statistics Flashcards

1
Q

why is data analysed

A

to separate the truth from the error

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

what 2 things does error/uncertainty occur from

A
  1. Measurements - resolution error or calibration uncertainty
  2. Sampling
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

what are the two types of uncertainty

A

random and systematic

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

what is and what causes random uncertainty

A

a scatter of measurements about a best value - poor resolution, noise of equipment, fatigue

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

what is systematic uncertainty and what causes it

A

constant error (bias) caused by poor calibration or methodology mistakes

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

which type of uncertainty can be removed from data

A

systematic

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

define precision

A

a tendency to have values clustered closely together

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

define accuracy

A

a tendency to mimic ‘true value’

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

define reproducibility

A

the likelihood that your data is reproducible from a replicate experiment

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

what is precision affected by

A

the ability to refine measurements e.g. weighing to a certain number of significant figures

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

what affects accuracy

A

systematic errors

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

what affects reproducibility

A

random error

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

what is absolute uncertainty

A

actual magnitude of uncertainty - an approximate value based on precision of measurements

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

how do you calculate absolute uncertainty

A

Δx ≈ xmax - xmin / n

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

what is relative uncertainty and how do you calculate it

A

it is a fraction or percentage of the measured value - multiply by 100

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

how do you communicate an uncertainty and what is the exception

A

round to 1 s.f and round the related measurement to the same d.p - if the uncertainty starts with a 1 do 2 s.f

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

how can you remove uncertainty

A

repeat measurements to form series
remove outliers

18
Q

define an outlier

A

a value that is significantly deviated from the rest of the data - has to be the biggest or smallest value

19
Q

how can we highlight outliers

A

plot values on a scatter plot to reveal those that separate from the cluster

20
Q

what are the three types of statistical distributions

A
  1. Normal (parametric)
  2. Non-normal (non-parametric) = Binomial
  3. Poisson
21
Q

how is most continuous biological data distributed

22
Q

what data falls under binomial distribution

A

data in proportions or counts that have only two states e.g. dead or alive

23
Q

what data falls under poisson distribution

A

rare events or very large samples with data in counts

25
Q

how do you calculate frequency, and frequency density from a histogram

A

frequency = area of column
frequency density = column height

26
Q

how do you calculate frequency density

A

frequency/ width of frequency interval

27
Q

what can frequency statistics show

A

if data is sharp or broad, symmetric or skewed and, single or bimodal

28
Q

where can most data be found in normal distribution

A

in the middle - around the mean

29
Q

how much data lies within 1 standard deviation of the mean when it is normally distributed

30
Q

how much data lies within 2 SD’s of the mean when it is normally distributed

31
Q

how much data lies within 3 SD’s of the mean when it is normally distributed

32
Q

how do we test for normal distribution

A

check to see whether 2 SD’s from the mean is within possible range for variables

33
Q

define probability

A

how likely an outcome is - 0 (never) to 1 (always)

34
Q

what is the equation for probability

A

number of selected outcomes / total number of possible outcomes

35
Q

define independent events

A

one event does not influence the probability of another event

36
Q

what affects the combination of probabilities

A

whether the events are independent or not

37
Q

what is P(AnB)

A

P(A) x P(B)

38
Q

what is P(AuB)

A

P(A) + P(B)

39
Q

why is probability important

A

use it to calculate likelihoods of finding evidence to give guilt or innocence

40
Q

what is the likelihood ratio

A

how likely evidence is to support guilt or innocence
high LR = guilt
low LR = innocence

41
Q

what is the likelihood ratio equation

A

probability of evidence given guilt / probability of evidence given innocence

42
Q

what is the one exception to the likelihood ratio and why

A

DNA evidence as DNA is specific to individuals