2 1 - $ /$0 1.#$ %$ &'$(!$) $( *$+,!'! $ -(!" $>-0 $? *@$ $( A8 <B<= :1; )!' '<, <<=.678 % 1980 2 ) '( -+' $?!( $ $-I $KL$ M$? ().-# -I <B<= % -G1 :6? E %( C@!' '!' DB) $?!(!' $ $, -R.'$ $ $ $ 6?' Q /0 ) 8 OP!' -O (.6? 78!" WBX! UGlass!( %B1! (Metanalysis) *BV=7 EL;".!' T>! U!' V" BS ) BS %B$B:!$- $( UGVP 6+#] ( *) Q %#@ -: *BV=.'(!) ( 1976 Z?!' @Y 2Y <B<= %+ _! *$BV=7.'$ $ '$(!$) (!Y B82 GVP! Y!' ) 6? 2^ *BV=7.*) Y 6B $ $(.'$ $+!'ab$ b$b<= 6$BDB)!$(!' ' 'D? `!!Y! 2 Y!' ) 6?! BB /B ( 2 *c We? d( K@ V ' 2c Y!' :1; R ) ' OP 2c ( ( *BV=7-3 $@ $( $Y #$< $ O$P a /B) -2 a (B2! f(-?- -1.'! G:` U'! i( a'!' U-BB!' '0 j@ *BV=7.;i a)!- ( *BV=7 (B2! *$BV=7 $) 6#$B G;1 2 1i /V; %!Y'.-) '! 7) a-b( bb<= ] T< %BB: ( -)!@Y»!$ Hall Green $D8 M$? ( '' *BV=!? - 6#B <B<= *X# K!' ( :;] k? «. Y %m0 6?!Y _! d*bv=7 d : (1385 & $43 $3 )!" ( B @m V, '!? oop )' ' 2 ( B @m V, '!? @'!'? dzp# -# ( B @m V, '!? @' VB+@ LBo= c - ) -'! B-B#c!(! - : V, )' (Bi - :M!'Y msn_sho@yahoo.com : @B@1 6# 021-22220980:(+ 021-22257698 :%DV 1 15
.4 9 5-3 4 5 67!,-./ 012 ",B% cj9 B. l$) / (ZM ma9 )F &B<I6 ) &B<I6 Glass. - &% ^!C9,B% n# $ % #: :)% @9 E F % 5*B ## &B<I $ / DB$ ;B % #/# #. d ZC $ #6 $ h<f ## = # / # 6 B7 5Uk $ @&B<I6 a )B #= = @4'% NBG,.b # = # % 59 /N &B<I6.)% = a!b)o' O# #$% $ = B7/ E<A #G9? = / Glass) = # % 59 #' # DB hbri 5BGB% $# #,B% a! # <'( 99 &.(2) (1967 o= qqp N*) - ma9 E<A RBRI.(3) (1986 Wolf) $ (F.K R &B<I) # # B79,- % B. &B<I h M / &B<I6 s C$.#/# (F.K #4 &B<I) k &B<I t $ #!G7 $ / qp a! % ))% )% : )% G7 ' @]Q- '9 )U 6 &B<I6 5*B!B) lb # O(4) (1981 Lynn Gallo) a! #B)$ &% #.59 -,<K B7$ # / # 67 F.K / &B<I ; P % 59!,B% # :G B ## &B<I6 q.(5) #/= @ # U( $ O@59 = / #G9 $ D / - &% ^ # $ :G B 6F @&B<I6 q # # 7= :G ^ &B<I6 ]*I =.59 #G) ;- < B<% :G % 59.(6) (1983 Strube Hartmann) # # % 59 ' $ &B<I6 # = ; =#7 @a! #.# #G) F.K ^ sc U9I )$RUM B $ (ZM &B<I /= - 7)% ;% sc ) = Rothstein.(5) # *U' @t student &v % 59! ;<* a! 5BR6 % 59 RF % $ F.K wk9 $,9) @F.K,B% #)B / a &P xt'f / RBRI a! $ 2,-.+*! "#$ % $ &'( # )$ #.567 4! 1980 / % #$ )'# = >? % @* <( / 9# )( $ :; <( A9 $ # / <BC # D # @59 * $ / <C :9# E F H HBI J)% : 59 G # D # / KBI &( 59 # B*$ /= E<A O# L9 = $ JF6 M $ N 67$ # *.# # ; NP D ;6 $.+*! JP 9 &: $ Q7 RBRI F.K % # #R( RRI! :59 / S $ T: # ## GB% U)- )W YZ [9 $).)* )W RBRI % 7 ]A # (.59 67 9$ 9$ # ( # 59# ^,- `U @ # < B_ % B_.# 1980 # # ; @ SK #R $ - $ @ @ B7% $ $ % B9 B! $ N) a ^ #U @= EF? `R 5C) $B/ @B*G! A9 ' $.#C N $ PZ &$b M $ P /$ $ ) 59# &B<I ;! @a.(1) # - #!"#$% RBRI!' cbd @Glass $!B. &B<I6 SZK!*: )F &B<I.#$% $ 1976 J9 # : = /=.&% = 5B!BBF ) $ E<A 5'*b $ &% ^ 5-,B% # # '*b ;-! ## b )F 6 #.(1) (1985 Rothstein) D # &( ## h M / $ :# N $ &'( #! &B<I6 a &B<I cj9 N B. i&% / 6 + $ &%!*: = 59# $ &B<I 9 NB# B..(1) N = 59# $ k (ZM NB)%,B% 16
@= @*$ ))%& F @J)% B_ @D /=.k / B h6 5U* :k / #)F SK9-3 $ $ 7 &B<I6 #!B$ k / U9I $ / <P 9 & DA$! : (" ]A F.K = :D 5BGB% $B/ -1 :59! # "#% 5 ( hbri 9)a J ' NBC R F.K / % #!BBF $ <P! $.# ##,? = $ $ )! $ ONB)% #G9 #B7 b ] # BC # B )9,B.))% $B/ ]A F.K 7 G / 5- % # G7 <P! # : wbis -2 #G9 %9 ^ a / @= &B<I (ZM =l'-.(hbri B?6 / >ZM () # GBt 7&B<I6 : # U9I -3 / M $ = U9I % ## ( $ %! :(6) # % U B *U' U9I :kz -E..(!Bj9,?) ## # # #F % # :c &B<I -].# #G9 a! / 59 T$ B*$ 59 }C ' :< G.z a $ -m.# <( &B<I / #G9 $ % $ %& '( ) * +,-.!./(0,B% #! &( # $ 59 /T #!.(3) $ - &$b : $ = * R > KC J'P ' :#)F wk9-1 :/ )U( &( % # B$ 0/01 0/05 wk9 # # % 59 J c / 59 #)F Fb G ^ )# 5U* ' :k / -2.59 B7' KC q#s & #.59 F.K = ' NP $ F.K #)F wk9 ;B k /.59 F.K # #- )# D ^ 7 JP.# G B?6 #$ 59#.(7) #!"#$% &'! % NB)% ]A /P $ $ &B<I6 $ &P cj9 O$ Y: < # /P = # F.K m $B/ l$) 9).(7) NB)% JU#,B $ / * R ]A D,B% @.KC D% ) $ &B<I6 $B/ @ : $ = :/ )U( % # DA$ 9 & #C <P!.(8) $B/ ZC ^ B @l$) 9) # # % ' : - F.K 9) $ @## #- ; bz( # >? l$) : :#% )$NB*R 7 # $ l$). # F.K 9) y($ B. l$).< l$) B. &% & # < l$). B: ' ) O / h M $ # )$9#.59 # D @/ @ssa) @('- EB.+) ]% :#B7 @a;7 @D.9 @(< @UC. ) N<B6 @7/ @.R @SM (ZM ;B > # # NB's :! - # N.+* #.#B7 DA$! # @ma9 $ #)F wk9 :##7 5Uk ma9 $ F.K # NP [9 $ = $ @&( #! #U #.k / ma9 $ (ZM 9# 9 <% M $.#% U9I ' ' F- @ B?6 q @Jz9 :##7 5Uk $ / B7/ ;$ @(#6 B7 ) ) $. #I #)B @B7B :# 5 ( / # $ 9) l$) #$ ) # B h6 5U* : 9) -1 F.K! ]A # # 7&B<I6 # # # # B h6 5U* :Q7% -2 :/ )U( [Z7 / %! % Q7 % @;$ @#/= 9) ' @hbri 9) ' # B_ $ `$ (ZM @hbri SM B7 17
.4 9 5-3 4 5 67!,-./ 012 " # % U9I :(N. l'-) * B6 a -1 (T'P l'-) ) # a -2 ( t l'-) ) a -3 ( Z l'-) 69 a -4 ** (# / Z l'-) a$ <9 a -5.## #$% # / #F # :a' a -6 ' / =l'- (ZM #$ #)F!BBF 5- # #)F SK9 # #G9 # % /= / @. * R N $ NP @!BB @a! # :)$Y<$ a -7 / %!BB / qi Q!BB ' % Bk+ c &B<I $ U9I ]A F.K.NB)9 F.K! # B_ &( / :(10) 59 <P 9 & a! :! ;B$ a -8 9 $ = )% B$ 5BFb / #C $ $ hri -E. b # c @ #!BB YZ &B<I6 $ F- $ F # U( #C #R(.U 7&B<I6 #C =l'- -]!B* (ZM ## &:,B% -m 1 +- 23 456!.7 hbb# BF @&B<I6 ^ $B/ /$ # #$ 7= $ &B<I6 # KC l$) / # #- P RBRI a! 5b# U( / O#% ##C = / :/ )U( l$)!.(2) $ Jz9 / Ä ( :]A ' # B79-1!BBF O59 6F H9 % B$#9 RB<9 @/ &: <( [9 $ D > T$ @#)FBn 6 a;7 ( O $ 4.= $ #6 D 7 #)F #F #$ Ä Ä / #G9 :&P * Fisher Edington Winer Stouffer ** Mosteller & Bush! $ k / $ # J)% xz% H # % 59,9) / k / %! )F O$ # H F.K B_ B *U' 7 :$ b$ / H k / @$ 0/3 7 @59 N% k / $ 0/1,9) # / B*$ k / @$ 0/5 7. 59 H9 #)F = / )F @# # G B?6 7.59.5*B G l- # &( = k / 59 @$ N% <BC k / 7-1 : 7 Rosenthal hbri 7. #% N # > KC / k / 7-2.5*B N &$b KC! @$ N% > KC @$ ;$ <BC ' NP $ ^% <BC @$ N% /= % # -3.59 #6 G J.(7) )% /$ # > KC / F.K * R,B% 5- :(9) 5*- #9 / k /,*P$ F.K # * R -1 #)F wk9,*p$ F.K # * R -2 k / #=$ h M / D #,B% -3 a) #)F wk9,*p$ D #,B% -4 (69 E<A = /= $ D ) * R -5 #)F wk9 [9 $ E<A = /= $ D ) * R -6 k / *: = /= $ D ) * R -7 #)F wk9 [9 $ *: = /= $ D ) * R -8 k / *: = /= $ D ),B% -9 #)F wk9 $ ;%' = /= $ D ),B% -10 k / [9 ]A F.K ' # B_ # B K$!BBF 5- :(8) # 67 ^'% / = / 18
@; $ $ U B*$ (ZM # / B*$ 5b ; EB # l * @$ %59# = ^B): / #G9 @(2) D &B<I $ = Bk+ F.K ) B `U ## $ = sc N ;%' @F.K! # k / F.K # C MU $ #% B 59# @k / N @5*B 9$ &$b N #*7 D #$!B$ / F.K # ^ # % $A #!Ç'K B7B!# $,9) #)B D (?!B$ Hartmann) - H$ b$ E% q: @F$ RBRI #9#) = #$% k / 6F (6) (1983 Strube.(4) (&B<I6 ::(6 ;%') RBRI /P ^ # 4P / DB$ #% #9 ( @(B <F k!67 # <% k @&'( # b B$ # = Q7% 7<C &( # $ = Bk+ `U 7<C &( }BA #$ # &$b #)F B ( 77 F.K,B% @F.K $ #I F.K #F @(Glass JR,B9.+*) #'( N*B9 @( &P.+* &:! ')!' U @}b (ZM &$R # # BoB Q7% R.$ B79 @#F B_,% # JZR9 ( )% $A F.K # 9$ # &( &B<I ; # 4'% $ 5U* = J 56B #$.(11) &B<I6 &*() ÅC $.59&B<I &B<I @&B<I6 hbri # a! % # @#:! @:; <( }CT$ ('- * <( # D 4'% /$.(12) 59 #7 A$! /N F.K C$ 5*B )W )%' # DB &Ub / k $ 9$ $ :<$ #Q7' )% #$EBF? &B.# $ 59# $ )B( b @6 $ hbri 5BGB% D# # @)BB # #- q: &B<I6.# = 7- &B<I @B_ E F @B7/ I # G :c ( -2 ( @([Z7 JR,B9.+*) $A F.K # #/= @a SM # G) ]A F.K 5BGB% # c.( )$9# c BF [9 $ F.K :&P.# ## U? / % $ ) #!B$ Y :(,% ) JZR9 ( -3 /= P a @#/= 7 @hri /) F.K ) #- @59 G F.K! # B?6 /= % (... F.K ^ # *$ B_ ) #- @F.K ^ # ;$.(J > KC J'P D ;6) ;$ &B<I *$ B_ 7- &B<I :&P.59 `U # B?6 $ ' / DB$ % ;B # G : &d* -4 $A F.K k / #=$ @Q7% @$ :!B+ :&P.F.K 5BGB% # # # #)F wk9 :}b ## -5 #% - C6 $ % TR Ä B%+ :&P d 5-6 hbb# &% a;7 5B9*P D ;6.R Ä &B<I ; )6 :)6 7)% -6.59 G B*$ @77!BRRI #; #,B% B7' @$ MU)9 / #G9 :&P /=U PM # &B<I6 @&R* 6#s. /=Bn 456!.7 *9:(6 8 :8 :)% B$ 7! &B<I6 /B / C$ Glass! '% # ÅC )B/ ^ $ HU @)B( = a PZK $ F.K B sc EB @#DB J'P #9 qi @!BB ma9 @4'% U 4'% #% ZC @C ## - $ = /= )/B % (? C$ TM R$9 )BB 19
.4 9 5-3 4 5 67!,-./ 012 " BG B*$ /= $ $B/ # ## L9 &B<I6 % 5*B EK. /.C,<K! =#.59 9 ) 5*B RBRI &d* Y# $ FKb " Hall Green.(14) (1986 G7 [9$ ## &B<I Wolf) "=! ; - 59!BBF $ )% := EF? @# C$ <F H$ )% # 6% D)B$ hbri b `R ## #- a! #.)% E% <C h<c Y# D ;6 # :<$ 5*B - ) ' # a!.(13) 59 ))%^'% B*$ - B?6 #$% @/# $ )B/ hbri # 5BFb :+.20-7 :10 d1366.6b( ^BV: *o7.bb<= q.q!c' -1 2- Glass GV. Primary, secondary and metanalysis of research. Educational Res. 1976; 5: 3-8. 3- Wolf FM. Metanalysis. Sage university paper series on Quantitative Applications in Social Science, Beverly Hills: Sage Publications; 1986: pp: 7-59. 4- Gallo PS, Lynn E. The variance accounted in metanalysis of psycho therapy outcomes: a reply to Wilson. Am Psychol. 1981; 36: 1196-1198..45-35 :1371 d! B '! :.! r. B( V,?-!!' bb<=!.q!c' -5 6- Strube MJ, Hartmann DP. Metanalysis: techniques, applications, and functions. J Consulting Clin Psychol.1983; 51: 14-27..82-71 :1384 d!! :.! r.,+0 # V,!' a V+, >.q!c' -7 8- Hunter JE, Schmidi FL. Metanalysis. In: Hambleton RK, Zaal JN. (eds.) Advances in educational and psychological testing theory and applications. Boston: Kluwer Academic; 1994: pp: 157-183. 9- Drayton MA. A Bayesian Metanalysis demonstration: mathematics achievement in seventh and eighth grade. [Dissertation] Northern Illinios University. 1987. pp: 43-54. 10- Feltz D, Landers D. The effects of mental practice on motor skill learning and performance: a metanalysis. J Sport Psychol. 1983; 5: 25-57. 11- Glass GV, McGraw B, Smith ML. Metanalysis in social research. Beverly Hills: CA Sag; 1981. pp: 3-54. 12- Whitehead AM. Metanalysis of controlled clinical trials. USA: John Wieley & Sons; 2002. 5-16. 13- Chambers I. Systematic reviews in health care: metanalysis in context. 2 nd ed. USA: BMJ Publishing; 2001. pp: 45-51. 14- Watson R, Thompson RD. Integrative literature reviews and metanalysis. J Advanced Nursing. 2006; 55: 330-363. 20
Title: What is Metanalysis Authors: M. Shokati Ahmad Abad 1, Parkhiadeh Hasani 2 Abstract A meta-analysis is a systematic quantitative review of original research studies about some phenomenon, such as the effect of a specific treatment on some aspect of health or behavior. The meta-analyst expresses the magnitudes of effects from all relevant studies in the same units, then uses an appropriate weighting factor (the inverse of each effect's error variance) to combine the magnitudes into a mean value and its uncertainty (confidence limits). In a traditional meta-analysis, the true effects are assumed to be homogeneous (have the same value) in the analyzed studies, and some "outlier" studies may be eliminated to satisfy this assumption. In the more recent and realistic random-effect or mixed-model meta-analysis, true values of all effects are assumed to be heterogeneous (different), and the analysis provides an estimate of the heterogeneity as a standard deviation representing unexplained typical true variation in the effect between studies. Inclusion of study and mean subject characteristics in the analysis as covariates may reduce heterogeneity and provide further useful information about the magnitude of the effect in different locations and with different subjects. Published effects are usually larger than their true values, owing to the misuse of statistical significance as a criterion for publication. A funnel plot can detect such publication bias, but there is currently no satisfactory way to adjust for it in the meta-analysis, and the only long-term solution is to ban statistical significance. Key Words: Theory; Metanalysis; Statistical Methods 1 PhD Student of Nursing, Shahid Beheshti University of Medical Sciences. Tehran, Iran 2 Corresponding Author; Assistant Professor, Faculty of Nursing and Midwifery, Shahid Beheshti University of Medical Sciences. Tehran, Iran msn_sho@yahoo.com 21