|
Size: 2576
Comment:
|
Size: 2586
Comment:
|
| Deletions are marked like this. | Additions are marked like this. |
| Line 28: | Line 28: |
| Baguley (2012, p.393-395) gives formulae for posterior mean and variance of a normal distribution with normal prior N($$u_text{p}$$, $$var_text{p}$$) and likelihood equal to a N($$u_text{l}$$, $$var_text{l}$$). In particular | Baguley (2012, p.393-395) gives formulae for posterior mean and variance of a normal distribution with normal prior N($$u_text{p}$$, $$var_text{p}$$) and likelihood equal to a N($$u_text{lik}$$, $$var_text{lik}$$). In particular |
| Line 30: | Line 30: |
| $$ var_text{post} = ( \frac{1}{var_text{l}} + \frac{1}{var_text{p}})^text{-1}$$ | $$ var_text{post} = ( \frac{1}{var_text{lik}} + \frac{1}{var_text{p}})^text{-1}$$ |
| Line 32: | Line 32: |
| $$ u_post = (\frac{var_text{post}}{var_{l}}) u_text{l} + (\frac{var_text{post}}{var_{p}}) u_text{p} $$ | $$ u_post = (\frac{var_text{post}}{var_{lik}}) u_text{lik} + (\frac{var_text{post}}{var_{p}}) u_text{p} $$ |
How do I calculate and interpret conditional probabilities?
Gigerenzer (2002) suggests a way to obtain conditional probabilities using frequencies in a decision tree.
Cortina and Dunlap (1997) give an example evaluating the detection rate of a test (positive/negative result) to detect schizophrenia (disorder).
To do this one fixes the following:
The base rate of schizophrenia in adults (2%)
The test will correctly identify schizophrenia (give a positive result) on 95% of people with schizophrenia
The test will correctly identify normal individuals (give a negative result) on 97% of normal people.
Despite this we can show the [attachment:bayes.doc test is unreliable].
This is a more intuitive way of illustrating the equivalent Bayesian equation:
$$\mbox{P(No disorder|+ result) = }\frac{\mbox{P(No disorder) * P(+ result | No disorder)}}{\mbox{P(No disorder) * P(+ result | No disorder) + P(Disorder) * P(- result | Disorder)}}$$
A talk with subtitles further illustrating aspects of conditional probabilities given by Ted Donnelly (Oxford), a geneticist, is available for viewing [http://blog.ted.com/2006/11/statistician_pe.php here.]
- [attachment:bayes2.doc More on Bayes theorem:Illustration of priors and likelihoods]
Using statistical distributions of likelihoods and priors to obtain posterior distributions
Baguley (2012, p.393-395) gives formulae for posterior mean and variance of a normal distribution with normal prior N($$u_text{p}$$, $$var_text{p}$$) and likelihood equal to a N($$u_text{lik}$$, $$var_text{lik}$$). In particular
$$ var_text{post} = ( \frac{1}{var_text{lik}} + \frac{1}{var_text{p}})^text{-1}$$
$$ u_post = (\frac{var_text{post}}{var_{lik}}) u_text{lik} + (\frac{var_text{post}}{var_{p}}) u_text{p} $$
Baguley also gives references for obtaining posterior distributions for binomial distributions using a beta distribution as a prior distribution.
References
Baguley T (2012) Serious Stats. A guide to advanced statistics for the behavioral sciences. Palgrave Macmillan:New York.
Cortina JM, Dunlap WP (1997) On the logic and purpose of significance testing Psychological methods 2(2) 161-172.
Gigerenzer G (2002) Reckoning with risk: learning to live with uncertainty. London: Penguin.
Krushchk JK (2011) Doing bayesian data analysis: a tutorial using R and BUGS. Academic Press:Elsevier. For further reading: genuinely accessible to beginners illustrating using prior and posterior probabilities in inference for ANOVAs and other regression models.