Topic 4: CAI Part 2 Flashcards
Evaluative Report
Type of report which provides an assessment of the strength to be attached to findings
What must combined probability add up to?
One
What is synonymous with transposing the conditional?
Prosecutors fallacy
What different types can transfer be?
Primary, secondary or teritiary
What is the second part of the transfer process?
Persistance
A likelihood ratio between 2 and 10 provides what level of support?
A weak level of support
Probability
- Probability (perhaps think likelihood) is a measurement of that event will occur
- Probability is quantified as a number between zero and one
- Zero indicates impossibility of the event a occurring
- One indicates certainty
Rule of Probability #1
The probability of any event will always be a number from 0 to 1
Rule of probability #2
When an event cannot occur, the probability will be zero
Rule of Probability #3?
When an event is certain to occur, the probability is one
Rule of probability #4
The sum of the probabilities of all the outcomes in the sample is one
Rule of Probability #5
The probability that an event will not occur is equal to 1, minus the probability that the event will occur
What are the two factors required to determine probability?
- ‘E’ the event whose probability is being considered and
- ‘I’ the information available to the assessor when the probability of ‘E’ is being considered
Axiomatic laws of probability
- All the probabilities most add up to 1 (as we’ve discussed previously )
- The accused is either guilty or innocent (in England and Wales at least)
- pG (Guilty) + pI (innocent) must equal 1
Probability can be either:
Probability can be either:
* Objective - A logical measure of chance where everyone would be expected to agree to the value of the relecant probability
* Subjective - Measuring the strength of a persons belief in a particular proposition
In probability, what does X represent?
X represents variable of interest
In probability, what does p represent?
P represents the probability of X
The probability that the accused is guilty, in light of the evidence introduced at trial. Typically this is expressed as:
The probability that the accused is guilty, in light of the evidence introduced at trial. Typically this is expressed as:
1. p (GIE) or the probability of guilt, given the evidence and
2. p (IIE) or the probability of innocence given the evidence
Lucia De Berk
- Arrested in 2001 after the death of a baby in her care at a hospital in The Hague, apparently from poisoning.
- Afterwards, investigators found what they thought was a trend of suspicious deaths among 13 patients treated by De Berk in the previous four years. Five others almost died in what investigators said were suspicious circumstances.
- In 2003, she was convicted of four murders and three attempted murders, and sentenced to life in prison.
- Part of the evidence against her was the testimony of a statistician, who said the odds were 342 million-to-one that it was a coincidence she had been on duty when all the incidents occurred
What happened in the Lucia De Berk case?
- Initially the death was thought of as natural causes.
- 30+ suspicious deaths were being investigated
- The (flawed) logic and only evidence was that the deaths occurred when she was on duty.
- A statistician calculated the 1 in 342 million that this could be a coincidence (Elffers 2002)
- Gill (2008) recalculated this to be between 1 in 1,000 and 1 in 25.
- After six years in prison she was acquitted in April 2010
Conditional probability
Assumptions based on the evidence introduced during trial
What are the two sample types?
- Recovered or questioned samples, namely a sample of unknown origin
- The control or reference
What is the purpose of a substrate control?
The purpose of a substrate control can be used to distinguish between the environment and surroundings and enable us to differentiate these against the questioned samples
How is relative frequency calculated?
The relative frequency is calculated against the items observed over a period of time in a laboratory or from all the DNA profiles in some defined population
How should the likelihood of the evidence be calculated?
An expert assessment of the likelihood (or probability) of obtaining particular findings should be formed upon data relevant to the type of evidence in question. Relevant data are two different types:
1. Extensive surveys, databases or experimentation
2. Refer to the experts personal experiences and previous casework
The two probabilites or likelihoods
- The likelihood of the evidence if the prosecutions proposition is true”
- “…and the likelihood of the evidence if the defence proposition is true”
What does the relative value of the two likelihoods provide?
A measure of the meaning and the probabitve value of the evidence. Normally this is represented as the likelihood ratio.
What is base rate fallacy?
Making a probability judgement based on conditional probabilites wihtout taking into account the effect of prior probabilites.
What are prior odds?
The chance of something happening at random