Index
Module 2 • Research Methods
Research Design, Biostatistics & Literature Evaluation
50%
Data Tables
Research Design, Biostatistics & Literature Evaluation
Julie E. Farrar ~3 min read Module 2 of 20
16
/ 32

Research Design, Biostatistics, and Literature Evaluation

Practice Case

Questions 2 and 3 pertain to the following case.

You are a critical care pharmacist in the medical ICU and wish to retrospectively study the safety and efficacy

of four-factor prothrombin complex concentrate (4F-PCC) for coagulopathy correction in patients with end-stage

liver disease. You decide on a primary outcome of in-hospital mortality and secondary outcomes of INR correc-

tion, viscoelastic test correction, and thrombotic events.

2Which is likely the most appropriate trial design for this study?
A.Case-control.
B.Cohort.
C.Case series.
D.Pharmacokinetic trial.
3

Which would create the highest risk of bias in this study?

A.Selection bias โ€“ typically only patients who are bleeding receive 4F-PCC at your institution.
B.Measurement bias โ€“ multiple students and a pharmacy resident collected data for this study.
C.Misclassification bias โ€“ classification of patients as having end-stage liver disease requires manual

chart review.

D.Observation bias โ€“ there was no blinding of those who did or did not receive 4F-PCC.
V.STATISTICAL ANALYSIS
A.Statistical analyses can be categorized into one of two main classifications: Bayesian or central tendency

(frequentist)

1

Bayesian analysis allows for incorporation of prior knowledge into current study and calculates the

probability of benefit.

2Frequentist statistics data are presented using descriptive statistics such as the mean, variance, standard

deviation, median, and interquartile range.

3

Interpretation of studies may be different based on whether frequentist or Bayesian analyses are selected

(JAMA 2019;321:654-64; Am J Respir Crit Care Med 2020;201:423-9).
B.Hypothesis Testing โ€“ Determining whether an observation or outcome was caused by chance results in either

rejecting or accepting (failing to reject) a null hypothesis (H0)

1

Rejecting the null hypothesis results in accepting the alternative hypothesis (H1)

2Null and alternative hypotheses are built according to study aim and design

Superiority trial example (N Engl J Med 2023; 388:499-510).

H0 = no difference in mortality exists between a restrictive versus liberal fluid strategy for

sepsis-induced hypotension

ii.

H1 = a restrictive fluid strategy would lead to lower mortality than liberal fluid strategy for

sepsis-induced hypotension

iii.

The study found no significant difference in mortality between groups, thereby resulting in a

failure to reject the null hypothesis.

Type I error (alpha [ฮฑ] error): To reject the H0 when, in fact, it is true. Decisional threshold to reject/

not reject the H0 is conventionally set at ฮฑ = 0.05. The ฮฑ value represents the likelihood that a type

I error will be made. An ฮฑ set at 0.05 means that the H1 will erroneously be accepted 1 in 20 times.

HD Video Explanation โ€” Synchronized with PDF
Starts at: minute 15 Open on YouTube