Sampling in outcomes studies differs from that in traditional ...

[mwit1967]

Sampling in outcomes studies differs from that in traditional quantitative research in several ways. Which of the following is true?
 
  a. A heterogeneous sample is preferred.
  b. A random sample is required.
  c. A small, focused sample is artificially assembled.
  d. The sample is selected before an intervention occurs.

Question 2

A preference for type I error, as compared with type II error, in outcomes research means that
 
  a. The outcomes researcher is not particularly concerned with drawing incorrect conclusions.
  b. The outcomes researcher would rather identify a possible connection that doesn't end up being true than miss something.
  c. The outcomes researcher would rather establish definite causation than an indefinite connection.
  d. Patients usually don't recognize what quality of care really is.

[deja]

Answer to Question 1

ANS: A
The preferred methods of obtaining samples are different in outcomes studies; random sampling is not considered desirable and is seldom used. Heterogeneous, rather than homogeneous, samples are obtained. Rather than using sampling criteria that restrict subjects included in the study to decrease possible biases and that reduce the variance and increase the possibility of identifying a statistically significant difference, outcomes researchers seek large heterogeneous samples that reflect, as much as possible, all patients who would be receiving care in the real world.

Answer to Question 2

ANS: B
Donabedian (1987) identified the following problem-solving styles: (1) routine approaches to care versus flexibility, (2) parsimony versus redundancy, (3) variations in degree of tolerance of uncertainty, (4) propensity to take risks, and (5) preference for type I errors versus type II errors. In a type I error, the null hypothesis is rejected when it is true; this means that a promising glimmer that may affect outcomes is not noted.

[mwit1967]

Excellent

[tranoy]

TYSM