As Denzin claimed, there is an advantage to performing mixed ...

[Alainaaa8]

As Denzin claimed, there is an advantage to performing mixed methods or triangulated research.
 
  In a study of pain and fatigue control after hip replacement, what would the primary advantage be of conducting both a quantitative descriptive portion and a grounded theory portion?
  a. The results would be more difficult to understand, but more scholarly.
  b. It would force a multiple-authorship arrangement, assisting each scholar.
  c. Bias would decrease.
  d. The time required to complete the study would be approximately double that of completing one that utilized only one method.

Question 2

A researcher tests the effect of a new laparoscopic treatment for chronic shoulder dislocation.
 
  The results are statistically significant, and the researcher states in his findings that there is evidence that the treatment has promise for widespread application. A subsequent replication study fails to show statistical significance. A third study produces the same effects as the second. What is the most likely explanation here?
  a. Type I error occurred in the first study.
  b. Type II error occurred in the second and third studies.
  c. Random error produced insufficient power.
  d. Bias was introduced by replicating the study.

[AngeliqueG]

Answer to Question 1

ANS: C
Denzin (1989) believed that combining multiple theories, methods, observers, and data sources can assist researchers in overcoming the intrinsic bias that comes from single-theory, single-methods, and single-observer studies. Triangulation evolved to include using multiple data collection and analysis methods, multiple data sources, multiple analysts, and multiple theories or perspectives. The concept of triangulation is now commonly replaced with the idea of mixed methods approaches

Answer to Question 2

ANS: A
A serious concern in research is incorrectly concluding that a relationship or difference exists when it does not (type I error, rejecting a true null). If only one of three studies supported the new treatment, it is most likely that a type I error occurred in the first study. Low statistical power increases the probability of concluding that there is no significant difference between samples when actually there is a difference (Type II error, failing to reject a false null). A type II error is most likely to occur when the sample size is small ro when the power of the statistical test to determine differences is low. Random error has no effect on power. Replication of research identifies areas of bias; it does not introduce bias.