Ⅰ. 개요
QBIC은 현재까지 선보인 내용기반 이미지 검색기법 중에서 가장 성공적인 기법으로 알려져 있다. 색상, 모양, 질감을 이용한 특징 데이터표현방법을 사용하며 색인기법은 R*트리를 이용한다. VisualSEEk과 Chabot는 색상에 의한 검색만 가능하였고, WALRUS는 변환함수로 웨이브릿 계수를 이용하여 검
Various BEER!!!
The Objective of our analysis is
-to identify groups of Beers
-to analyze results
-to make an application for
marketing
2. DataSet Information
Cass fresh
Casslight
Max
Dryfinishd
Hite
Budweiser
Heineken
Hoegaarden
Asahisuperdry
Tsingtao
Sanmiguel
Mudshake
KGB
Crusier Obgoldenlarger
Guiness
Miller
Cafri
Sapporo
Kirinichibang
Hooc
data descriptive output in the previous page, we can calculate the t-statistic.
t = ((.79-1.23))/√(2.14⁄61+1.8⁄22) = -1.294 d.f = 61+22-2=81
T-statistic from calculating and the SPSS output (-1.294, -1.270) is almost same. (Slight differences between the values we computed and the values on the table might have been caused from setting different decimal points.)
Logistic regression
A. Extension of multiple regression but the dv is categorical
B. Value being predicted represents a probability, and it varies between 0 and 1
C. Possible to use categorical ivs (dummy coded, but won’t here)
D. Key concept: logit
1. natural logarithm (ln) of the odds
2.
3. Therefore, prob success + ? + + + +
E. SPSS (example with the Helping3.sav dataset)
1.