Devise a method for estimating and plotting bayesian

Reference no: EM1380385

The mock data file consists of 3 columns, each containing 1000 numbers:

1. a flag indicating which data row

2. the sampled x value (1 - 1000)

3. the corresponding sampled y value (1 - 1000)

The challenge is essentially to determine the linear relationship between x and y using these 1000 data pairs. It divides up into three steps, of increasing complexity.

Step 1: Use ordinary least squares to fit the linear model y = a + bx to the mock data

(a) compute LS estimators of a and b,

(b) estimate the variance of the (assumed Gaussian) noise which has been added to the mock y values

Step 2: By casting the data analysis challenge not as a least squares problem, but as a maximum likelihood problem, form an appropriate likelihood function for the mock data, which depends on the parameters (a,b).

Then, by computing the log likelihood on a rectangular grid of values of a and b (you need to think carefully about the range of a and b values you should consider, and the spacing between them), and in turn computing the value of chi-squared for each (a,b) pair on your grid, you should find the minimum value of chi-squared. You then should turn your grid of values into a rectangular array of Delta chi-squared values. Finally, using the information in the table in Section 6, you should compute and plot Bayesian credible regions for the parameters at e.g. 68.3%, 95.4%, 99.73%. (Carrying out the calculations and making a contour plot from the results is straightforward in e.g. MATLAB, although you are welcome to use any programming language you wish).

Step 3: Finally, using the Metropolis algorithm, and assuming a Gaussian likelihood function for the model parameters a and b, write an MCMC code to generate a sample from the likelihood function - thinking carefully about your choices of proposal density and prior range for a and b. Use this sample to estimate the mean values, errors and covariance of the parameters a and b from their sampled marginal distributions. Devise a method for estimating and plotting Bayesian credible regions for the paramters, using your MCMC sample.

while Steps 2 and 3 both involve more sophisticated methods and will require you to write some simple computer code (e.g. in MATLAB)

Reference no: EM1380385

Questions Cloud

Object identifier tree : Assume you worked for a United States based corporation that wanted to develop its own MIB for managing a product line. Where in the object identifier tree would it be registered?

Illustrate what is relationship among organizational theory : Given complexities also risks involved with supply chains, might it make sense for a business organization to vertically integrate also be its own supply chain.

Pacific express instigated operating as an airline : Pacific Express instigated operating as an airline in 1982. It had ways connecting western cities with Los Angeles as well as San Francisco and by the summer of 1983 was beginning to show a profit

Explain seldom performed even slightest investigation : explain seldom performed even slightest investigation of property before recommending it to managing members. Eric also purchased a couple of rental properties on his own account.

Devise a method for estimating and plotting bayesian : Devise a method for estimating and plotting Bayesian credible regions for the paramters, using your MCMC sample and compute LS estimators of a and b,

Illustrate what value-chain match-ups do you see : Does Sara Lee's portfolio exhibit good strategic fit. Illustrate what value-chain match-ups do you see. Illustrate what opportunities for skills transfer, cost sharing or brand sharing do you see.

Calculation of a binary tree : Computations of a Binary Tree Write a function in C programming language that can find and return the height of a Binary Tree.

Use correlation coefficient to identify collocations : Would there be a possibility to use the correlation coefficient to identify collocations and Compare with the Chi2 test and How could we maybe do that

How necessary identification information is best placed : In a hard copy favourable response message in which a subject line is not used, necessary identification information is best placed.

User Account

All Pages