L4 Dealing with uncertanity

Question 1

what was it believed about probability until the 17th century?

Answer 1

to be Fortuna / fate

Question 2

until the 17th century, it probability was seen as something which could not be…

Answer 2

analysed systematically nor scientifically

Question 3

however in the 21st century what do we now know we can do when it comes to probability?

Answer 3

make surprisingly precise predictions about how ‘chance’ will turn out

Question 4

what does the ability to make precise predictions lead betting companies to do?

Answer 4

hire statisticians

Question 5

imprecisions are often referred to as =

Answer 5

uncertainty

Question 6

thing can go wrong in the …….. sometimes

Answer 6

…media…

Question 7

what does things going wrong in the media lead to with numbers?

Answer 7

uncertainty

Question 8

why can we predict coin tosses?

Answer 8

the law of large numbers

Question 9

individual events when it comes to probability such as a coin toss =

Answer 9

unpredictable

Question 10

however if we repeat a coin toss several times…what will we get?

Answer 10

we will get the average
(i.e. 50% heads / 50% tails)

Question 11

eventually, a large number of events becomes…

Answer 11

predictable

Question 12

when does a large number of events become predictable?

Answer 12

around the 100 times range

Question 13

for a random coin toss n =

Answer 13

6

Question 14

for a random coin toss p =

Answer 14

0.5

Question 15

the more coin tosses done means that the distribution is what?

Answer 15

smoother

Question 16

when the distribution is smoother for coin tosses it means that there is what?

Answer 16

a more equal split of heads and tails

Question 17

how can we visualise this coin toss?

Answer 17

a histogram

Question 18

CLT =

Answer 18

Central Limit Theorem

Question 19

what is the law of large numbers basically?

Answer 19

if we repeat an experiment many times, we can work out the average from the repetitions

Question 20

what does the Central Limit Theorem (CLT) say?

Answer 20

that the sampling distribution of the mean will always follow a normal distribution - if the sample size is big enough

Question 21

what do histograms look similar to?

Answer 21

bar charts

Question 22

what does a histogram do?

Answer 22

summaries the distribution of data over a time period

Question 23

how does a histogram capture the information?

Answer 23

it uses bins to capture the numbers of things that fall within each range of values

Question 24

bar chart is interested in -

Answer 24

the height of the bars

Question 25

histogram is interested in -

Answer 25

the area of bins

Question 26

binomial distributions =

Answer 26

the discrete probability distribution

Question 27

what does enough tosses =

Answer 27

normal distribution

Question 28

what does a normal distribution spread allow for?

Answer 28

features to be predicted

Question 29

………….. is at the core of statistics

Answer 29

probability

Question 30

what does probability also concern (+ an example)

Answer 30

our future (i.e. if its going to rain)

Question 31

measuring something is like doing what?

Answer 31

taking an educated guess
- it would be exactly right but will be an informed decision

Question 32

MoSE =

Answer 32

margin of sampling error

Question 33

logic =

Answer 33

single measurement from a sample reflects one set of possible outcomes

Question 34

a different sample would have what?

Answer 34

different results

Question 35

what will repetition when it comes to different samples do?

Answer 35

show us where the true value is

Question 36

statistics set out to measure the …….. - but there are …………..

Answer 36

world
imperfections

Question 37

random error =

Answer 37

the difference between the true value and the observed value

Question 38

do all samples come with random errors?

Answer 38

yes

Question 39

random errors is a ………… ……. of sampling process

Answer 39

normal part

Question 40

the coin tossing example can be what?

Answer 40

modelled

Question 41

MoE =

Answer 41

margin of error

Question 42

what is typically polls sample size?

Answer 42

N=1000

Question 43

we account for random error by…

Answer 43

reporting results with a ‘margin of error’

Question 44

enough measurements or sample draws will -

Answer 44

resemble a normal distribution

Question 45

however, there are many sources of error that are not random such as -

Answer 45

• sampling error
• coverage error
• non response bias

Question 46

diminishing returns =

Answer 46

the trade off between cost and uncertainty or the size of the MoE

Question 47

at large numbers, random variables follow what?

Answer 47

very predictable patterns

Question 48

the reason for measuring things if everything is uncertain

Answer 48

imagine next time going to get a blood test doctor takes all of it out…

Question 49

what is this blood test / soup analogy an example of?

Answer 49

sample representativness

Question 50

subsampling =

Answer 50

dividing the data into smaller groups

Question 51

when it comes to subsampling, we must be…

Answer 51

extra careful

Question 52

what does subsampling drastically change?

Answer 52

the MoSE
- margins of error = larger

Question 53

what can patterns be used to make?

Answer 53

predictions + calculations