Biostats/Epi Week 8 (Gordis Ch. 7)

Question 1

What is our objective, both in public health and in clinical practice?

Answer 1

To modify the natural history of a disease so as to prevent or delay death or disability and to improve the health of the patient or the population.

Question 2

T or F: Randomized trials can be used for many purposes. And if so, what are the purposes?

Answer 2

True. Evaluating new drugs and other treatments of disease, including tests of new health and medical care technology. Such trials can be used to assess new programs for screening and early detection, or new ways of organizing and delivering health services.

Question 3

What is the one thing a person must do before starting a study?

Answer 3

The criteria for determining who will or will not be included in the study must be spelled out with great precision, AND IN WRITING.

Question 4

What is a case study or case series?

Answer 4

A study where no comparison is made with an untreated group or with a group that is receiving some other treatment.

Question 5

What is a historical control?

Answer 5

Using a comparison group from the past to determine the effectiveness of a therapy of today. This type of design seems inherently simple and attractice. One issue that arises from this type of study is the difference in the quality of date. The data from the study groups must be comparable in kind and quality.

Question 6

What are simultaneous nonrandomized controls?

Answer 6

Simultaneous controls that are not selected in a randomized manner.

Question 7

What is the goal of randomization?

Answer 7

To eliminate the possibility that the investigator will know what the assignment of the next patient will be, because such knowledge introdufces the possibility of selection bias.

Question 8

T or F: Randomization is the best approach in the design of a trial. Randomization means, in effect, tossing a coin to decide the assignment of a patient to a study group.

Answer 8

True. The critical element of randomization is the unpredictability of the next assignment.

Question 9

What do we hope to accomplish by randomization?

Answer 9

If we randomize properly, we achieve nonpredictability of the next assignment; we do not have to worry that any subjective biases of the investigatiors, either over or cover, may be introduced into the process of selecting patients for one treatment group or the other.

Question 10

Randomization _______ the likelihood that the groups will be comparable not only in terms of variables that we recognize and can measure, but also in terms of variables that we may not recognize and may not be able to measure but that nevertheless may affect prognosis.

Answer 10

Increases

Question 11

What is stratified randomization?

Answer 11

We first stratify (stratum=layer) our study population by each variable that we consider important, and then randomize participants to treatment groups within each stratum.

Question 12

What are some measurable outcomes of a study?

Answer 12

1. Improvement (The desired effect) 2. Side effects

Question 13

What is masking (blinding) of a subject?

Answer 13

Use of a placebo, an inert substance that looks, tastes, and smells like the active agents so that subjects will not know what group they are in.

Question 14

Why is a placebo important when testing a new therapy?

Answer 14

If the patient knows that he or she is receiving a new therapy enthusiasm and certain psychological factors may operate to elicit an improved response. It plays a major role in identifying botht he real benefits of an agent and its side effects.

Question 15

What is it called when we blind the subjects as well as the observers or data collectors in regard to which group a patient is in?

Answer 15

“Double Blinding.”

Question 16

What is a planned crossover?

Answer 16

In a planned crossover, subjects are randomized to new treatment or current treatment. After being observed fora period of time on one therapy, they are switched to the other therapy. A planned crossover allows each patient to serve as his or her own control, holding constant the variation between individuals in many characteristics that could potentially affect a comparison of the effectiveness of two agents.

Question 17

What is a carryover?

Answer 17

In a crossover, when a patient from one therapy switches to the other therapy but the side effects of the first therapy remain. There must be enough of a washout period.

Question 18

What is an unplanned crossover?

Answer 18

After randomization, subjects might have second thoughts or worsen conditions to one therapy selection so they are placed in another.

Question 19

What is a factorial design?

Answer 19

Assuming that two drugs are to be tested, the anticipated outcomes for the two drugs are different, and their modes of action are independent, one can economically use the same study population for both drugs.

Question 20

What is it when patients do not comply with an assigned treatment?

Answer 20

Noncompliance, which can be overt or covert.

Question 21

When people may overtly articulate their refusal to comply or may stop participating in the studying, they are called _______?

Answer 21

Drop outs

Question 22

What is a drop-in?

Answer 22

When a patient in one group may inadvertently take the agent assigned to the other group.

Question 23

What is considered the “gold standard” of study designs?

Answer 23

Randomized clinical trials. They are vitually at the top of the list when study designs are ranked in order of descending quality.

Question 24

A type of sampling method whereby subjects are assigned according to a factor that would influence the outcomes of the study is called:

Answer 24

Stratified randomization

Question 25

In program evaluation, the researcher may want to look at 2 or more related variables associated with an educational activity, such as time and setting. The best method to look at the interaction is a/an:

Answer 25

Factoral design

Question 26

Power is…

Answer 26

Gordis Chapter 8, p. 150. Power is the ability of determining the ability to determine that treatments differ as shown in Table 8-2.

Question 27

True or False: Using a placebo blinds subjects and observers.

Answer 27

FALSE

. Gordis, Chapter 7, p. 139. Blinding subjects with placebos is not always effective as subjects report “knowing” what they were taking. Double blinding includes both subjects and their observers, and is more effective but not without pitfalls.

Question 28

An accused citizen found innocent when really guilty is an example of…

Answer 28

Type II Error

Gordis, p. 149 While a miscarriage of justice is a Type I error for falsely identifying culpability, an error of impunity would be a Type II error of failing to find a culpable person guilty.

Question 29

A pilot study was designed to study the impact of nurse practitioner practice on recently released rural congestive heart failure (CHF) patients. Four clinics were chosen - 3 physician run clinics and 1 APN run clinic, each in differing counties. The researcher looked at morbidity rates at 1 month, and 3 months of 120 patients (30 patients for each clinic). She found that the 3 physician run CHF clinics had 3 deaths each within 1 month and a total of 15 deaths within 3 months. The APN CHF clinic had 0 deaths at 1 month and 3 deaths at 3 months. All patient’s CHF acuity was measured and found to be higher at the APN CHF clinics. Further review of the records revealed the APN CHF clinic met all CHF guidelines for education and follow up. While promising, this study reflects…

Answer 29

Internal validity only.

Gordis, Chapter 8, p. 152-3. Determination of sample size was not met for generalizability in this example. In this case, internal validity has been met.

Question 30

With any scientific process, there is no such ideal as total proof or total rejection, and provider must, by necessity, work upon probabilities. That means that, whatever level of proof was reached, there is still the possibility that the results may be wrong. For instance, the patient who tests positive for HIV, but does not have the disease has resulted in a…

Answer 30

a Type I error, noted in the 2x2 table.

Question 31

A phase III trial was conducted where some participants were assigned at random to receive drug A, and later, drug B. Another group received B, then later drug A. This design is known as…

Answer 31

Crossover design

Question 32

A clinician observed a relationship between patients who received a printed copy of their active medications during a clinic visit and compliance to taking their prescribed meds. Can the clinician determine that the education increased compliance based upon this observation?

Answer 32

No. Other explanations were not considered.

Gordis, p. 148 (#2). When providing an intervention, e.g., receipt of printed materials, to conclude that the receipt of the materials leads to a result of compliance is to determine there is a difference when in reality there is no difference in efficacy between receipt of the materials or not. Therefore, to conclude there is a difference, based on this sample, is in error.

Question 33

True or False: It is unethical to discontinue a study when the intervention has been shown to work.

Answer 33

FALSE.

Gordis, Chapter 8, p. 158. It is ethical and probably required by IRB when data reveal that the intervention works. There is no reason to hold back on the information until the study is completed as others may benefit from the intervention.