final Flashcards

1
Q

between group

A

strongest methodological design

-outcomes are compared between two or more groups of people receiving different levels of the intervention

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

within-group

A

pretest, posttest

-analyze the same person after tests

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

any characteristic that can be measured or categorized

A

variable

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

what is a standard deviation?

what percent of data should fall within one standard deviation

A
  • spread of the data

- 68.2%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

positively skewed

A

right

-bulk of data is on the negative end of the scale, the longer tail trails toward the positive end of the scale

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Negatively skewed

A

left

-bulk of the data iso n the positive end of the scale, the longer tail trails towards the negative end of the scale

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

normally distributed

A

shaped like a bell, symmetric

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

type 1 error

A

we reject Ho when Ho is true

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

Type 2 error

A

accept Ho when Ho is false

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

what are p-values and what does it determine

A
  • Probability that ranges from 0 to 1 and provides a means of evaluating the role of chance
  • As sample size increases, the probability that the result is due to chance decreases
  • Ex. P value of 0.02 means there is a 0.02 probability that the result occurred by chance
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

what is a random sample

A
  • Putting a name in a hat and pulling them out
  • Not really knowing what the expected outcome is
  • Variable whose numerical value is determined by a chance mechanism
  • everyone has the same probability of being chosen
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the placebo effect? How does it interfere with research?

A
  • is defined as the effects on patient outcomes that may occur due to the expectation by a patient that a particular intervention will have an effect
  • psychological factors influence this
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

what are the phases of a clinical trial

A
  1. SAFETY. FDA approval. Safe for human consumption Unblended and uncontrolled. Less than 30 patients.
  2. 50 people. Randomized and blinded. –tolerability –safe dosage –side effects –how the body copes with the drug. Also sees what the treatment effective against
  3. may involve thousands. Randomized. Evaluate efficacy of new treatment. Different dosage and methods of administration
  4. after approval of FDA. Look for side effects and further therapeutic uses
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

placebo controlled study, subjects are blinded but investigators are aware of who is receiving the active treatment

A

single-blinding

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

the gold standard- neither the subjects nor the investigators know who is receiving the active treatment

A

double-blind

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

not only are the treatment and research approaches kept a secret from the subjects and investigators, but the analyses are completed in a manner that is removed from the investigators

A

triple-blinded

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

what statistics do we calculate fro case control studies

A

odds ratio

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

what statistics for cohort studies

A

relative risk

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

what does odds ratio show

A

odds of exposure. measures the association between exposure and disease variables

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
20
Q

what does risk ratios show

A

what is the chance you will get the disease

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
21
Q

what study design is ideas for rare conditions

A

case controls

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
22
Q

what is recall bias? when does it likely occur?

A

Disease may affect memory of the situation. Ex; babies with health problems and considered differential recall if bias exists differently between controls and cases.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
23
Q

how do we conduct group (frequency) matching?

A
  • Process of selecting the controls so that they are similar to the cases in certain. -Two types: Pair and Frequency.
  • Frequency are a proportion of controls with certain characteristics matches the proportion of cases with the same characteristic.
  • Cases have to be selected first.
  • Pair is every individual is matched with a control.
24
Q

what population can we generalize from

A

The population where we took the sample from.

25
at what stage do we want to avoid bias
easiest to avoid bias at the design stage
26
case control studies
disease to exposure
27
prospective studies
exposure to disease (start now and follow)
28
retrospective studies
find a group that existed in the past and follow to see if they got the disease
29
what is a confounding factor? what examples did we talk about in class?
- it influences the exposure and disease. - Coffee drinking was linked to heart disease (smoking was actually the confounder) - Vegetarianism was linked to better health (the confounder was health conscious)
30
for case controls studies, how many controls do we need? what is ideal?
1 case for 4 controls
31
why do we use YPLL?
* Things that kill people young * Health priorities * Death of someone young means limiting productivity
32
individual YPLL
65- age of death
33
group YPLL
age groups youngest age + oldest age +1 /2 65-midpoint multiply midpoint by how many people died
34
YPLL stands for
years of potential life lost
35
what is the odds ratio
(AD)/ (BC)
36
what is the relative risk
Ie/Io
37
how do you interpret relative risk
the risk of (disease) among (exposed) is x times higher (or lower) among (non exposure)
38
how do you interpret odds ratio
among those with (disease) the odds of having (exposure) are x times greater (or less) than those (without disease)
39
what does odds ratio measure
association between exposure and disease in case control studies
40
what does relative risk measure
risk of disease
41
what is attributable risk
Ie-Io
42
what is attributable risk proportion
Ie-Io/ ie x100
43
what is population attributable risk
It- Io
44
what is population attributable risk proportion
It-Io/ It x 100
45
what is the rate of incidence in exposed group or IE
A/ (A+B)
46
what is the rate of incidence in non exposed group or IO
C/ (C+D)
47
how do you interpret attributable risk
is the amount or proportion of disease incidence (of disease risk) that can be attributed to a specific exposure. How much of the lung cancer risk experienced by smokers can be attributed to smoking?
48
Variables go in
columns
49
participants in
rows
50
In experimental research we use
intervention or experimental group and a control.
51
In a case control study we
cases and controls.
52
what do we use to calculate sample size
formulas
53
what is frequency
are a proportion of controls with certain characteristics matches the proportion of cases with the same characteristic.
54
what is pair
every individual is matched with a control.
55
what is IT
a+c/n
56
interpret attributable risk
Among those with the exposure, how much of the disease is attributed to the exposure? _____% of the disease is attributable to exposure