Statistics Flashcards

1
Q

what are the two categories of variables

A

numerical (qualitative)

categorical (quantitative)

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

what are the two categories of categorical data

A

nominal (e.g eye colour, gender)

ordinal (e.g police ranking, exam scores)

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

what are the two categories of numerical data

A

discrete (whole numbers)

continuous (decimal points)

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

what is mean

A

a measure of location
average
(sensitive to outliers)

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

what is median

A

a measure of location
middle value of an ordered list
(not sensitive to outliers)

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

what is range

A

a measure of spread

maximum value - minimum value

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

what is standard deviation

A

a measure of spread
measure of the amount of variation from the mean (average)
larger the standard deviation suggests the larger the spread from the average

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

what is an interquartile range

A

a measure of spread
measure of dispersion in skew data
(refers to the middle 50% of the data)

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

what does normality test P>0.05 indicate

what tests should you do for data with this kind of P value

A

there is evidence to suggest that the data is normally distrubuted

mean
standard deviation

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

what does normality test P<0.05 indicate

what test should you do

A

that there is evidence to suggest that the data is not normally distrubuted

median
interquartile range

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

if doing a numerical hypothesis test and the data is paired and normally distrubuted what hypothesis test should you do

A

paired t test

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

if doing a numerical hypothesis test and the data is paired and NOT normally distrubuted, what hypothesis test should you do?

A

wilcoxin test

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

if doing a numerical hypothesis test and the data is independent and normally distrubuted, what hypothesis test should you do

A

2 sample t test

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

if doing a numerical hypothesis test and the data is independent and NOT normally distrubuted , what test should you do?

A

mann whitney test

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

if the data is categorical what hypothesis test should you do

A

a chi- squared test

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

if the value of the hypothesis test is P<0.05 what does this mean

(or the confidence interval doesnt have 0 in it)

A

that there IS EVIDENCE OF A DIFFERENCE

17
Q

if the value of the hypothesis test is P>0.05, what does this mean?

(or the confidence interval does have 0 in it)

A

that there is NOT evidence of a difference

18
Q

what statement should you say about the confidence interval for the difference

A

95% confidence for the difference, this means that if we repeat the test again with different people we may not get the exact same difference of (mean difference value) but we can be 95% sure that the difference will be between (confidence interval values)

19
Q

what statement would you say about the confidence interval for the average

A

We can be 95% certain that the true population mean for ___ lies between ___ and ___.