Newsom 1

USP 656 Multilevel Regression

Winter 2006
jhlhjfjhxfgdfgdfgdfgdfgfdk i!e!" 0 mg" 5 mg" #nd $0 mg%! &owever" if the rese#r'her w#nts to m#ke
inferen'es (e)ond the *#rti'ul#r v#lues of the 'ghdfdgfgdfgsfgsdfgsdfgdffffffffffkkkkkdfghdgh(le used
in the stud)" # r#ndom effe'ts model is used! + 'ommon ex#m*le would (e the use of *u(li' #rt
works re*resenting low" moder#te" #nd 'v('('('v('v(
Fixed and Random Coefficients in Multilevel Regression
,he r#ndom vs! fixed dhgdfgdfgdfgdfgdfgdfgdfk#nd effe'ts is im*ort#nt in multilevel regression! -n
multilevel regression models" (oth level.$ 'v'v('v(v'( to v#r) r#ndoml) #'ross grou*s! /e'#use of
the #ssum*tions #(out their error distri(utions" we '#ll their v#ri#n'es" oo=var(U0j) #nd 11=var(U1j),
0r#ndom 'oeffi'ients!1
,his me#ns th#t we '#n think #(out 0j #nd 1j #s #kin to the r#ndom variables - des'ri(ed
#(ove! -nste#d of #ttem*ting to gener#li2e (e)ond the *#rti'ul#r v#lues of the inde*endent v#ri#(le"
we #re #ttem*ting to gener#li2e (e)ond the *#rti'ul#r grou*s in the stud)! 3or inst#n'e" we m#) h#ve
50 'om*#nies" (ut we wish to gener#li2e to # l#rger universe of 'om*#nies when we ex#mine the
me#ns inter'e*ts% or the x.) rel#tionshi* slo*es%!
-n &4M" v#ri#n'es for the inter'e*ts #nd slo*es #re estim#ted () def#ult! ,h#t is" when )ou
first 'onstru't # model" U0j #nd U1j #re estim#ted () def#ult! &owever" the rese#r'her h#s the 'hoi'e
of setting U0j #nd U1j to (e 2ero! /) setting them to 2ero" we #re testing # model in whi'h we #ssume
0j #nd 1j do not v#r) r#ndoml) #'ross grou*s! -n f#'t" their v#ri#n'e is #ssumed to (e 2ero" so the)
#re #ssumed to (e 'onst#nt or 0nonv#r)ing1 #'ross grou*s! 3or ex#m*le" fixed" nonv#r)ing inter'e*ts
would im*l) the grou* #ver#ge for the de*endent v#ri#(le is #ssumed to (e e5u#l in e#'h grou*!
+lthough we t)*i'#ll) refer to this 'onstr#int #s 0fixing the inter'e*ts1 or 0fixing the slo*es"1 the term is
somewh#t loosel) #**lied" (e'#use we #re re#ll) #ssuming the) #re fixed and nonvarying!
Intercept Model and Random Effects ANOVA
-n the sim*lest &4M model" there #re no *redi'tors! We h#ve one level.$ e5u#tion #nd one level.2
e5u#tion6
0 ij j ij
Y R = +
where Y is the de*endent v#ri#(le" 0j is the inter'e*t" #nd Rij is the residu#l or error! 0j '#n (e
thought of #s the me#n of e#'h grou*! ,he level.2 e5u#tion #lso h#s no *redi'tors in it7s sim*lest
form6
0 00 0 j j
U = +
where
0j
is the de*endent v#ri#(le"
00
is the level.2 inter'e*t" #nd U
0j
is the level.2 error! -n this
e5u#tion" 00 re*resents the gr#nd me#n or the me#n of the inter'e*ts! U0j re*resents the devi#tion of
e#'h me#n from the gr#nd me#n! When the #ver#ge devi#tion is l#rge" there #re l#rge grou*
differen'es!
-t '#n (e shown th#t this is re#ll) the +N89+ model! +N89+ ex#mines the devi#tions of grou* me#ns
from the gr#nd me#n! /e'#use we #ssume th#t the grou* me#ns" re*resented () 0j #nd" thus" their
devi#tions #re r#ndoml) v#r)ing" this model is e5uiv#lent to the random effects +N89+ model! We
'#n rewrite our two &4M e5u#tions #s # single e5u#tion" if we *lug in the level.2 terms into level.$
e5u#tion!
00 0 ij j ij
Y U R = + +
-n this e5u#tion" 00 re*resents the gr#nd me#n" the U0j term re*resents the devi#tions from the me#n
or me#n differen'es or tre#tment effe't" if )ou would like%" #nd Rij re*resents the within.grou* error or
v#ri#tion! -n more m#them#ti'#ll) oriented +N89+ text(ooks" )ou will see #n +N89+ model written
something like6
Newsom 2
USP 656 Multilevel Regression
Winter 2006
ij j ij
Y e = + +
-f the model is #n r#ndom effe'ts +N89+" j is #ssumed to h#ve # r#ndom distri(ution! -n multilevel
regression" (e'#use we #ssume U0j to v#r) r#ndoml)" the sim*le &4M model with no level.$ or level.2
*redi'tors is e5uiv#lent to the r#ndom effe'ts +N89+ model!
When we #dd *redi'tors to the level.$ e5u#tion" the) #re 'ov#ri#tes #nd the model (e'omes #
r#ndom effe'ts +N:89+ in whi'h the me#ns #re #djusted for the 'ov#ri#te!
Newsom 3
USP 656 Multilevel Regression
Winter 2006
Summary a!le
Random vs"
Fixed
#efinition Example $se in Multilevel
Regression
Varia!les Random variable6 $% is #ssumed to (e me#sured with
me#surement error! ,he s'ores #re # fun'tion of # true
s'ore #nd r#ndom error; 2% the v#lues 'ome from #nd
#re intended to gener#li2e to # mu'h l#rger *o*ul#tion
of *ossi(le v#lues with # 'ert#in *ro(#(ilit) distri(ution
e!g!" norm#l distri(ution%; <% the num(er of v#lues in
the stud) is sm#ll rel#tive to the v#lues of the v#ri#(le #s
it #**e#rs in the *o*ul#tion it is dr#wn from! Fixed
variable6 $% #ssumed to (e me#sured without
me#surement error; 2% desired gener#li2#tion to
*o*ul#tion or other studies is to the s#me v#lues; <%
the v#ri#(le used in the stud) 'ont#ins #ll or most of the
v#ri#(le7s v#lues in the *o*ul#tion!
-t is im*ort#nt to distinguish (etween # v#ri#(le th#t is
varying #nd # v#ri#(le th#t is random! + fixed v#ri#(le
'#n h#ve different v#lues" it is not ne'ess#ril) inv#ri#nt
e5u#l% #'ross grou*s!
Random variable:
*hotogr#*hs
re*resenting individu#ls
with differing levels of
#ttr#'tiveness
m#ni*ul#ted in #n
ex*eriment" 'ensus
tr#'ks
Fixed variable:
gender" r#'e" or
intervention vs! 'ontrol
grou*!
Predi'tor
v#ri#(les in M4R
gener#ll)
#ssumed to (e
fixed
Effects Random effect6 $% different st#tisti'#l model of
regression or +N89+ model whi'h #ssumes th#t #n
inde*endent v#ri#(le is r#ndom; 2% gener#ll) used if
the levels of the inde*endent v#ri#(le #re thought to (e
# sm#ll su(set of the *ossi(le v#lues whi'h one wishes
to gener#li2e to; <% will *ro(#(l) *rodu'e l#rger
st#nd#rd errors less *owerful%! Fixed effect6 $%
st#tisti'#l model t)*i'#ll) used in regression #nd +N89+
#ssuming inde*endent v#ri#(le is fixed; 2%
gener#li2#tion of the results #**l) to simil#r v#lues of
inde*endent v#ri#(le in the *o*ul#tion or in other
studies; <% will *ro(#(l) *rodu'e sm#ller st#nd#rd
errors more *owerful%!
Random effect6
r#ndom effe'ts +N89+"
r#ndom effe'ts
regression
Fixed effect6 fixed
effe'ts +N89+" fixed
effe'ts regression
-nter'e*t onl)
models in M4R
#re e5uiv#lent to
r#ndom effe'ts
+N89+ or
+N:89+!
Coefficients Random coefficient: term #**lies onl) to M4R
#n#l)ses in whi'h inter'e*ts" slo*es" #nd v#ri#n'es '#n
(e #ssumed to (e r#ndom! M4R #n#l)ses most
t)*i'#ll) #ssume r#ndom 'oeffi'ients! 8ne '#n
'on'e*tu#li2e the 'oeffi'ients o(t#ined from the level.$
regressions #s # t)*e of r#ndom v#ri#(le whi'h 'omes
from #nd gener#li2es to # distri(ution of *ossi(le v#lues!
=rou*s #re 'on'eived of #s # su(set of the *ossi(le
grou*s!
Fixed coefficient: # 'oeffi'ient '#n (e fixed to (e non.
v#r)ing inv#ri#nt% #'ross grou*s () setting its (etween
grou* v#ri#n'e to 2ero!
R#ndom 'oeffi'ients must (e v#ri#(le #'ross grou*s!
:on'e*tu#ll)" fixed 'oeffi'ients m#) (e inv#ri#nt or
v#r)ing #'ross grou*s!
Random coefficient6
the level.2 *redi'tor"
#ver#ge in'ome" is
used to *redi't s'hool
*erform#n'e in e#'h
s'hool! -nter'e*t
v#lues for s'hool
*erform#n'e #re
#ssumed to (e #
s#m*le of the inter'e*ts
from # l#rger *o*ul#tion
of s'hools!
Fixed coefficient6
slo*es or inter'e*ts
'onstr#ined to (e e5u#l
over different s'hools!
/oth used in
M4R! Slo*es #nd
inter'e*t v#lues
'#n (e
'onsidered to (e
fixed or r#ndom"
de*ending on
rese#r'hers
#ssum*tions #nd
how the model is
s*e'ified! ,he
v#ri#n'e of the
slo*es or
inter'e*ts #re
'onsidered
r#ndom
'oeffi'ients!