Quasi-Experimental Ex post facto Correlational Descriptive Time Series/Single Subject Qualitative Research Designs: Ethnographic Grounded theory Case study Phenomenological Historical Philosophical

Summary Chart Quantitative Research ► Positivistic ► Hypotheses/deductive ► Particularistic ► Objective/outsider centered ► Outcome oriented ► Natural science worldview ► Attempt to control variables ► Goal: find facts & causes ► Static reality assumed; relative constancy in life ► Verification oriented ► Confirmatory Qualitative Research ► Phenomenological ► Inductive ► Holistic ► Subjective/insider centered ► Process orientated ► Anthropological worldview ► Relative lack of control ► Goal: Understand patient’s view ► Dynamic Reality assumed; “slice of life” ► Discovery orientated ► Explanatory

Choosing Quantitative, Qualitative, or Both How much is already known about the problem? What do you really want to learn about the problem? What do you want to do with data obtained from the research? ► What theories are applicable and what types of research do they suggest? ► How many participants are available? ► How much control can you exert over observation and data collection? ► How much time and money are available? ► How well do you know (or want to learn) specific methodologies? ► What do you feel comfortable with? ► ► ►

How Much is Known If not much is known about the problem of interest, then: Qualitative research might help you to better define and understand the problem, ► Descriptive research might help to describe the problem or reduce observations to underlying factors or dimensions, ► Ex post facto research might help you to establish relationships among variables that could later be tested for causality. ► ►

How Much is Known Cont. If you know enough to precisely state hypotheses and define outcome measures, then: ► Quasi-experimental research could help you to establish probable cause and effect in natural settings ► Experimental research could help you to determine cause and effect ► Single subject designs could help you see, in detail, how a treatment works over time, situations, or subjects ► Qualitative research could help you to understand the impact of proposed interventions from the perspectives of various stakeholders. In addition, qualitative research could help to explain how the interventions work. ►

What Do You Want to Learn Qualitative research will help uncover participant’s reactions to a program and underlying meanings. Answers or categories of answers are not presumed, but allowed to unfold. We gain more in-depth understanding of situations. ► Single subject research will allow you to really look at changes in the dependent variables across time. ► Descriptive studies help us to describe populations or samples. ► Ex post facto or correlational studies help us to understand the relationships among variables. For example, we might study the relationship of teacher expectations to student performance. ►

What Do You Want to Learn Cont. ► Quasi-experimental studies help us to establish probable causal relationships among variables, although we only really prove relationship. ► Experimental studies help us to prove cause and effect. For example, we may want to prove that program A gets better results than program B. Random assignment to groups is an important hallmark for experimental studies. ► When reading research, ask yourself: What did the authors really want to know about the problem? ► Before planning research, ask yourself: What do I really want to know about this problem?

What are you Going to Do with the Data ► The type of research approach you choose will depend on what you plan on doing with results of the study. ► Do you plan on evaluating a program? ► Do you plan on publishing your results? § Different journals may prefer quantitative or qualitative papers ► Do you plan write a book on the experiences of a population? ► Is this a class project or do you plan on winning the Nobel Prize?

What Theories are Applicable ► A theory is an explanation of natural phenomena (Kerlinger, 1986). It is a set of interrelated constructs (concepts), definitions, and propositions that present a systematic view of phenomena by specifying relations among variables, with the purpose of explaining and predicting phenomena (Kerlinger, 1986, p. 6). ► Once you have identified the problem and possibly the hypotheses, you are in a good position to examine the related theory. One way to do this is to examine theories that address varying combinations of your variables.

How Many Participants are Available ► If your research involves a low incidence population (e. g. , people with dual sensory impairments) or a limited occurrence, then you will need to consider: § Qualitative research to further illuminate meaning and individual perspectives § A variety of single subject designs § Experimental and quasi-experimental designs with (a) precise outcome measures and (b) preanalysis estimations of statistical power with appropriate adjustment of alpha levels. ► For Experimental designs, it is recommended that you have 25 -30 participants per/group

How Much Control do You Have ► This is an important consideration in any study. You need to be sure that the data that you collect is reliable and valid for the problem under consideration. ► Traditional experimental designs require control in random assignment of participants to groups and data collection. ► Single subject designs demand control in systematic observation and recording of observations.

What are Your Resources ► If you have limited time and money, you may not want to enter into a large scale, detailed experimental or quasi-experimental study with many participants. ► Research needs to be DO-ABLE with the amount of time and effort that you can commit. ► What resources will you need for quantitative and qualitative studies?

What Methodologies do you Know ► Without a firm grounding in your chosen methodology, it is possible to commit (unintentionally) what Rosnow and Rosenthal (1989) refer to as “sins of methodological spirit and methodological substance. ”

What do you Feel Comfortable with ► As mentioned before, the type of research you choose will be partly influenced by your own personality traits and your view of the world. ► Do you consider yourself to be Positivistic or Phenomenological? ► Are you very anal and in need of control or can you work with what you have (convenient sampling). ► Bottom Line: Choose a Research Approach that suits you!

Questions and Comments ?

Class Activity ► Please see class activity sheet