Probability Distributions (8) Flashcards

1
Q

What is a probability distribution

A

A list of all the possible outcomes together with their probabilities

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

What is binomial distribution

A

A type of probability distribution

There can only be teo outcomes
And the probability an event occurs is (p+q)^n

Where n is the number of times

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

How is binomial distribution written

A

B(n,p)

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

What is needed for binomial distribution to be used

A

A fixed number of trials
Two independent trials
Only two possible outcomes (success of failure)

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

How can you see the coesfficeints for binomial distribution

A

Using pascals triangle

                                1
                            1     1 
                          1    2   1
                        1   3    3  1

(Etc - 2 numbers above are added e.g 1+2 =3)

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

How do you use a calculator to find the coefficient of binomila expansion

A

Use the nCr button

N is the number of trials
R is the number of outcomes you are looking for

5C2

This would mean 5 trials
And you are looking for 2 success (or failure)

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

What is normal distribution

A

A bell shaped graph

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

What is needed to use normal distribution

A

A symmetrical and bell shaped distribution
Continuous data
The mode median and mean are approximately equal

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

How is the mean represented in normal distribution

A

It is in the centre written with the character

µ

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

What percentage of observations lie between
µ +/- 1σ
µ +/- 2σ
µ +/- 3σ
µ +/- 4σ

A

µ +/- 1σ = 68%
µ +/- 2σ = 95%
µ +/- 3σ = 99.8%
µ +/- 4σ = 100%

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

How is normal distribution denoted (written)

A

N(µ, σ^2)

This uses the mean and the variance (σ^2)

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

If a question asks to find where ‘nearly all’ observations lie how many standard deviations should you use

A

3
(99.8%)

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

What are standardized scores

A

A score calculated (e.g on a test or race) to compare with a different set

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

How do you calculate standardised score

A

IF THEY ARE MODELLED BY A NORMAL DISTRIBUTION YOU CAN

(Score - mean) ÷ standard deviation

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

How are standardized scores used to compare

A

The higher the standardized score the better someone did (even if their initial score is higher)

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

What is quality assurance used for

A

To check samples of a product and ensure that they meet required standards

17
Q

What are control charts

A

Graphs used to show quality assurance

They can be plotted with a mean, median or range of multiple samples

The samples are plotted on the x axis

18
Q

What is a warning limit

A

A limit set so that 95% of the means of a sample fall between them

The mean is normally distributed so the warning limit is
µ +/- 2σ

19
Q

What is the action limit

A

A limit that contains 99.8% of all samples.

µ +/- 3σ

20
Q

What should a company do if a value falls between the action and warning limit

A

They should take another sample just to make sure it isnt the 5% chance

If they find multiple at these values they may have to stop production

21
Q

What should a company do if a value is outside the action limit

A

If the sample mean is outside the action limit they usually should halt the manufacturing process and restart the machinery

22
Q

Why is the target value sometimes set higher than the company actually wants

A

If their target value is higher they are more likely to reach the actual value that they eant

23
Q

How do you calculate probability of binomial distribution
E.g
B(5,3)
Chance of success = 0.30

A

1-0.30 = 0.70 = chance of failure

We need to find the coefficient so:

5C3 × (0.30)^3 × (0.70)^2

=0.1323