Stats 1 Flashcards

1
Q

name the three steps in hypothesis testing

A

1) define a null hypothesis
2) compare observed and expected
3) work out probability observed expected difference happened by chance

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

p

A

significant - reject null hypothesis. unlikely to have happened by chance

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

If an odds value is 1 then do you accept/reject the null hypothesis?

A

accept

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

How do you determine Chi2 - three steps

A

a - work out expected ((row total observed x column total observed )/ overall)
b – sum of ((expected- observed)2 / expected)
c – look up P value against table

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

What degree of freedom is

a) Chi2
b) t test

A

1) 1

2) 2

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

What is important about numbers for the expected count in a Chi2

A

must be over 5 for it to work

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

What hypothesis test would you do for normally distributed continuous data

A

t tests

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

Which test for categorical data?

A

Chi2

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

Which test doesn’t work with unpaired data?

A

Chi2

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

What do you calculate in an independent t test and how

A

T value. Use differences between mean. diff/Standard error = T value. Then look up p value sing table

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

What are you looking for with 95% confidence intervals of t test mean values

A

Do they cross 0? if 0 then no differences between the means so no statistical significance

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

What would you do if your continuous data is not normally distributed?

A

try log or use none parametric test like mann-whitley

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

When do you use odds ratio

A

Categorical outcomes

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

when do you use mean difference

A

continous outcomes

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