Week 3 Flashcards

1
Q

What is ratio

A

Releationship between 2 numbers,, numerator not necessarily included in the deminontator 5:2= 2.5 sex ratio

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

What is proportion

A

Numererator necessarily included in the denominator ranges between 0 and 1 how many women in the population 2/4 50%

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

What is Odd

A

The probability of an event occuring relative to it not occurring different than proprtion its how many are divided by how many are not. If 25 people in 100 people are diabetic odd is 25/75=0.33.

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

What happens when a disease is rare?

A

Odd esitmates porpotion

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

What is rate

A

Speed of occurrence of an event over time it is porportion but need a time factor

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

What is prevalence rate

A

The proprtion of the population that has a given disease at a specified time

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

What is point prevalence rate

A

with disease at specific time divided by population at same time can times by 1000 to get per 1000 people

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

What is measures of incidence

A

The proportion of the population at risk that develops a given disease or other attribute during a specified time period

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

How do you measure incidence

A

Remove people who are not at risk you remove them from the population you can’t get cancer if you already had it

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

What is the formula for incidence rate

A

new events during specified time period divded by population at risk if 9000 residents were studied and 245 of them already had cancer and a total of 179 new cases has been digonsed what is the ir rate of cancer per 10 000 people 179 divided by 9000-245 times 10,000

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What is relative risk

A

How many times as likely it is that someone who is exposed to something will experince a particular health outcome compares to someone who is not exposed

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What is the formula for relative risk

A

the top is incidence in exposed a/ a+b divided by incidence in unexposed c divided by c+d

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What dose it mean if for relative risk you got the number 1.76

A

If you smoke the chance of you getting the disease is 76%

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What if you wanted to caculate odds ratio in a table

A

odds of disease in exposed (a/b) divided by odds of disease in unexposed c/d not a percentage

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

What is random error

A

Error due to chance

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

What is systematic error

A

Error due to recognizable source

17
Q

Can you have both random and systematic error

A

Yes

18
Q

What is precision vs accuracy is measurment

A

If you have high precision it is reliable with high accuracy is valid

19
Q

Why can insufficient precision happen

A

The measurment tool is not precise enough
Two indpendent interviewers rate the same differtly using the same scale
The same in

20
Q

What makes a valid measure

A

It measures what it is suppose to measure
Does not include unnecessary questions
Is able to do what it is designed to do predict discriminate etc

21
Q

What is Misclassification

A

Putting people into the wrong categories

22
Q

What is non-differential

A

Usually weakens associations brings estimants closer to the null valuse dilutes the estimate, data collected from one group is inacuarate while the other group is accurate

23
Q

What is differential

A

Different in different study group effect estimates may change in any direction depending on the particular error both groups are inaccurate

24
Q

What can you do to fix information bias once it occured

A

Nothing needs to be reduced during study design