Reference no: EM13949444

Respond in one or more of the following ways:

Ask a probing question.
Share an insight from having read your colleague's posting.
Offer and support an opinion.
Validate an idea with your own experience.
Make a suggestion.
Expand on your colleague's posting.

COLLAPSE

Creswell (2009) identified surveys and experiments as two methods by which to conduct quantitative research (p. 145). He defined a survey design as one providing a "numeric description of trends, attitudes, or opinions of a population by studying a sample of that population" (p. 145) from which generalizations or assumptions are made from that population. Creswell further suggested that and experimental design can also be used to generalize to a population, but the primary intent is to "test the impact of a treatment or an intervention on an outcome, controlling for all other factors that might influence that outcome" (pp. 145-146).

Creswell identified that the survey design typically involves identifying the purpose for the survey; justifying why a survey is preferred; identifying whether the data collection will be cross-sectional or longitudinal; and specifying the form of data collection (p. 146). In his example, Dr. Smeaton (Laureate Education, Inc., 2009), first sought literature on his research interest and determined a gap in the literature. He then had to put together a survey instrument, determine an approach to administer the survey and identify the sampling method. Once the survey was developed, Dr. Smeaton sought feedback from the intended population. The survey was administered to a random sample (Laureate Education, Inc., 2009). Creswell (2009) recommended relying on an existing survey instrument to establish validity based on its ability to draw useful inferences and reliability based on consistency (p. 149). Dr. Smeaton was not able to establish validity or reliability in his study because of the gap in the literature. However, he did identify this as a limitation in his study; allured to it in his analysis; and set precedent for future studies.

An experimental design, as Creswell (2009) suggested, follows a standard form: "participants, materials, procedures, and measures" (p. 155). The researcher must determine whether the selection process for participants will be random or convenient. When the sample is random, the procedure is referred to as "true experiment," and when the sample is not random, it is "quasi-experimental" (p. 155). Creswell further identified that an experiment requires a clearly identified "independent" variable and "dependent" variable(s). An experiment, unlike a survey, involves a pre- and/or post-test of the administered procedures, but also has to account for validity and reliability of the research (p. 158). Creswell cautioned about "internal validity threats" when administering an experiment. This refers to experiences of the participants which may "threaten the researcher's ability to draw correct inferences" (p. 162). Creswell also cautioned about "external validity threats" which involve a researcher drawing "incorrect inferences from a sample data to other persons [or] settings" (p. 162). Creswell also cautioned about "statistical conclusion validity" based on a researcher's inaccurate inferences based on inadequate statistical" interpretations (p. 163-164). He also cautioned about "construct validity" that may occur if the researcher does not properly define or measure variables (p. 164).

References

Creswell, J. (2009). Research design: Qualitative, quantitative, and mixed methods approaches (Laureate Education, Inc., custom ed.). Thousand Oaks, CA: Sage Publications.

Laureate Education, Inc. (Executive Producer). (2009). Quantitative methods: An example. Baltimore, MD: Author.