<< bma_g Bayesian Model Averaging bmapost_g >>

Grocer >> Bayesian Model Averaging > bma_g1

bma_g1

Bayesian model averaging

CALLING SEQUENCE

rbma_g = bma_g1(y,x,ndraw,burnin,mcmc,g,nvmax)

PARAMETERS

Input

* y = dependent variable vector

* x = explanatory variables

* ndraw = # of draws to carry out

* burnin = # of burn-in MCMC simulation

* mcmc = name of the MCMC algorithm (jump_g or mc3_g)

* g = value of g-prior (default = 1/max(nobs,k^2))

* nvmax = max number of variable allowed in each model

 

Output

* rbma_g = a results tlist with

  -rbma_g('meth') = 'bma g-prior'

  -rbma_g('nmod') = # of models visited during sampling

  -rbma_g('beta') = bhat averaged over all models

  -rbma_g('mprob') = posterior prob of each model

  -rbma_g('vprob') = posterior prob of each variable

  -rbma_g('model') = indicator variables for each model (nmod x k)

  -rbma_g('yhat') = yhat averaged over all models

  -rbma_g('resid') = residuals based on yhat averaged over models

  -rbma_g('sige') = averaged over all models

  -rbma_g('nobs') = nobs

  -rbma_g('nvar') = # of exogenous

  -rbma_g('y') = y data vector

  -rbma_g('x') = y data vector

  -rbma_g('visit') = visits to each model during sampling (nmod x 1)

  -rbma_g('time') = time taken for MCMC sampling

  -rbma_g('ndraw') = # of MCMC sampling draws

  -rbma_g('burnin')= # of burn-in MCMC simulation

  -rbma_g('gprior')= value of g-prior

DESCRIPTION

Computes bayesian model averaging under g-prior with selection of g-prior as proposed by Fernadez et alii (2001) g = 1/max(n,k^2). This function assumes that x and y are already a matrix and a vector.

EXAMPLE

load(GROCERDIR+'/data/crime.dat')
 
// take log of data
listn = ['crime';'m';'ed';'po1';'po2';'lf';'mf';'pop';'nw';'u1';'u2';'gdp';'ineq';'prob';'time'] ;
for i =1:size(listn,1)
    execstr('l'+listn(i)+' = log('+listn(i)+')')
end
[y,namey,x]=explouniv('lcrime',['lm','so','led','lpo1','lpo2','llf','lmf','lpop','lnw','lu1','lu2',...
'lgdp','lineq','lprob','ltime'])
 rbma_g = bma_g1(y,x,30000,10000,mc3_g)
// bma_g1 on y (log of crime) and x (explanatory variables), with 30000 draws, 10000 draws discarded,
// mc3 algorithm, default g-prior and maximum # of variables authorized in the models
 
 rbma_g = bma_g1(y,x,30000,10000,mc3_g,0.1,10)
// the same but with a greater g_priori (0.1 instead of 1/15) and a maximum # of variables limited to 10

AUTHOR

Emmanuel Michaux 2006

Report an issue
<< bma_g Bayesian Model Averaging bmapost_g >>