statistics

Question 1

why is data analysed

Answer 1

to separate the truth from the error

Question 2

what 2 things does error/uncertainty occur from

Answer 2

1. Measurements - resolution error or calibration uncertainty
2. Sampling

Question 3

what are the two types of uncertainty

Answer 3

random and systematic

Question 4

what is and what causes random uncertainty

Answer 4

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

Question 5

what is systematic uncertainty and what causes it

Answer 5

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

Question 6

which type of uncertainty can be removed from data

Answer 6

systematic

Question 7

define precision

Answer 7

a tendency to have values clustered closely together

Question 8

define accuracy

Answer 8

a tendency to mimic ‘true value’

Question 9

define reproducibility

Answer 9

the likelihood that your data is reproducible from a replicate experiment

Question 10

what is precision affected by

Answer 10

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

Question 11

what affects accuracy

Answer 11

systematic errors

Question 12

what affects reproducibility

Answer 12

random error

Question 13

what is absolute uncertainty

Answer 13

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

Question 14

how do you calculate absolute uncertainty

Answer 14

Δx ≈ xmax - xmin / n

Question 15

what is relative uncertainty and how do you calculate it

Answer 15

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

Question 16

how do you communicate an uncertainty and what is the exception

Answer 16

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

Question 17

how can you remove uncertainty

Answer 17

repeat measurements to form series
remove outliers

Question 18

define an outlier

Answer 18

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

Question 19

how can we highlight outliers

Answer 19

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

Question 20

what are the three types of statistical distributions

Answer 20

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

Question 21

how is most continuous biological data distributed

Answer 21

normally

Question 22

what data falls under binomial distribution

Answer 22

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

Question 23

what data falls under poisson distribution

Answer 23

rare events or very large samples with data in counts

Question 25

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

Answer 25

frequency = area of column frequency density = column height

Question 26

how do you calculate frequency density

Answer 26

frequency/ width of frequency interval

Question 27

what can frequency statistics show

Answer 27

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

Question 28

where can most data be found in normal distribution

Answer 28

in the middle - around the mean

Question 29

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

Answer 29

2/3

Question 30

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

Answer 30

95%

Question 31

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

Answer 31

99%

Question 32

how do we test for normal distribution

Answer 32

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

Question 33

define probability

Answer 33

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

Question 34

what is the equation for probability

Answer 34

number of selected outcomes / total number of possible outcomes

Question 35

define independent events

Answer 35

one event does not influence the probability of another event

Question 36

what affects the combination of probabilities

Answer 36

whether the events are independent or not

Question 37

what is P(AnB)

Answer 37

P(A) x P(B)

Question 38

what is P(AuB)

Answer 38

P(A) + P(B)

Question 39

why is probability important

Answer 39

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

Question 40

what is the likelihood ratio

Answer 40

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

Question 41

what is the likelihood ratio equation

Answer 41

probability of evidence given guilt / probability of evidence given innocence

Question 42

what is the one exception to the likelihood ratio and why

Answer 42

DNA evidence as DNA is specific to individuals