LECTURE 25 Outline Reference: Section 9.

4 Course Evaluations (until 12/16)

http://web.mit.edu/subjectevaluation

Simple binary hypothesis testing null hypothesis H0: X pX (x; H0)

[or fX (x; H0)]

alternative hypothesis H1: [or fX (x; H1)] X pX (x; H1) Choose a rejection region R; reject H0 i data R Likelihood ratio test: reject H0 if pX (x; H1) > pX (x; H0) or fX (x; H1) > fX (x; H0)

Review of simple binary hypothesis tests examples Testing composite hypotheses is my coin fair? is my die fair? goodness of t tests

x false rejection probability (e.g., = 0.05) choose so that P(reject H0; H0) =

Example (test on normal mean) n data points, i.i.d. H0: Xi N (0, 1) H1: Xi N (1, 1) Likelihood ratio test; rejection region: (1/ 2 )n exp{ i(Xi 1)2/2} > 2 /2} (1/ 2 )n exp{ i Xi algebra: reject H0 if:

Example (test on normal variance) n data points, i.i.d. H0: Xi N (0, 1) H1: Xi N (0, 4) Likelihood ratio test; rejection region: 2 /(2 4)} (1/2 2 )n exp{ i Xi > 2 /2} (1/ 2 )n exp{ i Xi algebra: reject H0 if Find such that

i 2 > Xi

Xi >

Find such that

Xi > ; H0 =

i=1

i=1

2 > ; H Xi 0 =

use normal tables

2 is known the distribution of i Xi (derived distribution problem)

chi-square distribution; tables are available

Composite hypotheses Got S = 472 heads in n = 1000 tosses; is the coin fair? H0 : p = 1/2 versus H1 : p = 1/2 Pick a statistic (e.g., S ) Pick shape of rejection region (e.g., |S n/2| > ) Choose signicance level (e.g., = 0.05) Pick critical value so that:

Is my die fair? Hypothesis H0: P(X = i) = pi = 1/6, i = 1, . . . , 6 Observed occurrences of i: Ni Choose form of rejection region; chi-square test: reject H0 if T = Choose so that:
(Ni npi)2
i

npi

>

P(reject H0; H0) =

Using the CLT:

P(reject H0; H0) = 0.05 P(T > ; H0) = 0.05

= 31 Need the distribution of T : (CLT + derived distribution problem) for large n, T has approximately a chi-square distribution available in tables

P(|S 500| 31; H0) 0.95;

In our example: |S 500| = 28 < H0 not rejected (at the 5% level)

Do I have the correct pdf? Partition the range into bins

What else is there? Systematic methods for coming up with shape of rejection regions Methods to estimate an unknown PDF (e.g., form a histogram and smooth it out) Ecient and recursive signal processing Methods to select between less or more complex models (e.g., identify relevant explanatory variables in regression models) Methods tailored to high-dimensional unknown parameter vectors and huge number of data points (data mining)

npi: expected incidence of bin i (from the pdf)

Ni: observed incidence of bin i Use chi-square test (as in die problem) Kolmogorov-Smirnov test: X , from data form empirical CDF, F

(http://www.itl.nist.gov/div898/handbook/)

X (x)| Dn = maxx |FX (x) F P( nDn 1.36) 0.05

etc. etc.. . .

MIT OpenCourseWare http://ocw.mit.edu

6.041 / 6.431 Probabilistic Systems Analysis and Applied Probability

Fall 2010

For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms.