Journal of Educational Measurement & Evaluation Studies Vol. 6, No. 14, Summer 2016 *** 0' U ^. >>:' H0 ***

Σχετικά έγγραφα
Research on Economics and Management

Bayesian statistics. DS GA 1002 Probability and Statistics for Data Science.

Chapter 1 Introduction to Observational Studies Part 2 Cross-Sectional Selection Bias Adjustment

: Monte Carlo EM 313, Louis (1982) EM, EM Newton-Raphson, /. EM, 2 Monte Carlo EM Newton-Raphson, Monte Carlo EM, Monte Carlo EM, /. 3, Monte Carlo EM

Mantel & Haenzel (1959) Mantel-Haenszel

Statistical Inference I Locally most powerful tests

1 (forward modeling) 2 (data-driven modeling) e- Quest EnergyPlus DeST 1.1. {X t } ARMA. S.Sp. Pappas [4]

ST5224: Advanced Statistical Theory II

Matrices and Determinants

ECE Spring Prof. David R. Jackson ECE Dept. Notes 2

A summation formula ramified with hypergeometric function and involving recurrence relation

ΧΩΡΙΚΑ ΟΙΚΟΝΟΜΕΤΡΙΚΑ ΥΠΟΔΕΙΓΜΑΤΑ ΣΤΗΝ ΕΚΤΙΜΗΣΗ ΤΩΝ ΤΙΜΩΝ ΤΩΝ ΑΚΙΝΗΤΩΝ SPATIAL ECONOMETRIC MODELS FOR VALUATION OF THE PROPERTY PRICES

... 5 A.. RS-232C ( ) RS-232C ( ) RS-232C-LK & RS-232C-MK RS-232C-JK & RS-232C-KK

172,,,,. P,. Box (1980)P, Guttman (1967)Rubin (1984)P, Meng (1994), Gelman(1996)De la HorraRodriguez-Bernal (2003). BayarriBerger (2000)P P.. : Casell

Prey-Taxis Holling-Tanner

HONDA. Έτος κατασκευής

Homework 8 Model Solution Section

Buried Markov Model Pairwise

Supplementary Appendix

High order interpolation function for surface contact problem

Χρηματοοικονομική Ανάπτυξη, Θεσμοί και

FORMULAS FOR STATISTICS 1

Conjoint. The Problems of Price Attribute by Conjoint Analysis. Akihiko SHIMAZAKI * Nobuyuki OTAKE

EM Baum-Welch. Step by Step the Baum-Welch Algorithm and its Application 2. HMM Baum-Welch. Baum-Welch. Baum-Welch Baum-Welch.

Πολιτισμός και ψυχοπαθολογία:

Parts Manual. Trio Mobile Surgery Platform. Model 1033

11 Drinfeld. k( ) = A/( ) A K. [Hat1, Hat2] k M > 0. Γ 1 (M) = γ SL 2 (Z) f : H C. ( ) az + b = (cz + d) k f(z) ( z H, γ = cz + d Γ 1 (M))

OLS. University of New South Wales, Australia

Fourier Analysis of Waves

NOB= Dickey=Fuller Engle-Granger., P. ( ). NVAR=Engle-Granger/Dickey-Fuller. 1( ), 6. CONSTANT/NOCONST (C) Dickey-Fuller. NOCONST NVAR=1. TREND/NOTREN

: Ω F F 0 t T P F 0 t T F 0 P Q. Merton 1974 XT T X T XT. T t. V t t X d T = XT [V t/t ]. τ 0 < τ < X d T = XT I {V τ T } δt XT I {V τ<t } I A

Fourier transform, STFT 5. Continuous wavelet transform, CWT STFT STFT STFT STFT [1] CWT CWT CWT STFT [2 5] CWT STFT STFT CWT CWT. Griffin [8] CWT CWT

Cable Systems - Postive/Negative Seq Impedance

MIA MONTE CARLO ΜΕΛΕΤΗ ΤΩΝ ΕΚΤΙΜΗΤΩΝ RIDGE ΚΑΙ ΕΛΑΧΙΣΤΩΝ ΤΕΤΡΑΓΩΝΩΝ

Hydraulic network simulator model

r r t r r t t r t P s r t r P s r s r r rs tr t r r t s ss r P s s t r t t tr r r t t r t r r t t s r t rr t Ü rs t 3 r r r 3 rträ 3 röÿ r t

SIEMENS Squirrel Cage Induction Standard Three-phase Motors

ΠΑΡΑΔΟΤΕΟ 3.1 : Έκθεση καταγραφής χρήσεων γης

2016 IEEE/ACM International Conference on Mobile Software Engineering and Systems

Εκπαιδευτική Ψυχολογία

HW 3 Solutions 1. a) I use the auto.arima R function to search over models using AIC and decide on an ARMA(3,1)

!"!# ""$ %%"" %$" &" %" "!'! " #$!

ΒΙΟΓΡΑΦΙΚΟ ΣΗΜΕΙΩΜΑ. Λέκτορας στο Τμήμα Οργάνωσης και Διοίκησης Επιχειρήσεων, Πανεπιστήμιο Πειραιώς, Ιανουάριος 2012-Μάρτιος 2014.

SOLUTIONS TO MATH38181 EXTREME VALUES AND FINANCIAL RISK EXAM


6.3 Forecasting ARMA processes

46 2. Coula Coula Coula [7], Coula. Coula C(u, v) = φ [ ] {φ(u) + φ(v)}, u, v [, ]. (2.) φ( ) (generator), : [, ], ; φ() = ;, φ ( ). φ [ ] ( ) φ( ) []

Supplementary figures

! "# $ % $&'& () *+ (,-. / 0 1(,21(,*) (3 4 5 "$ 6, ::: ;"<$& = = 7 + > + 5 $?"# 46(A *( / A 6 ( 1,*1 B"',CD77E *+ *),*,*) F? $G'& 0/ (,.

2. THEORY OF EQUATIONS. PREVIOUS EAMCET Bits.

Other Test Constructions: Likelihood Ratio & Bayes Tests

Example Sheet 3 Solutions


clearing a space (focusing) clearing a space, CS CS CS experiencing I 1. E. T. Gendlin (1978) experiencing (Gendlin 1962) experienc-

ΤΟ ΜΟΝΤΕΛΟ Οι Υποθέσεις Η Απλή Περίπτωση για λi = μi 25 = Η Γενική Περίπτωση για λi μi..35

Reliability analysis Ανάλυση αξιοπιστίας

ΑΣΚΗΣΗ 9 Μικτή Συνδεσμολογία, Ισχύς

Exercises 10. Find a fundamental matrix of the given system of equations. Also find the fundamental matrix Φ(t) satisfying Φ(0) = I. 1.

())*+,-./0-1+*)*2, *67()(,01-+4(-8 9 0:,*2./0 30 ;+-7 3* *),+*< 7+)0 3* (=24(-) 04(-() 18(4-3-) 3-2(>*+)(3-3*

ANSWERSHEET (TOPIC = DIFFERENTIAL CALCULUS) COLLECTION #2. h 0 h h 0 h h 0 ( ) g k = g 0 + g 1 + g g 2009 =?

Λογαριθμικά Γραμμικά Μοντέλα Poisson Παλινδρόμηση Παράδειγμα στο SPSS

Εργαστήριο στατιστικής Στατιστικό πακέτο S.P.S.S.

Σύνθεση και Χαρακτηρισµός Χαµηλοδιάστατων Ηµιαγωγών Αλογονιδίων του Μολύβδου και Χαλκογενιδίων.

SCHOOL OF MATHEMATICAL SCIENCES G11LMA Linear Mathematics Examination Solutions


Durbin-Levinson recursive method

7. ΕΥΧΑΡΙΣΤΙΕΣ 8. ΠΗΓΕΣ 6. ΣΥΜΠΕΡΑΣΜΑΤΑ

Repeated measures Επαναληπτικές μετρήσεις

Erkki Mäkinen ja Timo Poranen Algoritmit

Solving an Air Conditioning System Problem in an Embodiment Design Context Using Constraint Satisfaction Techniques

Dissertation for the degree philosophiae doctor (PhD) at the University of Bergen

Dark matter from Dark Energy-Baryonic Matter Couplings

Biostatistics for Health Sciences Review Sheet

Παρασκευή 1 Νοεμβρίου 2013 Ασκηση 1. Λύση. Παρατήρηση. Ασκηση 2. Λύση.

ΣΧΕΔΙΑΣΜΟΣ ΔΙΚΤΥΩΝ ΔΙΑΝΟΜΗΣ. Η εργασία υποβάλλεται για τη μερική κάλυψη των απαιτήσεων με στόχο. την απόκτηση του διπλώματος

Vol. 38 No Journal of Jiangxi Normal University Natural Science Nov DIF differential item functioning


519.22(07.07) 78 : ( ) /.. ; c (07.07) , , 2008

Discriminantal arrangement

Discontinuous Hermite Collocation and Diagonally Implicit RK3 for a Brain Tumour Invasion Model

Errata (Includes critical corrections only for the 1 st & 2 nd reprint)

:,,,, ,,, ;,,,,,, ,, (Barro,1990), (Barro and Sala2I2Martin,1992), (Arrow and Kurz,1970),, ( Glomm and Ravikumar,1994), (Solow,1957)

ΤΕΧΝΟΛΟΓΙΚΟ ΕΚΠΑΙΔΕΥΤΙΚΟ ΙΔΡΥΜΑ (Τ.Ε.Ι.) ΠΕΙΡΑΙΑ ΣΧΟΛΗ ΔΙΟΙΚΗΣΗΣ ΚΑΙ ΟΙΚΟΝΟΜΙΑΣ ΤΜΗΜΑ ΔΙΟΙΚΗΣΗΣ ΕΠΙΧΕΙΡΗΣΕΩΝ ΚΑΤΕΥΘΥΝΣΗ: ΔΙΟΙΚΗΣΗΣ ΕΠΙΧΕΙΡΗΣΕΩΝ


Vol. 37 ( 2017 ) No. 3. J. of Math. (PRC) : A : (2017) k=1. ,, f. f + u = f φ, x 1. x n : ( ).


ΕΚΤΙΜΗΣΗ ΤΟΥ ΚΟΣΤΟΥΣ ΤΩΝ ΟΔΙΚΩΝ ΑΤΥΧΗΜΑΤΩΝ ΚΑΙ ΔΙΕΡΕΥΝΗΣΗ ΤΩΝ ΠΑΡΑΓΟΝΤΩΝ ΕΠΙΡΡΟΗΣ ΤΟΥ

MÉTHODES ET EXERCICES

CRASH COURSE IN PRECALCULUS

APPENDICES APPENDIX A. STATISTICAL TABLES AND CHARTS 651 APPENDIX B. BIBLIOGRAPHY 677 APPENDIX C. ANSWERS TO SELECTED EXERCISES 679

Νόµοςπεριοδικότητας του Moseley:Η χηµική συµπεριφορά (οι ιδιότητες) των στοιχείων είναι περιοδική συνάρτηση του ατοµικού τους αριθµού.

ΕΘΝΙΚΟ ΜΕΤΣΟΒΙΟ ΠΟΛΥΤΕΧΝΕΙΟ

1. Panel Data.


ΔΘΝΙΚΗ ΥΟΛΗ ΓΗΜΟΙΑ ΓΙΟΙΚΗΗ ΙΗ ΔΚΠΑΙΓΔΤΣΙΚΗ ΔΙΡΑ

Simplex Crossover for Real-coded Genetic Algolithms

ΔΙΠΛΩΜΑΤΙΚΕΣ ΕΡΓΑΣΙΕΣ

Διευθύνοντα Μέλη του mathematica.gr

Quick algorithm f or computing core attribute

þÿº±¹ ½ ÀÄž ÃÄ Í³ÇÁ ½ À

Transcript:

Journal of Educational Measurement & Evaluation Studies Vol. 6, No. 1, Summer 016 11-39 ()!139 $%&'!1 "#! 9/06/08 : 9/01/9 :!&" # +( )* :&)!" #$" (1391 * *+, ** /. & *** 0' 1 01 +* 6; 9:'. +*.0 3 67/ ) 86 #6 A!B A+.@ %/ <+% $ 6 = &+> @&+ H. I' +. 1391-9 $ $0@0 R/ O/. PQ%.' ) N 000 #!(; 0) $ 6;!NOHARM *T.N% $. S'. 6 $. %U B 0 %/. 9:' MULTILOG!V. $1!@ +* A+'S+.*! "6.$ 6 A+ <+%. PQ% +* $ = 6 &+>,1.@ +* 6; : 6+* 9:'. A+ +0 6$. +'!%/ W% 'A+/ 6. +'!+* %/ = &+>..0. % @X. W% 'Y $' <+% H... @+Z %/ ' 6!+*.N% ; 6+*.Z#1 6 +* 6= + 0. +*..0 %/!+*!; ]/ +B!I$ :0 $[ (izan.b@khu.ac.ir!_& &+) U ^. %' T1 $ Z. +.% * U ^. %' T1 $ Z. +.% ** U ^. >>:' H0 ***

#+&" #+ 03 67 89 1 S,0 +B b...` Va +B.. 0 ; ]/ +B.. @d& 1 Ac $ +/ $' 0!. 6 0 ; ]/ +B 6... $e/ @N) +B $ f % 1,g!. U +` +B! S,0 +B 9>'.(1989! 3 $%d#6). 6 $.!;.. 6.N% +* 6$ 6; 9:' +*I'.. 0...` @+.: A+!S,0 +B #6!; ]/ +B. jy# 6 A+..# 9iX >%& @+6!: 6+* * e. N) =!@. 6+* ]/ S+ =!@. ]/... @. +* j)!; 6%/. % B +' k. '1,g!6; : 6+* 0 ') @. 6+* S+ 6 PQ% #% %&6 $6.]/ 6]/ #6 $'#. 6U N%!l%Q +' m. 6. 6+*..` > 1,g A%^ B..@&. =6 @. 6U N 1,g A% @. V`!. W' PQ% :.0 N+ 6. +' k. @X. +*. n; > ' 0-6 B o:!. 6 S,0 8,U ; 6%/.. ' 0.U @X A+!; ]/ +B 1,g *0#' +* 6; 6$. 6. +' ; 6%/. @X. +* V` @. 6+*..`. V.N% p.. 6 &+>. 6 '6.6 ' +* $ 6; 9:' +*I' @. 6]/ #6!..N% ). $...# + e..` 1,g % B. >dg S+. 1. Spearman. latent trait 3. Hambleton

13.... $1 +* 6 PQ% #% 0 @.U @+* A+..# =6 @. 6]/ 0. +' k ' '1,g ' > g!@ +' k ' +* 6 PQ% 0 I q b1983! 1 ^. A+) %.. 6.]/ +' k. *.(01! $Z#6 @Q!=^,1! ]/ >dg 9#% 6; 6; VX. 7+!.%& g * +' 6$.!=6 r ' 9Z 9. A+'Z A+'. +..N% 9X!+* 6; 6$.`!; ]/ +B 6...N%! %U 6$. jy# 0 @ I r. 7+ I l%q 6. +6$ A.N% A. +.@ P%` 9Xa!1#%` %Q 6s% 9#% 6; 0 @ `'. i*` 6N' I!+6. A.! A+.%& e $I.X j#1!. 6]/!]/ r>dg..u 9. 0 6;.N%,1.+ 3!6. / @N) %/ 't lg ' &+>. 6; @p`!i$ Z U 9. A+. 6; 0 @ A+ Z Z+.@ %. 6; 6. / +' %/ 't lg!. 6; &+> 6;. % ]/ >dg A%. @X A+ 0 #6!@N $' 'ux. $.@. 6; &+>. ). +' %/ ' ' (.) ; v @. 6 $* 0 @. `' + (@+e @dw ' @+e N.U x r> ( b j ) ; Z ^+`.. 6 ; S+ 0 V jda!+ / @N) %/. > A+ 6 r>. ; S+ X6 Z+ @N^.+ 60 6.6 $*!' 1. Levine & Drasgow. Ning et al

#+&" #+ 03 67 89 1!+' %/ '.: lg!0 6 % 6!.U x 0 @ A+ 6 @+*.@. 6U N 6.6 % 6 0.U @X A+!% >dg. ' %.U.(006! 1 q+ %y) 0 6 @N) %/ 't lg. 6 >dg. 0 0 86 0 %U $ gu (1988) %& 0 @. @N) k ". % 6 +@. @e`. =,'!; @N) k 'ux. 6. 0 g! X. ". 't` Q ' 1,g 0.. $ A+,1.. 9).. 9) +* $ 6 6; ' 6; $6.]/ +* #`-{ + (197) { 3 # ]/ e &+> (NRM) 6 # ]/ = 9) <+%.@ (MCM). 70 6]/ H @X. B %/. <+% %#0 6+' 0.. $ $+ / 6O+' $ 6; ' 1/!# ]/ 6.6 $* +' %/. N)!A&') 6 * 6 +* +'. 90..@ %/. @X. * :' @ / +* 6$. v3 A+ 0..(1976... 7+!+' m w0. # ]/ +'.! # ) @ %/.. @X. % &!A+/ +' %#0 6;!(NRM) # ]/ 0,1.(1387.(1993! 7 Y+.). 9) %/. @X. $#6 ' @ SZN' $Z A+ H 0 @ $ # ]/ 6%0 PQ%.' ) +* 0 +e 6 +* 0. (1997) { # (1979) #`!B A#6...`!0 1. Ostini & Nering. Masters 3. Nominal response model. Bock-samejima (BS) model. Multiple choice model 6. Nominal Response Model 7. De Ayala

1.... -{ 0 A+... * VI H %/ 0.. W& g S+ 6+* T#' VI H %/ $*!@ 8 * #` A+ @#6 9..(@ ; 6+*. ' m ) 0 R 1/m ;. +* 6;. : 6+* > `' U!v3. @. 6+* PQ% A 0 @ $ 0 667/ <+% +.@!. % I $. H. +' k 6; &. 6+* PQ% : A+.(199! 1 $Z#6 ^.)...` :' @ / +* 6$ W>.. @#6 * 6$ + #`-{ &+> (1989) ly0#..#.: $ A+.@U./ ]+' +* $ S+ 6... %/ : 6+*!$ 6; 6. 0 @U g 6.6 : 6+*!6; ^+. 6. $e/ @N).. $ <+%..0 ; v...00 A+.d.. %/ %e ; v. 6 #`-{ =. 7+!#`-{ @X. 0.. $!* 6.6 $* B.@ %/ 'l 3.. ; S+ 6+* T#' 0 @ $. #`-{ ) (> A+ $ 0 (198) d% A&'.. B. &Z+ H { # ',) #1 0) #`-{!9Z,1 0.. W& g (@ i (1979) #` W' (197) i $^ 67/ A+... *.' H %/!6%/ + = 6%/.!6.. A N)' Q& 0 6 + A+ <+%.. i g 0 +#@...0 &+> 3 +#@. @d& S#0!%&6 A+.: +* 6; : 6+* +*.0 l)' 1. Drasgow et al. Smilaycoff 3. Likelihood Ratio Statistics

#+&" #+ 03 67 89 16 990 6]/ e.@ TI (1989) S+'/*% d%!a&' W' 0 $ S+ Q 0 0 8 ƒ 3+ ;. A+ 0.0 9:' A+. 3+ @ / ; :. 6$ @U g. P 6+* 6; (Q '... X. +* U! 6 l%q +*.`!.@ ; `!.#.N% 6 A+ Z+!; 9:' 0 t 0 ',Z U.. (009) 1.&/ :. d% A&' +* #` +*,Z (1 : 'd1 0.0 U A+. 9Z %U./ ƒ,z ( b6%/ $..+ @1 6%/. ƒ ]/ 6 A+.U (3 b d% A&'. 6%/ +p/+ ' 6 = U. 667/ <+%. 3 % @. 6.@ e A+'e U.. 0 @ > 3!(197) { e = (199) $Z#6 ^. (198) d% A&' +*!(1979) 6 #` +* ASVAB) e +* $ 6; (1993) 7 A+ S+%/ # ]/.. $ <+%..0 N 3000 # (ACT! SAT!. 6%/. ' +*.. B. 6.. U & =!{!{ # ]/ @d& d% A&' +* #`!67/ <+% u.. /. 6.. 6 = $*..de... $ U = 6$ #' * A+ S+%/ 1. Abad, Olea and Ponsoda. identifiability 3. omitted responses. Drasgow et al. Bock 6. Samejima 7. Levine

17....!#` +* (009).&/! 9>. ) +` +* S+ # ]/! d% A&' +* R 6&Z.. 0 1 #`.: +* T A#Q' @+* A+ @ '8N!% @. 6.. U. $ % $ S+. N 3 # (0.N% 6%/ 0.. $ χ = (U <+%... X =. &^ 6..!# ]/ %e dx +*. 9w +`.e /. 67+ 0 v3 A+ +f' B ^+... = TI * %/ + U. d S+!@ %e j X +` +!dx +*. @d& +`. 0.. $ <+%..@ %e 6%/ @N + 9:' V PQ%..N% 6.%& lg $' +* 6;. $ B!:' @ / 6$ 0 I.0 `. V& ]/ 6+* $% 0 # g g jy# ^.. ).0 V' _& 9 $p + k:) ]/ A+ (@ B. (PCM) 3 ZZN' % + (GRM) x ]/ +*. V # ]/ v 6 0..N% + 6 v.0 m (198) d% A&' 0 +*..` 1,g #' $... ƒ 0 @ ; ]/ +B. @X. $.0 k:) 6]/ W> 6. 6]/..@ ]/ >dg m. j ; 0 R...N% +' j ; (k = 1,,..., m)t k >dg θ +'. Z #% +* : @ 6. ]/ 1. Restricted Samejima Multiple-Choice Model. Graded Response Model 3. Partial Credit Model. Thissen and Steinberg

#+&" #+ 03 67 89 18 exp( c + α θ ) + d exp( c + α θ ) p ( x = k θ; α, c, φ) = j jk jk jk j0 j0 m j h= 0 exp( c + α θ ) jk jk (1) d jk d R1 %/ c jk!v %/ a jk!+' %/ θ $. 0 6. $ +66.]/ @d& @ " 1.#" $e/ ]/ >dg %/ c!α 6. 0. `'.0 PQ% j ; k >dg ".#" 0 $#6 N) 0. >dg,1.%&6 m!6+*. ' g. d!a&' (198) d% A&'. % i*`) @ ".#" >dg 6 @. +* 6! A+..(@ i (1989) S+'/*% d%! d% A&' +*. 9:' +*I'!: 6+* +* 6;. +* 6.Z#1 %/ +' ),U +' +* 6 PQ% #% A 6),U A+ 0 0 6 ; 9:'.%&.0!0 g.0 l)' I : 6+* % 6.Z#1 % e +* H.N%!; 9:'. ' ^ +* Z+. p.. '!+* $ 6 6; 9:' ; $g.! %N V `'.(1989!S+'/*% d%!a&') N @&+ Q 6; I$ 67+ A ' 86 3 67/.@ % TI +* H 1391 $. 6 +*. @&+ $ 90 6!,1.. &+>!%/ = +* = %/ 3&@3 A. 0 6^.. $dg. #6 9 67/ A+ ` T1 %.. ' A+..@ 1391 I' T1 + Z+ `'... N 137 $ N 30608 9 N 99 I'!. t+' g %. e. 6;! + 6 S+ 6. 1. don t know

19.... %. 0 9:' dg. ƒ 6.. W> 67/ A+. 6+* V''. W> 6%. N' 0 @ 0ˆ $+.... ]/ A N 000. '.' # SPSS *T.N% #.@ 0 $ +*e 6; $dg. 6]/ 9 6... PQ% MULTILOG 6*T 6.. 9:'.. @&+ Q ; R/ O/ 0 ) A+..N% NOHARM!jMetrik +' ; 6%/. B NOHARM $. S' '..N% MULTILOG *T %/ +*..N% jmetrik * 6 6.. 6.# $9 $. S' R/!IRT +*.N% 6]/ 9:' / 1 6 pi A^ T. + (U. NOHARM.N%... 6.. S' PU = 0 @ 0/0037 (RMSR) dx 9X = 0 @ 0/987 67/ A+.! 0' U (U.(1393!$Z#6 *+) 6. $ 1. Root mean square of residual. Tanaka

#+&" #+ 03 67 89 0 6 $ C D&7E (1) 1+ (3 ) IE 0@3 & 6 $ H*3 (G3 (F6) &@3

.... 1 A (1) $0" 0@$ $JE+ LK 6 l+. 6) V'' (@ ƒ @ @# $% 6; ; %/ (1)DK 3 (1)DK 3 (1)DK 3 (1)DK 3 1 1 7 0 a k -1,13-1,0,6-0,77 0,6-1,8-0,80-0,6-0,3 3, -1,3-0,81 0,11-0,1, -0,93-0,0 1,37-0,17 - c k -0,1-0,0,3-1,13-0,9 -,67-0,6 0,11,7 -,7-0,61 3,8-1,6-0,,19 - - d k 0,1 0,6 0,0 0,17 0,1 0,67 0,8 0,19 0,9 0/0 0,61 0,3 r pbi s - 0,8-6 - - - 0, - 0,37-0, - - P+ 0,3 0,1 0/ 0/08 0/07 0,1 0,13 0,1 0,30 011. 0, 1 8 1 a k -1,0-0,6-0,93 -, -1,7-0,0-0,9,79-0, -1,9 0 -,90-0,6 -,03, -0,86-0,89-0,77 c k -0,38-0,8-0,7-0,,17 -,39-0,61-0,37 3,63-0, -3,1-0,11-3,7-0,1 -,9,7 - -0,1-0,66 d k 0/0 0/03 0,18 0,77 0,16 0,7 0,0 0,1 0,63 0,89 r pbi s - 6 9 0, - 0,3 - - 1 0,9-0,7-0,16-0,11 - P+ 0,17 0,7 0,18 0, 0,1 0,1 0,9 0,17 0,16 3 16 9 a k -1,7-1,6,17-1,01-1,18-1,36 3,03 - -0,7-0,8-1,1-0,1,37-0,38-0,7-1,07-0,8,3-0,9-0,9 c k -1,88-1,90,68-0,68-1, -1,0 3,37-0, -0, -1,1-1,17-0,6,9-0, -0,70-1,93-0,0 3,1-0,36-0,1 d k 0,98 0,39 0,1 0,8 0,8 0,6 0,80 0,13 r pbi s - 0,0 - - 0/39 0/03 7-0,37-0, - - P+ 0,3 0,1 0,17 0,30 0,178 7 0,113 17 30 3 a k -1, -0,0-0,8,9-0, -1,81-1,38,6-1,0-1,3-1,33-0,77,70-0,68-1,6 0,6-0,7 1,87 c k,1 - -0, 3,99-1,7-1,3-1,17,38-1, -1, -1,61-1,3 3,1-0, -3,6 0,6-0,7,7 0, d k 0,99 0/01 0,99 0, 0, 0,9 0,16 0, 0,7 r pbi s -0,11-0,111-0,78 - - 0,6 - - 0, - 0,1 P+ 0,11 0,8 0,1 0, 9 0,1 7 0,183 0,11

#+&" #+ 03 67 89 ; %/ (1)DK 3 (1)DK 3 (1)DK 3 (1)DK 3 18 31 a k -1,7-0,83 0,1 1,8 -,03 -,9-0, -0,6 -,6-0,90-0,66-0,76,9-1,09-0,3 1,0-0,13 c k -0,98-0,8-0, 0,3 1,8-6,08 0,, 0,6 0,66 -,8-0,3-0,13 6, -,3-0,,7-0,18 d k 0/0 0/0 0,3 0,1 0,1 0,8 100 0/07 0,31 0,3 0,0 r pbi s - 0,0-7 0,3 - - - 0,8 - -1 0,7-9 P+ 0,11 0/07 0,13 0,1 0, 0,11 0,13 3 0, 0,13 0,136 0,1 0,11 6 19 3 a k -1,6-0,8 1,6 0, - -1,7-0,83-0,17,7-1,3-0,7 1,9-0,30 0,98-1,10-0,86-0, -,8 c k -,10 0,31 3,3 1, - -,30 0,13 0,30 0,,0-1, -1,01 1,86-0,13 0,83-1,01-1,9-0,1-0,9,7 d k 0/0 0,88 0,17 0, 0,60 0,3 0,7 0,13 0,19 0, 0,1 r pbi s -0,1 0, 0,13 - -0, - 0,3-0,30 0,0-6 8 0, P+ 0,0 0, 0, 0,16 0,1 0,1 0/06 0,1 0,1 7 0 33 6 a k -1,7-0,96-0,83-0,8,1-0,9-0,9 - -0, 1,8-1,1-0,8-0,60,98-0,67-1,6-0,69-0,6 3,8-1,03 c k -3,3-1,6-0,61 0,18,11-1,11-0,9 0,6-0,37,18-1,13-0,79-0,8 3,68-0,93-1,1-0,78-0,73,0-1,7 d k 0,97 0,6 0,68 0, 0,7 0,91 r pbi s - - 0,1-0,13 0,38 6-0,0-9 0 0,39 - P+ 0,3 0,11 0,18 0,1 0,30 0,3 8 1 3 7 a k -0,96 1,8 0,30-0,63-0, -,19-0,70-0,7-0,77,3-1,8-0,3-0, -0,81 3,67-1,6-0,3 1,0 1,7-0,3 c k -0,7 1,73 0,3-1,18-0,1 -,07 - -0,8-0,3,7 -,08-0,7-0,39-0,8 3,80 -,7 -,18,1 d k 0,38 0, 0,1 0,99 0,0 0,7 0,3 0,3 0,33 r pbi s 0,9 - - - 0, 0,11 0,0 0,9 0,6 - P+ 8 7 0,111 0,30 6 9 0,11 9 a k -1, -0,39-0,,78-0,1-0,68-0,3-0,9 1,90-0,0-1,3-0,16 - -0,38,03-1,07-0,97-0,1-0,6 3,7 c k -3,30-0,3-0,,0-0,7 - -1,09-0, 1,87-0,8-3,9-0,8 3, -1,76-0,83 - -0,68 3,36

.... 3 ; %/ (1)DK 3 (1)DK 3 (1)DK 3 (1)DK 3 3 8 d k 0,98 0/00 0,8 0/0 0,11 0,86 0,87 r pbi s - - 0,6 - - - 0,13 - -7-3 - 0,36-6 - 0,3 P+ 0,0 0,17 0,3 0,1 0,30 0,19 0,1 10 3 36 9 a k -1, -1,17-0,89 0,73,7-1,76 - -0,7-0,66, -1, -0, -0,,89-0,8-1,6-1,30, -1,10-0,0 c k -0,6-1,6-0,86 0,7,3-0,7-1,0-0,6-0,8, -3,07-0,6-0,7,10-0,11-1,18-1,6,3-0,73-0,88 d k 0,1 0, 0,0 0,3 0,0 0,89 0,76 0,18 r pbi s - - 0, 0,8 0,6 - - 0,39 - -6 P+ 0,11 0,1 0,13 0,0 0,37 9 0 11 37 0 a k -,80,6 -,1 -,6, -1/3-0,3,06-0,9 0,81 -,69 3, -,09 -, 3,79-1,3 0,91-0,3 1,9-0,96 c k -,7,1-1,86,1,3 -,8-0,9,6-0/71.1 -,3,8-1,89-1,89 3,7 -,16 1,07-0,66,3-0,9 d k 0,33 0/01 0,6 0/10 0/0 0/0 0/38 0, 0, 0,0 0,69 r pbi s 0,1 - -7 0/0 0,31-0/0 1/06 0,7 0, - 0,13-0,1 P+ 0,16 0,7 0/03 13/0 1/038 009/1 0,11 0,3 0, 1 38 a k -1,3-0,3 0,6-0,70,0-1,08-0,3-1,99-0, -1,10-0,8-0,8-0,33,1 c k -3,9-0,6 0, -0,31 3,0-1,90-0,1 -,78-0,63-1,1-0,68-0,67-0,19,9 d k 0/01 0,16 0,78 0,3 0, 0,18 0, 0,9 r pbi s - - 0, - 7 0,397-1 - 7 0,37 P+ 0,0 0,0 0,119 0,170 0,11 0,13 13 6 39 a k -1,79-1,3-1,9 3,3 1,6-1,6-0,90 1,17 1,96-0,9-1,90 3,3 1,19-1,0-1,3 c k -1,3-1, -1,00 3,7-1,98-0,8 1,77, -1,3-1,86 3,3 1,73-1,9-1,93 d k 0,71 0,1 7 0,39 0, 0,6 0,38 r pbi s 0/01 0/00 0/30 0/0-0,3 0,9 0,3 0,16 - -7 P+ 0/07 0/0 0,1 0/03 0,1 0,16 0,1

#+&" #+ 03 67 89...` 0p $ $. S' R/. 0 6!A+ i (1) `. +*.N% 6.. 9:' ƒ 6%/ H!(a k) V %/! 1 ; 6 6+* T#' A+.@ ƒ 6%/ 0 @ 0ˆ TY.0 i (c k) d R1 (d k).0 6 $. ]/!; 0.!DK=Don t know).# +* 6!; 6 6%/ +..@ i ` A+. * (.0 PQ% +* 6 0 (P+). @d& (r pt-bis) > %. ^%&d#6.n% @&+ $ 6; 9:'.@ i!.0 A....` $ A+. ; %. e v#i... $ +*. P&: d 6; 0 %&6 7 37!6!6 6; %. k +* 0 A+ b.. * V!6; A+. 0 +* +.+ 60 @. ]/ PQ% #% $dg. +' ]/ t' (1 `) @&+ $ 6 ; 6%/!# 6 <+%) 0 `' (1) 9Z. ; A+ 6+* S+6 ƒ.(0 &+> l.#. ; +* e 6 6 6.. 9). 3 : +* 0 6. $ (1) `. V %/ +.> 1 9Z. : +* A+ ƒ.# 0 g$#6 @ @dw V +* @1 : +* A+ PQ% #% +' k +* @/ PQ% `. +Y +' 0. % 0 @ $ A+.+.Z#1 6.$ 0 : +* A+ Pp` (@. ]/) +* A 0 6. $ +* A+ c k %/ >.@ 3 : +* P %. $dg. A @d: $* A+% 3 : +*!; 6+* 3 +* ). 0/.. ]/ ; A+ 0. T#' A @ ). 88 0 6. $ 3 : +* Y H %/..0 PQ% +*!.d @. ]/ (Q '.X %. +/ +' 0 dg. ) 6..!3!!1!0 ` 6.. +* 6.. 9:' 0 0 `'. 1.. S+ 3!0 +* #`!6+* T#' +. p0 (!3!!1=DK).. `' %Z A+ 6.# 6 6.. ƒ 6.# <+% &+>

.... (r pt-bis) > %. ^%&d#6 V+3.1 >..0 PQ% 3 @dw 6.$ 0 @ 0/ (1) `. 3 : +* ƒ ƒ n WU 0 g$#6.@ $ 90 # : +* A+ # A S+.* ' +' A+/ m!@/ (1) 9Z. ( +*) 0 +* Z+.*. + +* * k:) ]/ #% +' +* -1/ +' +' k A+. 0/3!.U > A+% #% A+ -1 +' A : +*.+ 60 @. ]/ #% +' +* 0 jd+>' @.U +Y @p`. +/ +' 0 dg. n WU..0 PQ% : +*!. +/ +' 0. ). 60 +* PQ% #% +' +* 0 6. $ : +* A+.+ 6 $ C D&7E () 1+

#+&" #+ 03 67 89 6 (3 ) IE 0@3 & 6 $ H*3 (G3 (H) &@3!+' +* 0 6. $ 9Z. : +* ƒ n WU A+%#0. +* A #6.+ 60 : +* A+ PQ% #% 0 @ $ ^ (C = -0/09) @ Y `. d R1 %/ > B 0 : +* Pp`!6 ; $6.]/ ). e' 6 ; 0 @N $' <+% `'.%. X +/ k. +'.@ %..Z#1 d 6; * e+ 0 %&6 6 33!9!!! 6; T. %. @US+. ) V. +' H e 0 +* + b%&6 %/!v#i..@& @US+ * V. * : 6+* #' 0 +* PQ% #% * +' m A+'A+/. % +' ' A+ 0 @ % 0ˆ 6; #'. : 6+* $1. : 6+* A+/ @p` 0 + ; $.. @1 ]/ t' (1) `. @&+ $ 6 ; 6%/!w <+% <+% A+) 0 `' () 9Z. $ 6+* S+6 ƒ.(0 &+> P.# @dw V A+%. ( +*) 0 +* 0 6. $ V %/ +.> d R1 > A+%!0 +* A #6.@ 6 ; 6+* A.

7..... @d: A+%. +* 6. $ 0.. %U =.U ]/ ; 0. ). 36 A 0 g!@. $dg. A 9Z 0 g$#6..0 PQ% 0 +* %. ). 3 S+.*.. A+ 0 @Y & +' A+/ m. k:) ]/ #% 6. $ () +* Y H %/ @1 + ; @1 + ' ). 91 0 6. $ H %/ A+ + b (c =0/91) 0 %. %&'!.d ; @. +* (Q '.X 0 $6.]/ 6+* d R1 V 6%/ +.>.* H 0 +* * +*. 6 ƒ n ƒu S+.* 6 & 3 :. 6 ud 6 j,0 +' %/ ƒ> U. %.@ p.%&6 @p` A+%. -1 +' k Z+.*. : +* +*. 6!^+. d1.@&. ^+Z+. : +*. A+ $' +* n WU.%. e.z#1 A+/ +' k $dg. Pp`. +* PQ% #% [-3-1/] +' ). 0 6. $ : +' +* -1/ +' k.@ @n jd+>' : I% $' v#i..+ 60 <+' : +* A+ PQ% #% $dg. Pp` 0 @p` 6 ; : 6+* 0 @ * N) jd+>' ^%&d#6 V+3 W' I% A+).d.U A+/ +' 0 +* %. W% A+/ +' $dg. % (. +f' @UZ+. ) V. 0 +* +' H,1.. H.%& @UZ+ * V. * : 6+*

#+&" #+ 03 67 89 8 $ C D&7E (3) 1+ ( ) IE 0@3 & $ H*3 (G3 (M) &@3 ;. : +*. 0 19!17!1 6;!T %. A+.%&6. : +*.. 0 1 36!8!1!18!1!11 6 ' 0 9#1 +*. 6; ) % 6; A+. Vd @ 3 9Z (1) `. ; 6%/ #.+*e 6;.(0 &+> M.# <+% A+) 0 `' (3) V A+%. (3 +*) ; A+ 0 +*. B% 0 g$#6 WU. 6 (3) 9Z. 0 $#6.@ ; 6+*. @dw

9.... R1 %/ +.>.@θ +' k @dw. 0 +* n A+ @ d R1 A+%. 3 +* 0 6. $ `. d 18 S+.* 0 g.@ 6.. 0 +* Y @d:6.$ %/..0 PQ% 0 +* %.!; $6.]/ 90 )... ]/ ; 0 dg. ). 80 0 6. $ 0 +* H +*!k:) g %&'!.d @. +* (Q '.X.. j>x. : 6+* V %/!; A+..* H 0-0/8) @ e jd+>' * : +* V %/ (a =a =0-/9) g$#6.@ 6 : 6+* A+ ƒ n ƒu A #6.(a 3=. A+ ƒ n ƒu!. 6 : 6+*.. 0 : +* 6 0 @N $'!A+.@ ud 6 jd+>' +*.Z#1!A+/ +' $dg. Pp`. +* + Z +^ + 6. 6. $ : 6+* d R1 %/ +.>.%. e @d: A+%.! : 6+* V'' 0 +* 0 jd+>' : 6+* H %/.%&6 $dg. A PQ% +.' PQ% O +*. 6 6. $ 0 @ 6 dg. ). 13 0. 6 : +*....U.' g!.d @. +* (Q '.X.. ]/ ; 0 (r pt-bis) > %. ^%&d#6 6 H..0 PQ% +*. 0 0 `'.%&6 90 # N) jd+>' ^%&d#6. : 6+* 6 Z+ `'!A+.@ %e 6^%&d#6 A+ $. N + @ ) % ; 0 @N $'!^+Z+. ; : +* $ : 6+* +*e ; ' @.0 9#1 +*. ;.. %e : 6+* +*^+` m,)!: 6+* 6; A+..%&6 3! 6;!Te %.!w.. 0 %. d.z#1 jd+>'!6; > @d& A+ 6+* S+6 ƒ ]/ t' (1) `. ; 6%/.(0 &+>..# <+% ) 0 `' () 9Z. ;

#+&" #+ 03 67 89 30. ( +*) 0 +* 0 6. $ (1) `. V %/ +.> * +* A+ ƒ n WU.@ ; 6+*. @dw V A+%. k:) ]/ #% 0 g!@ +' k X @dw. +* @1 $ #% +' +* <+' @ 0 & A+/ +' #%. (N)) W% Y +' k 0 dg. % +..0 6U PQ% 0 +*.+ $ C D&7E () 1+ (3 ) IE 0@3 & $ H*3 (G3 () &@3

31.... 6. $ 0 @ d R1 %/ > A+%. 0 +*,1 A 0 g.@. $dg. A. @d: A+%. +* A+ 0 +* ). 1 S+.*.. ]/ ; 0. ). $6.]/ ). 3 0 6. $ +* H %/..0 PQ% 0 +* %. u!%& @. +* (Q '.X 0 ; @θ +' k N. : +* n WU.* H +* A+.+ 60 : +* A+ PQ% #% +' +* @.0 Pp`.U ; $6.]/ ). 13.. : k +*.@ -1 %#0 e +' k 0 %&6 dg. % 0 s' @ @n 3 : +* PQ% #% [-3-1] ). +' PQ% #% +' +* -1 +' k.0# &: S+.*!; $6.]/ #6 A.+ 60 <+' : +* A+ A+%!0 +* 0.0 PQ% 3 : +* ). 1 0 6. $ +* A+ H %/.@ %. $dg. A. @d:.' ).d 0 +* (Q '.X 0 dg. ). 31 %/ > A+'A+/. : +*..0 PQ% @. +*. @d: A+%#0. : +* A+ 6. $ 0 @ d R1.U ; $6.]/ 90 ). 11 e' @. $dg. A k +* 0 6. $ : +* A+ n WU.@.. %U H.+ 60 <+' * : +* A+ PQ% #%!+' N) jd+>' ^%&d#6. : 6+*!> %. ^%&d#6 6 %e 6^%&d#6 A+ $. N + @. 0 0 `'.%&6 90 #. ; : +* 6 0 @N $' <+% `'.@..0 9#1U A+/ +' $dg. Pp`. $1!%/ +* 6 $* &+> B 9Z.. PQ% @&+ $. 90 6 &+> V. $ 90 6 t' +* H $ 90 6 t' ().@ i %/

#+&" #+ 03 67 89 3. +* H $ 6 0 6. $ () 9Z +' A+..@ 10 jd+>' $ >..X -0/8 +' Z+.* +' k. 6... +Y @X. 1. θ 0.. $ 6 > + 'S+.* H> e%. +^ ) >. %/. $ 6 t'.#.+ 60. 9Z @X. ' +' 0 < θ 3.. $ 0 6. $ () 9Z +' k. 0 6. A+. $ 0 6 0..@ jd+>' $ > 0.. X 1/ 0@$ # +(!&" #$" N () 1+ O3" 3 7E 1 + #@. %+ ^. N!6... = &+> ƒ (17/9) +* N'..N% N' A+.@ 181/3-17/9=8966/6 (181/3) %/ `. N' 9 ). `. `'!@. 0 t+'. 0 g!@00 0(10) %/ (0) +*. @ I% $' O/.@ 0/01 k. :. 0 ' *.... 6.. 1#I %e = +* @d& %/ 0 1. -Log -Likelihood

33.... 3 V'' ; 6 +* %/ 6%/. ' %e = + #@. %+^ 9) <+%!@ 11 %+ ^ 0 BIC AIC 6(U... @+Z 6.. %/ 137/9 V '' +*! + @. +#@. @. 196/8 1681/3 V'' %/ 1891/.. ` = H... % / %e = 0 0 9. A#6!@ % +*. %/ MULTILOG 0 ' )...0.N% $'. = &+>.Z+ 9 :' N000 #. 6 6^!. 6.. `.. %/ %e = 0 <+% #3& 0+ " 3 7E #3& &@3 IE 0@3 3 7E (6) 1+

#+&" #+ 03 67 89 3 A+ +'. 3. (1989) d% A&' )' H +* 1 @UZ+a n ƒu ' $ 9. 0.# )' +* 9) +' 6# 8 % 0/. ƒ 6; U 0 6. +'.@.e (6) 9Z. TU # ƒd'. +*. @ +Y ^%&d#6. TU # +*. 6.. +'!@ Ua e A 0 $* @ U 6. TU # %/. 6. 6 +' T%&6.@ % +* @d& $ ^%&d#6 @d& +*. +' m 0/ 0 6. $. +' Z' A+.6. $ +#. +'. % %/.@ % +*. P3 Q 0.. $ +*.N% @&+ $ 6; 9:' 6;. 0 +* +.%&6 d 6; 7 37!6!6 6; +' k +* 0 @ $ A+ @ * V. +' k 0 dg. + 60 @. ]/ PQ% #% $dg... X +Y k. +' B 0 dg. @d&. +/ A+ ; $g @ TY A+ b%. %e.z#1!0 +* PQ% A VZ' +. ' 0 (Q v3 A+ 9..0 6; 8).0 `' +. %. A+ 6 ; w. #% 6d%!@N $' ; 6 9Z `' W>!@&+. Ž6 B Q 0 g!@ g @.!I$ ) B ; +.0.+.+ 1,g +. @ (Q ; '.+ +* PQ%.. ]/ ; HZ e 6=. A+ ' $ '0 g &^.# #0.` 9.. W'.0 +f' 3 1. Nonmonotonic trace lines

3.......!'+0+ 6 #6...6. '. +//. %&6/ (1.. TI I / a9dx DNA #6 (.+'6T0 {. 6%! &>' v. (3.0/ ^%$. a!%&6&>' O/ ), ( +!%&6 d 6; * 6 33!9!!! 6; A #6 * : 6+* @UZ+. ) V. 0 +* +' H A+'A+/. % +' %/!v#i..%& @UZ+ * V. #'. : 6+* #' 0 +* PQ% #% * +' m + ; $.. @1 ' A+ 0 @ % 0ˆ 6; %. A+ +# $1. : 6+* A+/ @p` 0 Y.@.e * I+. dx ; 9Z $#6.0 `' +. 6 ; 3 > @d& 0 +* g $. 'Yg 0 +* H %/ $..0 @+>' * I+. dx...!. $6#6...@+6 vs+ W' W> TU (1.@AZ#aA&/ 9) 6@9Z ' (.9Z ' +{S+.* X{. A%&Q6%&+ (3.@9:9Z ' +pa.uˆ9: e' X (!18!1!116;. : +*. 19!17!1 6; 6; A+. Vd 0 @. : +*.. 1 36!8!1 +# $1.+*e ; ' 0 9#1 +*. ; ) % ; '. @ (Q 0 g$#6.0 `' +. ; %. A+ 0 +* H %/ $. Y,1.@ (Q N #0!+.@ ; : 6+* 0 0.@&AZ#...!H,0 U. &>' @ ' ( %&>' 6 ' (1 6@. v '. ` ( 1& W+. ci' (3 u:

#+&" #+ 03 67 89 36 d jd+>'.z#1!: 6+* #' 3! ;. e' Nf%.0 `' +. ; %: %. A+ +# $1.%. A+.@. 6 6 ;.,Z 6 9Z B * ; A+. 0 +* 'Pp`!l 3. $ : 6+* 0 N'.@ %#0 > 0 +* g 6 %d.@...0+6%00#6.0 A+ 6P.!0' (1.0 6{U.!96 (.. +.!0' $% (3.09#:' U `. 10 ' 80 A.!9' (. + S+ 6; %.!.. $ +* 9:' <+% 0 g$#6 $ 6 Q A+'e 0 @. `' +.@..` P : +* 6+* A+ $. n; 0 @ : 6+* A%!+* TY!9:' 9) <+% `' A+.0.+ S#0 ; 0 6; @N0 '. ) % @X. : 6+* g. 0 @ $ ` O/ 6; % + v3 A+ 0. %d.+ +* 1 $ g. A+ 0 @ A..0 6 > $ 9+Y. g.. V : 6+* ; g. $g @+.: $g $.! A+.. 'q' e )1 $ 6 O/ 0 6+* 6; $. +` N ; g 8 % 6= ;.@& VI1 $.. +*!$ 90. 0.. $ 67/ 6%+.. 6 >. +Y j%d& @X. +' 1. θ 0 $ 6 w0 0 @ 0ˆ TY) @ ^+. m % θ = 1 0p $!+* H A+ b(@ 10 jd+>' 6+'... +0 A+% +' k A+ +6. % +* @d& %/. @X. N) ' * HX. %/ W' 6 6 6.@. @X. ' 0 9:' <+%!,1.@ A+/ & +*

37.... %#0 +' 6.!%/ @d&!+* +' %#0 6+' 0 @ I% $' () 9Z `'.@ N) A+.. $ 90 6 +* Vd @. 6]/ 6!N) 9X g +*!$ 90. N) + 6+' 0 @N $'.0. %/ @d& % @X. +' B, 6 % j%d& 6 $* %/ N) ' * 6+' $ 6.. 0 6. $ = U. 67/ 6%+.0.. %e = +* @d& %/ @&+ 0.. +* 6%/.+ ' A+ 9.!@ +* = = 6(U.d#0 v3 A+ 6.. = A '. 0 = (U.N% 0 6= # I $' e A+'e 0 @ #6 +6@+.: ; 6%/. = 6 # 6 +!.0 6%/..(007! 1 $'+) 6. X nj' @:'. 0 = (U. A!+*.0 $ (009) $Z#6 0 g$#6 ) 6; * 0 @ +* 6; 90 * t` A&'.@ / #0! A+ = 6= 6. TI PU U 6$ 9:' +* 0 0 )' (1989) d% +* #'.Z#1 A+ + b..n% +* 6; 9#%.0 90 g : 6 1. Yutong

#+&" #+ 03 67 89 38 N.(1393)!0 6!X.) b!. bhd1!$ b,!*+... A ' = @ 6 H ; 6U %. SZN' -.91-9 Z0 S+* 3+ % 3+ $!. :. 6.0-07!(18)!%' +* Y;. +'. @X. &+>.(1387) e! # % 0 $+/.. ]/ ; 6 0.+dgdg,1 ^. I Abad, F. J.; Olea, J., & Ponsoda, V. (009). The Multiple- Choice Model Some Solutions for Estimation of Parameters in the Presence of Omitted Responses. Applied Psychological Measurement, 33 (3), 00-1. Bock, R. D. (197). Estimating item parameters and latent ability when response are scored in two or more nominal categories. Psychometrika, 37 (1), 9-1. Bock, R. D. (1997). The nominal categories model. In Handbook of modern item response theory (pp. 33-9). New York: Springer. De Ayala, R. J. (1993). An introduction to polytomous Item Response Theory Models. Measurement and Evaluation in counseling Development, (). Drasgow, F.; Levine, M. V.; Tsien, S.; Williams, B., & Mead, A. D. (199). Fitting polytomous item response theory models to multiple-choice tests. Applied Psychological Measurement, 19 (), 13-166. Hambleton, R. k. (1989). Principles and selected applications of item Response Theory. In R. L. Linn (Ed.), Educational measurement (3rd ed.). (pp. 17 00). Levine, M. V. (1993). Orthogonal functions and the niteness of continuous item response theories. Unpublished manuscript. Levine, M. V., & Drasgow, F. (1983). The relation between incorrect option choice and estimated ability. Educational and Psychological Measurement, 3 (3), 67-68. Masters, G. N. (1988). An analysis of partial credit scoring. Applied Measurement in Education, 1, 79 97.

39.... Ning, R.; Waters, A. E.; Studer, C., & Baraniuk, R. G. (01). SPRITE: A Response Model for Multiple Choice Testing. ArXiv preprint arxiv: 101.08. Ostini, R. & Nering, L. (006). Polytomous Item Response Theory Models. Sage Publications. Samejima, F. (1979). A New Family of Models for the Multiple- Choice Item (No. RR-79-). Tennessee Univ Knoxville Dept of Psychology. Smilaycoff, M. P. (1989). An application of the Bock_Samejima model for multiple category scoring to test items in which distractors contains information related to latent ability. Dissertation Abstracts International, (1-A), 100, (University Microfilms No. 911783). Thissen, D. & Steinberg, L. (198). A response model for multiple- choice items. Psychometrika, 9 () 67-77. Thissen, D. & Steinberg, L. & Fitzpatrick, A. R. (1989). Multiple-Choice Models; the Distracters are also part of Item. Journal of Educational Measurement. 6 (), 161-176. Thissen, D. (1976). Information in wrong responses to the Raven Progressive Matrices. Jounal of Educational Measurement, 13 (3), 01-1. Yutong, Yin (007). Using Beaton fit inices to assess goodnessof-fit of IRT models. PHD thesis. :6 R. +*. 0.(139) 1! 0'. &!/ b,!*+ Q :. ) % / $ 6 = &+> ; 9 :' 6!.( $ @&+.39 11!(1)