{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

lab3a

# lab3a - We will estimate the parameter a 1 Maximum...

This preview shows pages 1–7. Sign up to view the full content.

Inference: MLE Sayan Mukherjee Lab assignment Three September 24, 2009 Sayan Mukherjee Inference: MLE

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Lab outline The lab will be due on the 2th of October. You will be expected to write a short: 1-2 page lab report. The 1-2 pages do not include plots or graphs that illustrate ideas. Sayan Mukherjee Inference: MLE
The data Data comes from a noisy linear relation. We have two variables x , y and we are given n values x from an even grid between [4 , 10]. Note that n (the number of observations) is something we will play with in our analysis. The way we compute y is as follows y = a × x + ε, where a = 4 and ε N (0 , 2) is i.i.d.normal. This results in data D := ( x i , y i ) n i =1 . Sayan Mukherjee Inference: MLE

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Inference

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: We will estimate the parameter a 1 Maximum liklihood estimation (MLE). Sayan Mukherjee Inference: MLE MLE Open matlab Download the fle makedat.m run the command ≫ [x,y] = makedat(20) you should see a plot oF 20 points corresponding to a line with noise play with n Sayan Mukherjee Inference: MLE MLE assignment Write code to estimate a based on MLE. Generate several data sets for a Fxed n and estimate a for each data set generated. What does the distribution of the a-values look like ? How does this distribution vary as n increases ? Sayan Mukherjee Inference: MLE Sayan Mukherjee Inference: MLE...
View Full Document

{[ snackBarMessage ]}