¥3dRegAna:
Qualitative Variables (ANCOVA)
HQualitative variables can also be used
åi.e. WeÕre modeling the response amplitude to a stimulus of
varying contrast when subjects are either young, middle-aged or old.
åX1 represents the stimulus contrast (quantitative):
covariate
åCreate indicator variables X2 and X3 to represent age:
íX2 = 1 if subject is middle-aged
å = 0 otherwise
íX3 = 1 if subject is old (i.e. at
least 1 year older than Bob)
å = 0 otherwise
åFull Model (no interactions between age and contrast)
íY = b0 + b1X1 +
b2X2,+
b3X3 +
e
E(Y) = b0 + b1X1 for
young subjects
E(Y) = ( b0 + b2 ) +
b1X1 for middle-aged
subjects
E(Y) = ( b0 + b3 ) +
b1X1 for old
subjects
åFull Model (with interactions between age and contrast)
íY = b0 + b1X1,+
b2X2 +
b3X3,+
b4X2,X1 +
b5X3X1,+
e
E(Y) = b0 + b1X1 for
young subjects
E(Y) = ( b0 + b2 ) +
( b1 + b4 )X1 for middle-aged subjects
E(Y) = ( b0 + b3 ) +
( b1 + b5 )X1 for old subjects
HWill be available and easier to run analysis in Matlab script