estimators

estimators - Simulation of Estimators Suppose you want to...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Simulation of Estimators Suppose you want to estimate the center of the normal distribution. Should you use the sample mean, or the sample median? Let’s try it and see. Let’s simulate draws from a normal distribution with mean 10 and standard deviation 2. MTB > random 500 c1-c7; SUBC> normal mu=10, sigma=2. MTB > print c1 -c7 Row C1 C2 C3 C4 C5 C6 C7 1 13.3323 12.0040 10.4347 8.7582 9.5735 12.3209 11.7769 2 10.2563 10.3434 10.7180 12.9429 10.8445 12.9942 9.2298 3 9.7769 7.5453 8.8069 11.2322 12.3766 8.9044 9.9838 Here are the commands along with some of the data. Then we try to estimate the population mean both ways. Remember, the right answer is 10. MTB > rmean c1-c7 c8 MTB > rmedian c1-c7 c9 Here is the result: By eyeballing it you can see that both measures seem to give “average guesses” of about 10, 6.8 7.8 8.8 9.8 10.8 11.8 12.8 13.8 Dotplot for means-medians means medians
Background image of page 1

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

View Full DocumentRight Arrow Icon
which is what we would expect from unbiased estimators. Also, the guesses for the median are more spread out . . . more likely to be far from the truth. We can see this in the descriptive statistics.
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 5

estimators - Simulation of Estimators Suppose you want to...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online