Research Article New Combined Weighting Model Based on Maximizing the Difference in Evaluation Results and Its Application

Size: px
Start display at page:

Download "Research Article New Combined Weighting Model Based on Maximizing the Difference in Evaluation Results and Its Application"

Transcription

1 Hdaw Publshg Corporato Mathematcal Problems Egeerg Volume 2015, Artcle ID , 9 pages Research Artcle New Combed Weghtg Model Based o Maxmzg the Dfferece Evaluato Results ad Its Applcato B Meg ad Guota Ch Faculty of Maagemet ad Ecoomcs, Dala Uversty of Techology, Dala , Cha Correspodece should be addressed to Guota Ch; chgt@dluteduc Receved 17 May 2015; Revsed 2 August 2015; Accepted 18 August 2015 Academc Edtor: Davde La Torre Copyrght 2015 B Meg ad G Ch Ths s a ope access artcle dstrbuted uder the Creatve Commos Attrbuto Lcese, whch permts urestrcted use, dstrbuto, ad reproducto ay medum, provded the orgal work s properly cted Ths paper presets a approach for weghtg dces the comprehesve evaluato I accordace wth the prcple that the etre dfferece of varous evaluato obects s to be maxmally dfferetated, a adusted weghtg coeffcet s troduced Based o the dea of maxmzg the dfferece betwee the adusted evaluato scores of each evaluato obect ad ther mea, a obectve programmg model s establshed wth more obvous dfferetato betwee evaluato scores ad the combed weght coeffcet determed, thereby avodg cotradctory ad less dstgushable evaluato results of sgle weghtg methods The proposed model s demostrated usg 2,044 observatos The emprcal results show that the combed weghtg method has the least msudgmet probablty, as well as the least error probablty, whe compared wth four sgle weghtg methods, amely, G1, G2, varato coeffcet, ad devato methods 1 Itroducto I the process of comprehesve evaluato, a complete set of evaluato dces must be determed, wth the correspodg weght of each evaluato dex The dex weght reflects the relatve mportace of each dex, that s, the status adfuctoofeachfactortheevaluatoaddecsomakg process Hece, the determato of dex weght relates to the relablty ad valdty of rakg results of the proect For example, a eterprse credt rsk evaluato s related to ts facal factors, ofacal factors, ad macro factors I terms of large eterprses, facal codto ca reflect the repaymet ablty ad wllgess to remburse well; for ths reaso, there must be substatal weghts for the facal factors a large eterprse credt rsk evaluato Whe the facal system of small eterprses s ot stadard ad soud, facal formato caot fully reflect ther operatg codto, ad ofacal ad macro factors have greater fluece As a result, f we caot allocate the weghts of facal, ofacal, ad macro factors, the rratoal pheomeo that small eterprses wth poor credt mght have a hgh rakg ca result losses to the bak Therefore, weght determato methods have bee a maor focus comprehesve evaluato research Weghtg methods for comprehesve evaluato ca be dvded to three categores: subectve, obectve, ad combed A subectve weghtg method s a meas whereby decso makers obta dex weghts o the bass of ther ow experece ad the emphass that they subectvely place o each dex For ths reaso, the dex weght obtaed usg subectve weghtg depeds o experts kowledge, experece, ad persoal prefereces, wth o cosderato for the characterstcs ad regulartes of actual sample data [1] Subectve weghtg models clude, for example, the aalytc herarchy process (AHP) [2, 3], aalytc etwork process (ANP) [4, 5], ad Delph method [6] I cotrast, a obectve weghtg method s a meas whereby the dex weght s determed usg obectve formato regardg each dex Hece, the dex weght obtaed usg ths method does ot volve subectve opos of decso makers Obectve weghtg models clude, for example, themeaweght[7],goalprogrammg[8,9],etropy[10] stadard devato (SD) [11], crtera mportace through tercrtera correlato (CRITIC) [12], ad preferece selecto dex (PSI) [13] methods Though a obectve weghtg method provdes weghts accordg to the actual sample data, t s easly subect to the fluece of sample data Moreover, dfferet obectve

2 2 Mathematcal Problems Egeerg weghtg methods ted to yeld dfferet results Therefore, may scholars have proposed combed weghtg methods that cosder the advatages ad dsadvatages of both subectve ad obectve weghtg A combed weghtg model has the advatage of tegratg the beefts from both subectve ad obectve weghtg models ad mtgatg lmtatos of sgle weghtg models [14, 15] Su ad Bao tegrated the rough set weghtg method ad AHP model based o varace maxmzato theory to mprove the tradtoal combato weghts determato method ad made the weghts determed more reasoably ad more helpful supportg decso makg [16] L ad Ch proposed a combed weghtg model that tegrates the evaluato values from sgle evaluato methods by maxmzg the devato of sgle evaluato values [17] Although exstg research has made great progress, there are stll drawbacks Frst, there s usually radomess the method selecto for the determato of obectve ad subectveweghtsmeawhle,themethodforthecoeffcet ofobectveadsubectveweghtssotappropratesecod, a reasoable test s lackg to verfy the ratoalty of a combed weghtg method Ths paper proposes a combed weghtg method based o dfferece maxmzato Dfferet evaluato scores for the same obect are obtaed usg dfferet weghtg methods Accordg to the prcple that the etre dfferece of dfferet evaluato obects must be maxmally dfferetated, a adusted weghtg coeffcet s troduced Based o the dea of maxmzg the dfferece betwee the adusted evaluato scores of each evaluato obect ad ther mea, a obectve programmg model s establshed wth more obvous dfferetato betwee evaluato scores guarateed ad the combed weght coeffcet determed At the same tme, wth 2,044 small prvate busesses from a Chese govermet-owed commercal bak as emprcal samples, a hgher dfferetato accuracy of the combed weghtg method compared wth four kds of sgle weghtg methods, amely, G1, G2, varato coeffcet, ad devato methods, s esured by usg msudgmet probablty (MP) ad error probablty (EP) to test evaluato results from the use of dfferet weghtg methods The rest of the paper s structured as follows Secto 2 troduces the prelmary models Secto 3 dscusses the proposed model Secto 4 presets the data ad the emprcal results Coclusos are gve Secto 5 2 Prelmary Models 21 Data Stadardzato The purpose of dex data stadardzato s to trasform the dex data to [0, 1] to elmate the cosstecy of uts ad dmesos There are four types of dexes: postve, egatve, terval, ad qualtatve Postve dces are those for whch greater values are better, such as X 4,1 Net come, egatve dces are those for whch smaller values are better, such as X 3,1 Lqudty rato, ad terval dces are those for whch the values are reasoable oly whe they le partcular tervals, such as X 1,2 Age Let x deotethestadardscoreoftheth sample o the th dex Let V deote the orgal data of the th sample o the th dex s the total umber of dces ad m s the total umber of samples The stadardzato equatos of the postve ad egatve dces are show as (1) ad (2), respectvely [18] Cosder the followg: x = x = V m 1 (V ) max 1 (V ) m 1 (V ), (1) max 1 (V ) V max 1 (V ) m 1 (V ) (2) Equato (1) s the rato of the devato betwee the dex orgal data V ad the mmum value m(v ) to the rage max(v ) m(v ) It dcates that the closer the dex of the orgal data V stothemaxmumvaluemax(v ),the greater the stadardzed value x wll be The two equatos have smlar meags Equato (2) dcates that the closer the dex of the orgal data V s to the mmum value m(v ), the greater the stadardzed value x wll be Let q 1 ad q 2 be the left ad rght boudares of the deal terval, respectvely The stadardzato of the terval factorssshowasfollows[18]equato(3)dcatesthata dex value wll be gve oe pot f t falls the optmal rage [q 1,q 2 ] Greater devato from ths terval leads to lower x : q 1 V 1 max (q 1 m 1 (V ),max 1 (V ) q 2 ), V <q 1 (a) { x = V q 2 1 max (q 1 m 1 (V ),max 1 (V ) q 2 ), V >q 2 (b) { { 1, q 1 V q 2 (c) (3) For all qualtatve dces, we establsh a gradg stadard sutable for small prvate busesses Note that the data of qualtatve dces fall [0, 1] after stadardzato, dcatg that we eed ot ormalze them through (1) (3) 22 Sgle Weghtg Models 221 Subectve Weghtg Model: G1 G1 reflects the mportace of dces by ther sequetal order After the order s

3 Mathematcal Problems Egeerg 3 determed, ratoal weghts are assged based o comparg the adacet dces Therefore, the relatve mportace of ay two adacet dces s certa, assurg that the mportace correspods to the weght The steps of G1 are as follows Step 1 Experts specfy the sequece order of dces Step 2 Defe as the G1 weght of the th dex ad as the total umber of dex Experts specfy the ratoal rato r of dces ext to each other, that s, specfyg the relatve rato of mportace betwee adacet dex x 1 ad x [19]: r = w(1) 1 (4) Step 3 Based o the ratoal rato r of (4), the weght of the th dex the etre dex system s calculated usg (5), as follows [19] also deotes the total umber of dex: =(1+ =2 k= r k ) 1 (5) Step 4 Equato (4) ca be trasformed to (6) Based o weght of (5), the ( 1)th,( 2)th,,3th,2th,1st dex s weghts are calculated usg the followg: 1 =r (6) Note that =1 w(1) =1; hece the ormalzato of s ot ecessary =1 w(1) =1sproved as follows The symbolc meags (7) (10) are the same as (4) (6) Equato (6) ca be terated to obta the followg: =r (7) Equato (7) s substtuted to (6) to obta the followg: 1 =r r (8) Smlarly, terato cotues utl 1 cabeexpressed by, show as follows: 1 =r =r r =r r +1 r = I (9), each 1 that =r r +1 r +2 r w(1) = k=2 = k= r k (9) ca be expressed by w(1),wththeresult r k + k=3 r k + + k= r k + 1 = ( k=2 r k + = ( =2 k= k=3 r k +1) r k + + k= r k +1) (10) As a result of (5), (10) clearly equals oe; hece =1 w(1) = 222 Subectve Weghtg Model: G2 The essetal role of G2 s to reflect dex mportace by dex order; a more mportat dex correspods to a greater weght We frst specfy dex order by expert experece ad fd the least mportat dex labelg x p The, experts specfy the relatve rato of mportace betwee x p ad every other dex x Let w (2) be the G2 weght of the th dex, p the relatve rato of mportace betwee all other dces x ad x p,ad the total umber of dex, wth w (2) calculated usg the followg [20]: w (2) = p =1 p (11) Equato (11) dcates that a greater weght comes wth a greater relatve rato p 223 Obectve Weghtg Model: Varato Coeffcet Let w (3) be the varato coeffcet weght of the th dex, c the varato coeffcet of the th dex, δ the stadard devato of the th dex, the total umber of dex, ad x the mea value of all samples of the th dex Thus, the varato coeffcet weght γ of the th dex s calculated usg the followg [21]: w (3) = c =1 c, (12) c = δ x (13) The, x = (1/m) m =1 x, δ = (1/m) m =1 (x x ) 2, where x s the stadard score of the th sample o the th dex, ad m s the total umber of samples Equatos (12) ad (13) dcate that a greater varato coeffcet correspods to a greater dstrbuto varato comprehesve evaluato Furthermore, the formato dscrmato capacty of the dex s stroger ad ts weght w (3) s greater 224 Obectve Weghtg Model: Devato Let w (4), x, x q,,adm be the devato weght of the th dex, the stadard score of the th sample o the th dex, the stadard score of the qth sample o the th dex, the total umber of dces, ad the total umber of samples, respectvely The,

4 4 Mathematcal Problems Egeerg the devato weght of the th dex s calculated usg the followg [22]: m w (4) =1 = m q=1 x x q =1 m =1 m q=1 x (14) x q m =1 m q=1 x x q (14) reflects the dfferece of ay two samples Greater m =1 m q=1 x x q dcates greater dfferece betwee ay two samples; hece the formato dscrmato capacty of the dex s stroger, ad ts weght s greater w (4) 3 Proposed Model 31 Stadardzato of Multple Evaluato Models Dfferet sgle weghtg models lead to varyg evaluato results Stadardzato s ecessary to establsh the comparablty of weghtg models Let y (h), w (h),adx be the score of the th obect of the hth weghtg model, the weght of the th dex of the hth weghtg model, ad the stadard score of the th dex ad the th evaluato obect, respectvely Let m be the total umber of samples ad H the total umber of weghtg models The symbolc meags of m ad H (16) (19) are the same as (15) The, the score of the hth model ad the th evaluato obect s show as y (h) = w (h) =1 x (15) Let z (h) be the stadardzed score of the hth weghtg model ad the th evaluato obect The, the stadardzed process s show as z (h) = y(h) y (h), (16) s (h) where y (h) s the mea of all evaluato scores of the hth weghtg model ad s (h) s the stadard devato of the evaluato scores of the hth weghtg model For coveece, the ormalzed evaluato result matrx s deoted as Z = [z (h) ] m H 32 Combed Weghtg Model to Maxmze the Evaluato Score Dfferece The H colum vectors z (1),z (2),,z (H) of the stadardzed matrx Z have postve dces We troduce a adusted weght coeffcet λ=(λ 1,λ 2,,λ H ) T to reflect the etre dfferece of varous evaluato obects most fully The adusted evaluato score s show as Z =λ T Z=λ 1 z (1) +λ 2 z (2) + +λ H z (H) (17) Based o the prcple of reflectg the etre dfferece of dfferet evaluato obects most fully, the varace of the evaluato scores adusted by (17) must be as large as possble The adusted varace of the evaluato scores s show as m s 2 z = 1 (z m 1 z ) 2 =1 = (λt (Z) T Zλ) m 1 m m 1 (z ) 2 (18) Amog these, s 2 z s the adusted varace of the evaluato scores, whle z s the th adusted evaluato score, ad z s the mea of the adusted evaluato scores z (1),z (2),,z (H) are stadardzed values Combed wth the rght sde of (18) z =0, ths leads to the followg: (m 1) s 2 z =λt (Z) T Zλ (19) Matrx (Z) T Z s the covarace matrx Accordg to the prcple of reflectg the etre dfferece of dfferet evaluato obects to the maxmum, solvg for λ trasforms the problem to a programmg problem, as show max st λ T (Z) T Zλ λ T λ=1 (20) The ecoomc sgfcace of (17) (20) les the troducto of the adusted weghtg coeffcet λ = (λ 1,λ 2,,λ H ) T to satsfy the prcple of reflectg the etre dfferece of dfferet evaluato obects to be the maxmum A obectve programmg model s establshed to calculate the combed weght coeffcets of the dces based o the dea of maxmzg the dfferece betwee the adusted evaluato scores of each evaluato obect ad ther mea Accordg to [23], the optmum soluto of (20) s the characterstc vector correspodg to the largest characterstc root of the covarace matrx (Z) T Z The ormalzed characterstc vector ca lead to weght vector λ = (λ 1,λ 2,,λ H ) T The calculato process s to calculate the (Z) T Z characterstc roots of equato λe (Z) T Z = 0 to obta the greatest characterstc root λ max,toestablsh equato (λ max E (Z) T Z)X = 0, adtosolvethsequato to obta the characterstc vector correspodg to the greater characterstc root of the covarace matrx (Z) T Z Adusted weght vector λ=(λ 1,λ 2,,λ H ) T s obtaed by ormalzg the characterstc vector Note that ths paper lets H have the value of four as a result of the fact that there are four sgle weghtg models Secto 22 Let w,, w (2), w (3),adw (4) be the combed, G1, G2, varace coeffcet, ad devato weghts, respectvely The, the combed weght w ca be expressed as w =λ 1 +λ 2 w (2) +λ 3 w (3) +λ 4 w (4) (21) 33 The Accuracy Test The accuracy of the evaluato results for each weghtg model s tested usg the recever operatg characterstc (ROC) curve ROC requres two dces, MP (msudgmet probablty), the probablty of reectg a good sample as a bad sample by msudgmet, ad EP (error probablty), the probablty of acceptg a bad sample as a good sample by msudgmet I the case

5 Mathematcal Problems Egeerg 5 of measurg a credt evaluato model, there are default samples ad odefault samples the sample set; hece each weghtg model ca dscrmate a sample as ether default or odefault Greater MP ad EP dcate that the model has less dscrmato accuracy, whle lower MP ad EP dcate that the model has greater dscrmato accuracy 4 Emprcal Study 41 Samples ad Data Source Based o avalable dces from a Chese govermet-owed commercal bak, ths paper selects 21 dces of small prvate busesses, cludg sx feature layers, X 1 Basc formato, X 2 Guaratee ad ot guaratee, X 3 Capacty of repaymet, X 4 Capacty of proftablty, X 5 Capacty of operato, ad X 6 Macro evromet, as show Table 1 Data are collected from a Chese govermet-owed commercal bak that deals wth 2,044 small prvate busesses from 30 provces [24] The 2,044 small prvate busesses cosst of 348 default small prvate busesses ad 1,696 odefault small prvate busesses Moreover, we ca compute that the default small prvate busesses accout for oly 1703% of the total sample, wth the odefault small prvate busesses accoutg for 8297% of the total sample The samples are dvded to two groups, expermetal ad test Each group has 1,022 small prvate busesses, cosstg of 174 default ad 848 odefault samples Accordg to the type Colum 4 of Table 1, substtute the orgal data of postve dces V, egatve dces V, ad terval dces V to (1), (2), ad (3), respectvely, to obta the stadard scores of dces x Thescorgstadard of qualtatve dces ca be obtaed usg ratoal aalyss, as show Colums 2 through 6 of Table 2 Accordg to the dex type Colum 4 of Table 1, the stadard scores of qualtatve dces ca be obtaed based o the scorg crtera of the qualtatve dces Table 2 42 Calculato of Fve Types of Weght 421 Calculato of G1 Weght Through tervews wth may customer maagers from a Chese govermetowed commercal bak, the order ratoal rato r betwee two adacet dces was determed, as show Colum 4 of Table 3 Substtutg the order ratoal rato r from Colum 4 of Table 3 to (5), the G1 weght of the last dex X 6,3 Idustry cycle dex = s obtaed, as show the last row of Colum 5 of Table 3 Through (6), the other 20 dces G1 weghts are obtaed, as show Colum 5 of Table Calculato of G2 Weght w (2) Through tervews wth may customer maagers from a Chese govermetowed commercal bak, we ca determe the least mportat dex of 21 dces X 6,2 GDP growth rate ad, at the same tme, the mportat degree rato p of the other 20 dces to the dex X 6,2 GDPgrowthrate, asshow Colum 6 of Table 3 The, substtutg the mportace degree rato p to (11), the G2 weght w (2) s obtaed, as showcolum7oftable X 1 X 3 X 5 X 7 X 9 X 11 X 13 X 15 X 17 X 19 X 21 G1 model G2 model Varato coeffcet Devato model Combed weghtg model Fgure 1: Results of fve kds of weghtg method 423 Calculato of Varato Coeffcet Weght w (3) The mea x ad the stadard devato δ of each dex ca be obtaed from the stadardzed score x of all samples of each dex The varato coeffcet of each dex c,show Colum 8 of Table 3, s obtaed by substtutg x ad δ to (13) The, thevarato coeffcet weght w (3),show Colum 9 of Table 3, s obtaed by substtutg the varato coeffcet c to (12) 424 Calculato of Devato Weght w (4) The devato weghts, show Table 3, Colum 10, are obtaed by substtutg the stadardzed score x of all samples of each dex to (14) 425 Calculato of Combed Weght w The evaluato scores of the four kds of sgle weghtg methods are obtaed by substtutg the G1 weght from Colum 5, G2 weght w (2) from Colum 7, varato coeffcet weght w (3) from Colum 9, devato weght w (4) from Colum 10 of Table 3, ad the stadard score x of all samples of each dex to (15) separately The stadard matrx Z s obtaed by puttg the evaluato scores of four kds of sgle weghtg methods to (16) The, we calculate covarace matrx (Z) T Z The maxmum egevalue of (Z) T Z s λ max = , ad the correspodg egevector s ( 03682, 04068, 06332, 05458) Last, weobtathe weght coeffcets λ 1 = 0201, λ 2 = 0105, λ 3 = 0327, ad λ 4 = 0367 from egevector ormalzato The combed weght w, show Table 3, Colum 11, s obtaed by substtutg λ 1 = 0201, λ 2 = 0105, λ 3 = 0327, λ 4 = 0367,G1weght from Colum 5, G2 weght w (2) from Colum 7, varato coeffcet weght w (3) from Colum 9, ad devato weght w (4) from Colum 10 of Table 3 to (21) Results of the fve kds of weghtg method are show Fgure 1 The results of combg weghts demostrate that the weght of X 4,2 Operatg come s greatest, exceedg 01 The weghts of X 2,2 Stregth of the guarator ad X 1,5 Number of labor force are ad 00701, rakg umber 2 ad umber 3, respectvely These three dces have a more mportat fluece o the credt evaluato of

6 6 Mathematcal Problems Egeerg Table 1: Idex system for small prvate busesses (1) Number (2) Feature layer (3) Idces (4) Type of dex 1 X 1,1 Educatoal backgroud Qualtatve 2 X 1,2 Age Iterval 3 X X 1 Basc formato 1,3 Years for a busess lcese Qualtatve 4 X 1,4 Owed place of busess or ot Qualtatve 5 X 1,5 Number of labor force Postve 6 X 1,6 Famly expedture Negatve 7 X 2,1 Geder of guarator Qualtatve 8 X X 2 Guaratee ad ot guaratee 2,2 Stregth of the guarator Postve 9 X 2,3 Martal status of guarator Qualtatve 10 X 2,4 Credt status of ot guarator Qualtatve 11 X X 3 Capacty of repaymet 3,1 Lqudty rato Postve 12 X 3,2 Asset-lablty rato Negatve 13 X 4,1 Net come Postve 14 X 4 Capacty of proftablty X 4,2 Operatg come Postve 15 X 4,3 Average tax each moth Postve 16 X 5,1 Accouts recevable turover Postve 17 X 5 Capacty of operato X 5,2 Ivetory turover Postve 18 X 5,3 Operato tme Qualtatve 19 X 6,1 Per capta savgs balace Postve 20 X 6 Macro evromet X 6,2 GDP growth rate Postve 21 X 6,3 Idustry cycle dex Iterval (1) Number (2) Feature layer (3) Idces Table 2: The scorg crtera of qualtatve dces (4) Optos umber (5) Optos (6) Scorg 1 1 Udergraduate ad above Juor college 08 3 X 1 Basc formato X 1,1 Educatoal backgroud 3 Hgh school ad techcal secodary school Juor hgh school Prmary school Other Eght years or more Fve years or more ad less tha eght years X 5 Capacty of operato X 5,3 Operato tme 3 Two years or more ad less tha fve years Less tha two years Mssg Data 0 small prvate busesses I cotrast, the three dces X 1,1 Educatoal backgroud, X 2,1 Geder of guarator, ad X 3,1 Lqudty rato have weghts smaller tha 003, ad they have less mportat fluece o credt evaluato of small prvate busesses 43 Accuracy Test of the Fve Kds of Weghtg Method To test the accuracy of the fve kds of weghtg method, we used the remag 1,022 small prvate busesses as the test sample There are 174 default samples ad 848 odefault samples The results of MP ad EP ca be obtaed usg the ROC curve The accuracy of weghtg results ca be estmatedbycompargthempadepofthedfferet kds of weghtg method I ths way, we ca evaluate the advatages ad dsadvatages of the dfferet weghtg methods as well The results of MP ad EP based o the dfferet kds of weghtg method are show Fgure 2

7 Mathematcal Problems Egeerg 7 Table 3: Weghts of dfferet types of weghtg method 1 (4) Order (6) Importace (8) (9) Varato (10) (11) (5) G1 (7) G2 (1) Number (2) Feature layer (3) Idces ratoal weght degree rato p weght w (2) Varato coeffcet Devato Combed rato r of G1 of G2 coeffcet c weght w (3) weght w (4) weght w X 1,1 Educato backgroud X 1,2 Age X 1 Basc X 1,3 Years for a busess lcese formato X 1,4 Owed place of busess or ot X 1,5 Number of labor force X 1,6 Famly expedture X 2,1 Geder of guarator X 2 Guaratee ad X 2,2 Stregth of the guarator ot guaratee X 2,3 Martal status of guarator X 2,4 Credt status of ot guarator X 3 Capacty of X 3,1 Lqudty rato repaymet X 3,2 Asset-lablty rato X X Capacty of 4,1 Net come X proftablty 4,2 Operatg come X 4,3 Average tax each moth X X Capacty of 5,1 Accouts recevable turover X operato 5,2 Ivetory turover X 5,3 Operato tme X X Macro 6,1 Per capta savgs balace X evromet 6,2 GDP growth rate X 6,3 Idustry cycle dex

8 8 Mathematcal Problems Egeerg G1 model G2 model Varato coeffcet model Devato model Combed weghtg model MP EP Fgure 2: MP ad EP of the dfferet kds of weghtg models Fgure 2 demostrates that of the fve kds of weghtg method, the combed weghtg method has the smallest msudgmet probablty as well as the smallest error probablty, wth G2 havg the hghest MP ad EP The obectve weghtg models, varato coeffcet ad devato, have smaller MP ad EP tha the subectve weghtg models G1 ad G2 5 Coclusos I a comprehesve evaluato, the dex weght reflects the relatve mportace of each dex I other words, t reflects the status ad fucto of each factor the evaluato ad decso-makg process Hece, the determato of dex weght relates to the relablty ad valdty of rakg results of the proect It s for ths reaso that weght determato methods have bee a maor focus comprehesve evaluato research To ths ed, may mathematcal models have bee explored as decso support methods Ths paper proposed a combed weghtg method based o dfferece maxmzato Dfferet evaluato scores for the same obect are obtaed usg dfferet weghtg methods A adusted weghtg coeffcet was troduced accordace wth the prcple that the etre dfferece of dfferetevaluatoobectsstobemaxmallydfferetated A obectve programmg model was establshed wth more obvous dfferetato betwee evaluato scores guarateed ad the combed weght coeffcet determed Our model s based o the dea of maxmzg the dfferece betwee the adusted evaluato scores of each evaluato obect ad ther mea The proposed model s demostrated usg 2,044 observatos The emprcal results show that the combed weghtg method has the smallest msudgmet probablty, as well as the smallest error probablty, whe compared wth four kds of sgle weghtg methods, G1, G2, varato coeffcet, ad devato methods The research cotrbuto theory was as follows A adusted weghtg coeffcet was troduced accordace wth the prcple of reflectg the etre dfferece of dfferet evaluato obects to the maxmum A obectve programmg model was establshed to calculate the combed weght coeffcets of the dces, based o the dea of maxmzg the dfferece betwee the adusted evaluato scores of each evaluato obect ad ther mea Therefore, our model avods the cotradctory ad less dstgushable evaluato results that are typcal sgle weghtg methods Coflct of Iterests The authors declare that there s o coflct of terests regardg the publcato of the paper Ackowledgmets ThsresearchssupportedbytheNatoalNaturalScece Foudato of Cha (os , , ad ), Bakg Iformato Techology Rsk Maagemet Proect of Cha Bakg Regulatory Commsso (CBRC) (o ), Scece ad Techology Research Proect of Mstry of Educato of Cha (o ), the Bak of Dala as credt ratg ad loa prcg systems for Small busess (o ), ad Credt Rsks Evaluato ad Loa PrcgForPettyLoaFudedfortheHeadOffceofPost Savgs Bak of Cha (o ) The authors thak the orgazatos metoed above Refereces [1] T L Saaty, Measurg the fuzzess of sets, Joural of Cyberetcs,vol4,o4,pp53 61,1974 [2] W N P, Suppler evaluato usg AHP ad TOPSIS, Joural of Scece ad Egeerg Techology,vol1,pp75 83,2005 [3] W-N P ad C Low, Suppler evaluato ad selecto va Taguch loss fuctos ad a AHP, Iteratoal Joural of Advaced Maufacturg Techology, vol27,o5-6,pp , 2006 [4]RVRao, Machabltyevaluatoofworkmateralsusg a combed multple attrbute decso-makg method, The Iteratoal Joural of Advaced Maufacturg Techology, vol 28, o 3-4, pp , 2006 [5] H-J Shyur, COTS evaluato usg modfed TOPSIS ad ANP, Appled Mathematcs ad Computato, vol 177, o1,pp , 2006 [6] B Brow, Delph Process: A Methodology Usg for the Elctato of Opos of Experts, o 9, RAND Corporato, Sata Moca, Calf, USA, 1987 [7] H Deg, C-H Yeh, ad R J Wlls, Iter-compay comparso usg modfed TOPSIS wth obectve weghts, Computers ad Operatos Research,vol27,o10,pp ,2000 [8] F García, F Guarro, ad I Moya, A goal programmg approach to estmatg performace weghts for rakg frms, Computers & Operatos Research,vol37,o9,pp , 2010 [9] F García, V Gméez, ad F Guarro, Credt rsk maagemet: a multcrtera approach to assess credtworthess, Mathematcal ad Computer Modellg, vol57,o7-8,pp , 2013 [10] A Shaa ad O Savadogo, A methodologcal cocept for materal selecto of hghly sestve compoets based o multple crtera decso aalyss, Expert Systems wth Applcatos,vol36,o2,pp ,2009 [11] D Dakoulak, G Mavrotsa, ad L Papayaaks, Determg obectve weghts multple crtera problems: the crtc method, Computers ad Operatos Research,vol22,o7,pp , 1995 [12] K Maya ad M G Bhatt, A selecto of materal usg a ovel type decso-makg method: preferece selecto dex

9 Mathematcal Problems Egeerg 9 method, Materals ad Desg, vol 31, o 4, pp , 2010 [13] CLHwagadKYoo,Multple Attrbute Decso Makg Methods ad Applcatos, Sprger, Berl, Germay, 1981 [14] K Zbkowsk, Usg volume weghted support vector maches wth walk forward testg ad feature selecto for the purpose of creatg stock tradg strategy, Expert Systems wth Applcatos,vol42,o4,pp ,2015 [15] B Aou, C Colapto, ad D La Torre, Facal portfolo maagemet through the goal programmg model: curret state-of-the-art, Europea Joural of Operatoal Research,vol 234, o 2, pp , 2014 [16] Y Su ad X Z Bao, A ew combato weghtg method ad ts applcato based o maxmzg devatos, Chese Joural of Maagemet Scece, vol 6, pp , 2011 [17] G L ad G T Ch, The comprehesve evaluato of all-roud huma developmet based o level dfferet maxmzato, Cha Soft Scece Magaze,vol9,pp ,2009 [18] ZL,GCh,adZXu, Measuremetmodelofproectrsksof commercal baks based o combato weghtg, Idustral Egeerg ad Egeerg Maagemet, vol6,pp , 2013 [19] C Qa, M Zhag, Y Che, ad R Wag, A quattatve udgmet method for safety admttace of facltes chemcal dustral parks based o g1-varato coeffcet method, Proceda Egeerg,vol84,pp ,2014 [20] K Khall-Damgha ad S Sad-Nezhad, A decso support system for fuzzy mult-obectve mult-perod sustaable proect selecto, Computers & Idustral Egeerg, vol64, o 4, pp , 2013 [21] Y Gao, Z Da, ad W Lu, Modelg dyamc trust ad rsk evaluato based o hgh-order momets, Mathematcal Problems Egeerg, vol2015,artcleid789820,9pages, 2015 [22] PWag,YL,Y-HWag,adZ-QZhu, Aewmethodbased o topss ad respose surface method for MCDM problems wth terval umbers, Mathematcal Problems Egeerg, vol 2015, Artcle ID , 11 pages, 2015 [23] M-RGhasem,JIgatus,adAEmrouzead, Ab-obectve weghted model for mprovg the dscrmato power MCDEA, Europea Joural of Operatoal Research, vol 233, o 3, pp , 2014 [24] Postal Savgs Bak of Cha, The Busess Credt Ratg Table of Postal Savgs Bak of Cha, The busess credt ratg table of Postal Savgs Bak of Cha, 2009

10 Advaces Operatos Research Hdaw Publshg Corporato Advaces Decso Sceces Hdaw Publshg Corporato Joural of Appled Mathematcs Algebra Hdaw Publshg Corporato Hdaw Publshg Corporato Joural of Probablty ad Statstcs The Scetfc World Joural Hdaw Publshg Corporato Hdaw Publshg Corporato Iteratoal Joural of Dfferetal Equatos Hdaw Publshg Corporato Submt your mauscrpts at Iteratoal Joural of Advaces Combatorcs Hdaw Publshg Corporato Mathematcal Physcs Hdaw Publshg Corporato Joural of Complex Aalyss Hdaw Publshg Corporato Iteratoal Joural of Mathematcs ad Mathematcal Sceces Mathematcal Problems Egeerg Joural of Mathematcs Hdaw Publshg Corporato Hdaw Publshg Corporato Hdaw Publshg Corporato Dscrete Mathematcs Joural of Hdaw Publshg Corporato Dscrete Dyamcs Nature ad Socety Joural of Fucto Spaces Hdaw Publshg Corporato Abstract ad Appled Aalyss Hdaw Publshg Corporato Hdaw Publshg Corporato Iteratoal Joural of Joural of Stochastc Aalyss Optmzato Hdaw Publshg Corporato Hdaw Publshg Corporato

Functions of Random Variables

Functions of Random Variables Fuctos of Radom Varables Chapter Fve Fuctos of Radom Varables 5. Itroducto A geeral egeerg aalyss model s show Fg. 5.. The model output (respose) cotas the performaces of a system or product, such as weght,

More information

Research Article A New Derivation and Recursive Algorithm Based on Wronskian Matrix for Vandermonde Inverse Matrix

Research Article A New Derivation and Recursive Algorithm Based on Wronskian Matrix for Vandermonde Inverse Matrix Mathematcal Problems Egeerg Volume 05 Artcle ID 94757 7 pages http://ddoorg/055/05/94757 Research Artcle A New Dervato ad Recursve Algorthm Based o Wroska Matr for Vadermode Iverse Matr Qu Zhou Xja Zhag

More information

Solving Constrained Flow-Shop Scheduling. Problems with Three Machines

Solving Constrained Flow-Shop Scheduling. Problems with Three Machines It J Cotemp Math Sceces, Vol 5, 2010, o 19, 921-929 Solvg Costraed Flow-Shop Schedulg Problems wth Three Maches P Pada ad P Rajedra Departmet of Mathematcs, School of Advaced Sceces, VIT Uversty, Vellore-632

More information

Ranking Bank Branches with Interval Data By IAHP and TOPSIS

Ranking Bank Branches with Interval Data By IAHP and TOPSIS Rag Ba Braches wth terval Data By HP ad TPSS Tayebeh Rezaetazaa Departmet of Mathematcs, slamc zad Uversty, Badar bbas Brach, Badar bbas, ra Mahaz Barhordarahmad Departmet of Mathematcs, slamc zad Uversty,

More information

A New Method for Decision Making Based on Soft Matrix Theory

A New Method for Decision Making Based on Soft Matrix Theory Joural of Scetfc esearch & eports 3(5): 0-7, 04; rtcle o. JS.04.5.00 SCIENCEDOMIN teratoal www.scecedoma.org New Method for Decso Mag Based o Soft Matrx Theory Zhmg Zhag * College of Mathematcs ad Computer

More information

Combining Gray Relational Analysis with Cumulative Prospect Theory for Multi-sensor Target Recognition

Combining Gray Relational Analysis with Cumulative Prospect Theory for Multi-sensor Target Recognition Sesors & Trasducers, Vol 172, Issue 6, Jue 2014, pp 39-44 Sesors & Trasducers 2014 by IFSA Publshg, S L http://wwwsesorsportalcom Combg Gray Relatoal Aalyss wth Cumulatve Prospect Theory for Mult-sesor

More information

Research Article A New Iterative Method for Common Fixed Points of a Finite Family of Nonexpansive Mappings

Research Article A New Iterative Method for Common Fixed Points of a Finite Family of Nonexpansive Mappings Hdaw Publshg Corporato Iteratoal Joural of Mathematcs ad Mathematcal Sceces Volume 009, Artcle ID 391839, 9 pages do:10.1155/009/391839 Research Artcle A New Iteratve Method for Commo Fxed Pots of a Fte

More information

Bootstrap Method for Testing of Equality of Several Coefficients of Variation

Bootstrap Method for Testing of Equality of Several Coefficients of Variation Cloud Publcatos Iteratoal Joural of Advaced Mathematcs ad Statstcs Volume, pp. -6, Artcle ID Sc- Research Artcle Ope Access Bootstrap Method for Testg of Equalty of Several Coeffcets of Varato Dr. Navee

More information

Consistency test of martial arts competition evaluation criteria based on mathematical ahp model

Consistency test of martial arts competition evaluation criteria based on mathematical ahp model ISSN : 0974-7435 Volume 8 Issue 2 BoTechology BoTechology A Ida Joural Cosstecy test of martal arts competto evaluato crtera based o mathematcal ahp model Hu Wag Isttute of Physcal Educato, JagSu Normal

More information

A New Family of Transformations for Lifetime Data

A New Family of Transformations for Lifetime Data Proceedgs of the World Cogress o Egeerg 4 Vol I, WCE 4, July - 4, 4, Lodo, U.K. A New Famly of Trasformatos for Lfetme Data Lakhaa Watthaacheewakul Abstract A famly of trasformatos s the oe of several

More information

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc. Research on scheme evaluation method of automation mechatronic systems

An Indian Journal FULL PAPER ABSTRACT KEYWORDS. Trade Science Inc. Research on scheme evaluation method of automation mechatronic systems [ype text] [ype text] [ype text] ISSN : 0974-7435 Volume 0 Issue 6 Boechology 204 Ida Joural FULL PPER BIJ, 0(6, 204 [927-9275] Research o scheme evaluato method of automato mechatroc systems BSRC Che

More information

Multi Objective Fuzzy Inventory Model with. Demand Dependent Unit Cost and Lead Time. Constraints A Karush Kuhn Tucker Conditions.

Multi Objective Fuzzy Inventory Model with. Demand Dependent Unit Cost and Lead Time. Constraints A Karush Kuhn Tucker Conditions. It. Joural of Math. Aalyss, Vol. 8, 204, o. 4, 87-93 HIKARI Ltd, www.m-hkar.com http://dx.do.org/0.2988/jma.204.30252 Mult Objectve Fuzzy Ivetory Model wth Demad Depedet Ut Cost ad Lead Tme Costrats A

More information

Estimation of Stress- Strength Reliability model using finite mixture of exponential distributions

Estimation of Stress- Strength Reliability model using finite mixture of exponential distributions Iteratoal Joural of Computatoal Egeerg Research Vol, 0 Issue, Estmato of Stress- Stregth Relablty model usg fte mxture of expoetal dstrbutos K.Sadhya, T.S.Umamaheswar Departmet of Mathematcs, Lal Bhadur

More information

COMPARISON OF ANALYTIC HIERARCHY PROCESS AND SOME NEW OPTIMIZATION PROCEDURES FOR RATIO SCALING

COMPARISON OF ANALYTIC HIERARCHY PROCESS AND SOME NEW OPTIMIZATION PROCEDURES FOR RATIO SCALING Please cte ths artcle as: Paweł Kazbudzk, Comparso of aalytc herarchy process ad some ew optmzato procedures for rato scalg, Scetfc Research of the Isttute of Mathematcs ad Computer Scece, 0, Volume 0,

More information

Introduction to local (nonparametric) density estimation. methods

Introduction to local (nonparametric) density estimation. methods Itroducto to local (oparametrc) desty estmato methods A slecture by Yu Lu for ECE 66 Sprg 014 1. Itroducto Ths slecture troduces two local desty estmato methods whch are Parze desty estmato ad k-earest

More information

Research on SVM Prediction Model Based on Chaos Theory

Research on SVM Prediction Model Based on Chaos Theory Advaced Scece ad Techology Letters Vol.3 (SoftTech 06, pp.59-63 http://dx.do.org/0.457/astl.06.3.3 Research o SVM Predcto Model Based o Chaos Theory Sog Lagog, Wu Hux, Zhag Zezhog 3, College of Iformato

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(7): Research Article

Journal of Chemical and Pharmaceutical Research, 2014, 6(7): Research Article Avalable ole www.jocpr.com Joural of Chemcal ad Pharmaceutcal Research, 2014, 6(7):1035-1041 Research Artcle ISSN : 0975-7384 CODEN(SA) : JCPRC5 Desg ad developmet of kowledge maagemet platform for SMEs

More information

Management Science Letters

Management Science Letters Maagemet Scece Letters 2 (202) 29 42 Cotets lsts avalable at GrowgScece Maagemet Scece Letters homepage: www.growgscece.com/msl A goal programmg method for dervg fuzzy prortes of crtera from cosstet fuzzy

More information

Unimodality Tests for Global Optimization of Single Variable Functions Using Statistical Methods

Unimodality Tests for Global Optimization of Single Variable Functions Using Statistical Methods Malaysa Umodalty Joural Tests of Mathematcal for Global Optmzato Sceces (): of 05 Sgle - 5 Varable (007) Fuctos Usg Statstcal Methods Umodalty Tests for Global Optmzato of Sgle Varable Fuctos Usg Statstcal

More information

Lecture 7. Confidence Intervals and Hypothesis Tests in the Simple CLR Model

Lecture 7. Confidence Intervals and Hypothesis Tests in the Simple CLR Model Lecture 7. Cofdece Itervals ad Hypothess Tests the Smple CLR Model I lecture 6 we troduced the Classcal Lear Regresso (CLR) model that s the radom expermet of whch the data Y,,, K, are the outcomes. The

More information

2.28 The Wall Street Journal is probably referring to the average number of cubes used per glass measured for some population that they have chosen.

2.28 The Wall Street Journal is probably referring to the average number of cubes used per glass measured for some population that they have chosen. .5 x 54.5 a. x 7. 786 7 b. The raked observatos are: 7.4, 7.5, 7.7, 7.8, 7.9, 8.0, 8.. Sce the sample sze 7 s odd, the meda s the (+)/ 4 th raked observato, or meda 7.8 c. The cosumer would more lkely

More information

Research Article Some Strong Limit Theorems for Weighted Product Sums of ρ-mixing Sequences of Random Variables

Research Article Some Strong Limit Theorems for Weighted Product Sums of ρ-mixing Sequences of Random Variables Hdaw Publshg Corporato Joural of Iequaltes ad Applcatos Volume 2009, Artcle ID 174768, 10 pages do:10.1155/2009/174768 Research Artcle Some Strog Lmt Theorems for Weghted Product Sums of ρ-mxg Sequeces

More information

A New Method for Consistency Correction of Judgment Matrix in AHP

A New Method for Consistency Correction of Judgment Matrix in AHP Ne Method for Cosstecy Correcto of Judgmet Matrx HP Hao Zhag Haa Normal UverstyHakou 5758Cha E-mal:74606560@qq.com Ygb We 2 Haa College of Softare TechologyQogha 57400Cha E-mal:W6337@63.com Gahua Yu 3

More information

Chapter 11 Systematic Sampling

Chapter 11 Systematic Sampling Chapter stematc amplg The sstematc samplg techue s operatoall more coveet tha the smple radom samplg. It also esures at the same tme that each ut has eual probablt of cluso the sample. I ths method of

More information

best estimate (mean) for X uncertainty or error in the measurement (systematic, random or statistical) best

best estimate (mean) for X uncertainty or error in the measurement (systematic, random or statistical) best Error Aalyss Preamble Wheever a measuremet s made, the result followg from that measuremet s always subject to ucertaty The ucertaty ca be reduced by makg several measuremets of the same quatty or by mprovg

More information

It is Advantageous to Make a Syllabus as Precise as Possible: Decision-Theoretic Analysis

It is Advantageous to Make a Syllabus as Precise as Possible: Decision-Theoretic Analysis Joural of Iovatve Techology ad Educato, Vol. 4, 2017, o. 1, 1-5 HIKARI Ltd, www.m-hkar.com https://do.org/10.12988/jte.2017.61146 It s Advatageous to Make a Syllabus as Precse as Possble: Decso-Theoretc

More information

Comparing Different Estimators of three Parameters for Transmuted Weibull Distribution

Comparing Different Estimators of three Parameters for Transmuted Weibull Distribution Global Joural of Pure ad Appled Mathematcs. ISSN 0973-768 Volume 3, Number 9 (207), pp. 55-528 Research Ida Publcatos http://www.rpublcato.com Comparg Dfferet Estmators of three Parameters for Trasmuted

More information

Validating Multiattribute Decision Making Methods for Supporting Group Decisions

Validating Multiattribute Decision Making Methods for Supporting Group Decisions Valdatg Multattrbute Decso Makg Methods for Supportg Group Decsos Chug-Hsg Yeh, Seor Member, IEEE Clayto School of Iformato Techology Faculty of Iformato Techology, Moash Uversty Clayto, Vctora, 3800,

More information

ESS Line Fitting

ESS Line Fitting ESS 5 014 17. Le Fttg A very commo problem data aalyss s lookg for relatoshpetwee dfferet parameters ad fttg les or surfaces to data. The smplest example s fttg a straght le ad we wll dscuss that here

More information

ANALYSIS ON THE NATURE OF THE BASIC EQUATIONS IN SYNERGETIC INTER-REPRESENTATION NETWORK

ANALYSIS ON THE NATURE OF THE BASIC EQUATIONS IN SYNERGETIC INTER-REPRESENTATION NETWORK Far East Joural of Appled Mathematcs Volume, Number, 2008, Pages Ths paper s avalable ole at http://www.pphm.com 2008 Pushpa Publshg House ANALYSIS ON THE NATURE OF THE ASI EQUATIONS IN SYNERGETI INTER-REPRESENTATION

More information

The Necessarily Efficient Point Method for Interval Molp Problems

The Necessarily Efficient Point Method for Interval Molp Problems ISS 6-69 Eglad K Joural of Iformato ad omputg Scece Vol. o. 9 pp. - The ecessarly Effcet Pot Method for Iterval Molp Problems Hassa Mshmast eh ad Marzeh Alezhad + Mathematcs Departmet versty of Ssta ad

More information

On Modified Interval Symmetric Single-Step Procedure ISS2-5D for the Simultaneous Inclusion of Polynomial Zeros

On Modified Interval Symmetric Single-Step Procedure ISS2-5D for the Simultaneous Inclusion of Polynomial Zeros It. Joural of Math. Aalyss, Vol. 7, 2013, o. 20, 983-988 HIKARI Ltd, www.m-hkar.com O Modfed Iterval Symmetrc Sgle-Step Procedure ISS2-5D for the Smultaeous Icluso of Polyomal Zeros 1 Nora Jamalud, 1 Masor

More information

MEASURES OF DISPERSION

MEASURES OF DISPERSION MEASURES OF DISPERSION Measure of Cetral Tedecy: Measures of Cetral Tedecy ad Dsperso ) Mathematcal Average: a) Arthmetc mea (A.M.) b) Geometrc mea (G.M.) c) Harmoc mea (H.M.) ) Averages of Posto: a) Meda

More information

Module 7: Probability and Statistics

Module 7: Probability and Statistics Lecture 4: Goodess of ft tests. Itroducto Module 7: Probablty ad Statstcs I the prevous two lectures, the cocepts, steps ad applcatos of Hypotheses testg were dscussed. Hypotheses testg may be used to

More information

Bayes Estimator for Exponential Distribution with Extension of Jeffery Prior Information

Bayes Estimator for Exponential Distribution with Extension of Jeffery Prior Information Malaysa Joural of Mathematcal Sceces (): 97- (9) Bayes Estmator for Expoetal Dstrbuto wth Exteso of Jeffery Pror Iformato Hadeel Salm Al-Kutub ad Noor Akma Ibrahm Isttute for Mathematcal Research, Uverst

More information

Uniform asymptotical stability of almost periodic solution of a discrete multispecies Lotka-Volterra competition system

Uniform asymptotical stability of almost periodic solution of a discrete multispecies Lotka-Volterra competition system Iteratoal Joural of Egeerg ad Advaced Research Techology (IJEART) ISSN: 2454-9290, Volume-2, Issue-1, Jauary 2016 Uform asymptotcal stablty of almost perodc soluto of a dscrete multspeces Lotka-Volterra

More information

Analysis of Variance with Weibull Data

Analysis of Variance with Weibull Data Aalyss of Varace wth Webull Data Lahaa Watthaacheewaul Abstract I statstcal data aalyss by aalyss of varace, the usual basc assumptos are that the model s addtve ad the errors are radomly, depedetly, ad

More information

Chapter 13, Part A Analysis of Variance and Experimental Design. Introduction to Analysis of Variance. Introduction to Analysis of Variance

Chapter 13, Part A Analysis of Variance and Experimental Design. Introduction to Analysis of Variance. Introduction to Analysis of Variance Chapter, Part A Aalyss of Varace ad Epermetal Desg Itroducto to Aalyss of Varace Aalyss of Varace: Testg for the Equalty of Populato Meas Multple Comparso Procedures Itroducto to Aalyss of Varace Aalyss

More information

CHAPTER VI Statistical Analysis of Experimental Data

CHAPTER VI Statistical Analysis of Experimental Data Chapter VI Statstcal Aalyss of Expermetal Data CHAPTER VI Statstcal Aalyss of Expermetal Data Measuremets do ot lead to a uque value. Ths s a result of the multtude of errors (maly radom errors) that ca

More information

Measures of Dispersion

Measures of Dispersion Chapter 8 Measures of Dsperso Defto of Measures of Dsperso (page 31) A measure of dsperso s a descrptve summary measure that helps us characterze the data set terms of how vared the observatos are from

More information

Block-Based Compact Thermal Modeling of Semiconductor Integrated Circuits

Block-Based Compact Thermal Modeling of Semiconductor Integrated Circuits Block-Based Compact hermal Modelg of Semcoductor Itegrated Crcuts Master s hess Defese Caddate: Jg Ba Commttee Members: Dr. Mg-Cheg Cheg Dr. Daqg Hou Dr. Robert Schllg July 27, 2009 Outle Itroducto Backgroud

More information

{ }{ ( )} (, ) = ( ) ( ) ( ) Chapter 14 Exercises in Sampling Theory. Exercise 1 (Simple random sampling): Solution:

{ }{ ( )} (, ) = ( ) ( ) ( ) Chapter 14 Exercises in Sampling Theory. Exercise 1 (Simple random sampling): Solution: Chapter 4 Exercses Samplg Theory Exercse (Smple radom samplg: Let there be two correlated radom varables X ad A sample of sze s draw from a populato by smple radom samplg wthout replacemet The observed

More information

Evaluation model of young basketball players physical quality and basic technique based on rbf neural network

Evaluation model of young basketball players physical quality and basic technique based on rbf neural network ISSN : 0974-7435 Volume 8 Issue 9 BoTechology BoTechology A Ida Joural Evaluato model of youg basketball players physcal qualty ad basc techque based o rbf eural etwork Guag Lu Wuha Isttute Of Physcal

More information

The Mathematical Appendix

The Mathematical Appendix The Mathematcal Appedx Defto A: If ( Λ, Ω, where ( λ λ λ whch the probablty dstrbutos,,..., Defto A. uppose that ( Λ,,..., s a expermet type, the σ-algebra o λ λ λ are defed s deoted by ( (,,...,, σ Ω.

More information

Econometric Methods. Review of Estimation

Econometric Methods. Review of Estimation Ecoometrc Methods Revew of Estmato Estmatg the populato mea Radom samplg Pot ad terval estmators Lear estmators Ubased estmators Lear Ubased Estmators (LUEs) Effcecy (mmum varace) ad Best Lear Ubased Estmators

More information

Summary of the lecture in Biostatistics

Summary of the lecture in Biostatistics Summary of the lecture Bostatstcs Probablty Desty Fucto For a cotuos radom varable, a probablty desty fucto s a fucto such that: 0 dx a b) b a dx A probablty desty fucto provdes a smple descrpto of the

More information

Lecture 3. Sampling, sampling distributions, and parameter estimation

Lecture 3. Sampling, sampling distributions, and parameter estimation Lecture 3 Samplg, samplg dstrbutos, ad parameter estmato Samplg Defto Populato s defed as the collecto of all the possble observatos of terest. The collecto of observatos we take from the populato s called

More information

An Extended TOPSIS Method for the Multiple Attribute Decision Making Problems Based on Interval Neutrosophic Set

An Extended TOPSIS Method for the Multiple Attribute Decision Making Problems Based on Interval Neutrosophic Set Neutrosophc Sets ad Systems, Vol., 0 Exteded TOPSIS Method for the Multple ttrbute Decso Makg Problems Based o Iterval Neutrosophc Set Pgpg Ch,, ad Pede Lu,,* Cha-sea Iteratoal College, Dhurak Pudt versty,

More information

Fuzzy TOPSIS Based on α Level Set for Academic Staff Selection

Fuzzy TOPSIS Based on α Level Set for Academic Staff Selection Gadg Busess ad Maagemet Joural Vol. No., 57-70, 007 Fuzzy TOPSIS Based o evel Set for Academc Staff Selecto Nazrah Raml Nor Azzah M. Yacob Faculty of Iformato Techology ad Quattatve Scece Uverst Tekolog

More information

Lecture Notes Types of economic variables

Lecture Notes Types of economic variables Lecture Notes 3 1. Types of ecoomc varables () Cotuous varable takes o a cotuum the sample space, such as all pots o a le or all real umbers Example: GDP, Polluto cocetrato, etc. () Dscrete varables fte

More information

Application of Improved Grey Correlative Method in Safety Evaluation on Fully Mechanized Mining Faces

Application of Improved Grey Correlative Method in Safety Evaluation on Fully Mechanized Mining Faces Avalable ole at www.scecedrect.com Proceda Earth ad Plaetary Scece 2 ( 2011 ) 58 63 The Secod Iteratoal Coferece o Mg Egeerg ad Metallurgcal Techology Applcato of Improved Grey Correlatve Method Safety

More information

The number of observed cases The number of parameters. ith case of the dichotomous dependent variable. the ith case of the jth parameter

The number of observed cases The number of parameters. ith case of the dichotomous dependent variable. the ith case of the jth parameter LOGISTIC REGRESSION Notato Model Logstc regresso regresses a dchotomous depedet varable o a set of depedet varables. Several methods are mplemeted for selectg the depedet varables. The followg otato s

More information

Research Article Gauss-Lobatto Formulae and Extremal Problems

Research Article Gauss-Lobatto Formulae and Extremal Problems Hdaw Publshg Corporato Joural of Iequaltes ad Applcatos Volume 2008 Artcle ID 624989 0 pages do:055/2008/624989 Research Artcle Gauss-Lobatto Formulae ad Extremal Problems wth Polyomals Aa Mara Acu ad

More information

PICTURE FUZZY CROSS-ENTROPY FOR MULTIPLE ATTRIBUTE DECISION MAKING PROBLEMS

PICTURE FUZZY CROSS-ENTROPY FOR MULTIPLE ATTRIBUTE DECISION MAKING PROBLEMS Joural of Busess Ecoomcs ad Maagemet ISSN 6-699 / eissn 2029-4433 206 Volume 7(4): 49 502 do:0.3846/6699.206.9747 PICTURE FUZZY CROSS-ENTROPY FOR MULTIPLE ATTRIBUTE DECISION MAKING PROBLEMS Guwu WEI School

More information

Distance and Similarity Measures for Intuitionistic Hesitant Fuzzy Sets

Distance and Similarity Measures for Intuitionistic Hesitant Fuzzy Sets Iteratoal Coferece o Artfcal Itellgece: Techologes ad Applcatos (ICAITA 206) Dstace ad Smlarty Measures for Itutostc Hestat Fuzzy Sets Xumg Che,2*, Jgmg L,2, L Qa ad Xade Hu School of Iformato Egeerg,

More information

Journal of Chemical and Pharmaceutical Research, 2014, 6(7): Research Article

Journal of Chemical and Pharmaceutical Research, 2014, 6(7): Research Article Avalable ole www.jocpr.com Joural of Chemcal ad Pharmaceutcal Research, 04, 6(7):4-47 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 Predcto of CNG automoble owershp by usg the combed model Ku Huag,

More information

Lecture 2 - What are component and system reliability and how it can be improved?

Lecture 2 - What are component and system reliability and how it can be improved? Lecture 2 - What are compoet ad system relablty ad how t ca be mproved? Relablty s a measure of the qualty of the product over the log ru. The cocept of relablty s a exteded tme perod over whch the expected

More information

Chapter 8. Inferences about More Than Two Population Central Values

Chapter 8. Inferences about More Than Two Population Central Values Chapter 8. Ifereces about More Tha Two Populato Cetral Values Case tudy: Effect of Tmg of the Treatmet of Port-We tas wth Lasers ) To vestgate whether treatmet at a youg age would yeld better results tha

More information

ENGI 3423 Simple Linear Regression Page 12-01

ENGI 3423 Simple Linear Regression Page 12-01 ENGI 343 mple Lear Regresso Page - mple Lear Regresso ometmes a expermet s set up where the expermeter has cotrol over the values of oe or more varables X ad measures the resultg values of aother varable

More information

Chapter Business Statistics: A First Course Fifth Edition. Learning Objectives. Correlation vs. Regression. In this chapter, you learn:

Chapter Business Statistics: A First Course Fifth Edition. Learning Objectives. Correlation vs. Regression. In this chapter, you learn: Chapter 3 3- Busess Statstcs: A Frst Course Ffth Edto Chapter 2 Correlato ad Smple Lear Regresso Busess Statstcs: A Frst Course, 5e 29 Pretce-Hall, Ic. Chap 2- Learg Objectves I ths chapter, you lear:

More information

ABOUT ONE APPROACH TO APPROXIMATION OF CONTINUOUS FUNCTION BY THREE-LAYERED NEURAL NETWORK

ABOUT ONE APPROACH TO APPROXIMATION OF CONTINUOUS FUNCTION BY THREE-LAYERED NEURAL NETWORK ABOUT ONE APPROACH TO APPROXIMATION OF CONTINUOUS FUNCTION BY THREE-LAYERED NEURAL NETWORK Ram Rzayev Cyberetc Isttute of the Natoal Scece Academy of Azerbaa Republc ramrza@yahoo.com Aygu Alasgarova Khazar

More information

On the Interval Zoro Symmetric Single Step. Procedure IZSS1-5D for the Simultaneous. Bounding of Real Polynomial Zeros

On the Interval Zoro Symmetric Single Step. Procedure IZSS1-5D for the Simultaneous. Bounding of Real Polynomial Zeros It. Joural of Math. Aalyss, Vol. 7, 2013, o. 59, 2947-2951 HIKARI Ltd, www.m-hkar.com http://dx.do.org/10.12988/ma.2013.310259 O the Iterval Zoro Symmetrc Sgle Step Procedure IZSS1-5D for the Smultaeous

More information

Solving Interval and Fuzzy Multi Objective. Linear Programming Problem. by Necessarily Efficiency Points

Solving Interval and Fuzzy Multi Objective. Linear Programming Problem. by Necessarily Efficiency Points Iteratoal Mathematcal Forum, 3, 2008, o. 3, 99-06 Solvg Iterval ad Fuzzy Mult Obectve ear Programmg Problem by Necessarly Effcecy Pots Hassa Mshmast Neh ad Marzeh Aleghad Mathematcs Departmet, Faculty

More information

Descriptive Statistics

Descriptive Statistics Page Techcal Math II Descrptve Statstcs Descrptve Statstcs Descrptve statstcs s the body of methods used to represet ad summarze sets of data. A descrpto of how a set of measuremets (for eample, people

More information

Reliability evaluation of distribution network based on improved non. sequential Monte Carlo method

Reliability evaluation of distribution network based on improved non. sequential Monte Carlo method 3rd Iteratoal Coferece o Mecatrocs, Robotcs ad Automato (ICMRA 205) Relablty evaluato of dstrbuto etwork based o mproved o sequetal Mote Carlo metod Je Zu, a, Cao L, b, Aog Tag, c Scool of Automato, Wua

More information

Part 4b Asymptotic Results for MRR2 using PRESS. Recall that the PRESS statistic is a special type of cross validation procedure (see Allen (1971))

Part 4b Asymptotic Results for MRR2 using PRESS. Recall that the PRESS statistic is a special type of cross validation procedure (see Allen (1971)) art 4b Asymptotc Results for MRR usg RESS Recall that the RESS statstc s a specal type of cross valdato procedure (see Alle (97)) partcular to the regresso problem ad volves fdg Y $,, the estmate at the

More information

Chapter 13 Student Lecture Notes 13-1

Chapter 13 Student Lecture Notes 13-1 Chapter 3 Studet Lecture Notes 3- Basc Busess Statstcs (9 th Edto) Chapter 3 Smple Lear Regresso 4 Pretce-Hall, Ic. Chap 3- Chapter Topcs Types of Regresso Models Determg the Smple Lear Regresso Equato

More information

Chapter Statistics Background of Regression Analysis

Chapter Statistics Background of Regression Analysis Chapter 06.0 Statstcs Backgroud of Regresso Aalyss After readg ths chapter, you should be able to:. revew the statstcs backgroud eeded for learg regresso, ad. kow a bref hstory of regresso. Revew of Statstcal

More information

Analysis of System Performance IN2072 Chapter 5 Analysis of Non Markov Systems

Analysis of System Performance IN2072 Chapter 5 Analysis of Non Markov Systems Char for Network Archtectures ad Servces Prof. Carle Departmet of Computer Scece U Müche Aalyss of System Performace IN2072 Chapter 5 Aalyss of No Markov Systems Dr. Alexader Kle Prof. Dr.-Ig. Georg Carle

More information

Generalized Minimum Perpendicular Distance Square Method of Estimation

Generalized Minimum Perpendicular Distance Square Method of Estimation Appled Mathematcs,, 3, 945-949 http://dx.do.org/.436/am..366 Publshed Ole December (http://.scrp.org/joural/am) Geeralzed Mmum Perpedcular Dstace Square Method of Estmato Rezaul Karm, Morshed Alam, M.

More information

Estimation of the Loss and Risk Functions of Parameter of Maxwell Distribution

Estimation of the Loss and Risk Functions of Parameter of Maxwell Distribution Scece Joural of Appled Mathematcs ad Statstcs 06; 4(4): 9- http://www.scecepublshggroup.com/j/sjams do: 0.648/j.sjams.060404. ISSN: 76-949 (Prt); ISSN: 76-95 (Ole) Estmato of the Loss ad Rsk Fuctos of

More information

A Conventional Approach for the Solution of the Fifth Order Boundary Value Problems Using Sixth Degree Spline Functions

A Conventional Approach for the Solution of the Fifth Order Boundary Value Problems Using Sixth Degree Spline Functions Appled Matheatcs, 1, 4, 8-88 http://d.do.org/1.4/a.1.448 Publshed Ole Aprl 1 (http://www.scrp.org/joural/a) A Covetoal Approach for the Soluto of the Ffth Order Boudary Value Probles Usg Sth Degree Sple

More information

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS

UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS UNIVERSITY OF OSLO DEPARTMENT OF ECONOMICS Exam: ECON430 Statstcs Date of exam: Frday, December 8, 07 Grades are gve: Jauary 4, 08 Tme for exam: 0900 am 00 oo The problem set covers 5 pages Resources allowed:

More information

TRIANGULAR MEMBERSHIP FUNCTIONS FOR SOLVING SINGLE AND MULTIOBJECTIVE FUZZY LINEAR PROGRAMMING PROBLEM.

TRIANGULAR MEMBERSHIP FUNCTIONS FOR SOLVING SINGLE AND MULTIOBJECTIVE FUZZY LINEAR PROGRAMMING PROBLEM. Abbas Iraq Joural of SceceVol 53No 12012 Pp. 125-129 TRIANGULAR MEMBERSHIP FUNCTIONS FOR SOLVING SINGLE AND MULTIOBJECTIVE FUZZY LINEAR PROGRAMMING PROBLEM. Iraq Tarq Abbas Departemet of Mathematc College

More information

PROJECTION PROBLEM FOR REGULAR POLYGONS

PROJECTION PROBLEM FOR REGULAR POLYGONS Joural of Mathematcal Sceces: Advaces ad Applcatos Volume, Number, 008, Pages 95-50 PROJECTION PROBLEM FOR REGULAR POLYGONS College of Scece Bejg Forestry Uversty Bejg 0008 P. R. Cha e-mal: sl@bjfu.edu.c

More information

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA

THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA THE ROYAL STATISTICAL SOCIETY EXAMINATIONS SOLUTIONS GRADUATE DIPLOMA PAPER II STATISTICAL THEORY & METHODS The Socety provdes these solutos to assst caddates preparg for the examatos future years ad for

More information

Bayes Interval Estimation for binomial proportion and difference of two binomial proportions with Simulation Study

Bayes Interval Estimation for binomial proportion and difference of two binomial proportions with Simulation Study IJIEST Iteratoal Joural of Iovatve Scece, Egeerg & Techology, Vol. Issue 5, July 04. Bayes Iterval Estmato for bomal proporto ad dfferece of two bomal proportos wth Smulato Study Masoud Gaj, Solmaz hlmad

More information

Study on Risk Analysis of Railway Signal System

Study on Risk Analysis of Railway Signal System Yuayua L, Youpeg Zhag, Rag Hu Study o Rsk Aalyss of Ralway Sgal System YUANYUAN LI, YOUPENG ZHANG, RANG HU School of Automato ad Electrcal Egeerg Lazhou Jaotog Uversty NO.88 ANg West Aeue, Lazhou, GaSu

More information

Lecture 1 Review of Fundamental Statistical Concepts

Lecture 1 Review of Fundamental Statistical Concepts Lecture Revew of Fudametal Statstcal Cocepts Measures of Cetral Tedecy ad Dsperso A word about otato for ths class: Idvduals a populato are desgated, where the dex rages from to N, ad N s the total umber

More information

9.1 Introduction to the probit and logit models

9.1 Introduction to the probit and logit models EC3000 Ecoometrcs Lecture 9 Probt & Logt Aalss 9. Itroducto to the probt ad logt models 9. The logt model 9.3 The probt model Appedx 9. Itroducto to the probt ad logt models These models are used regressos

More information

1. BLAST (Karlin Altschul) Statistics

1. BLAST (Karlin Altschul) Statistics Parwse seuece algmet global ad local Multple seuece algmet Substtuto matrces Database searchg global local BLAST Seuece statstcs Evolutoary tree recostructo Gee Fdg Prote structure predcto RNA structure

More information

Evaluation on Ecological Environment of Scientific and Technological Innovation Talents in China

Evaluation on Ecological Environment of Scientific and Technological Innovation Talents in China AMSE JOURNALS-2016-Seres: Modellg C; Vol. 77; N 1; pp 108-118 Submtted July 2016; Revsed Oct. 15, 2016, Accepted Dec. 10, 2016 Evaluato o Ecologcal Evromet of Scetfc ad Techologcal Iovato Talets Cha Nabg

More information

STA 105-M BASIC STATISTICS (This is a multiple choice paper.)

STA 105-M BASIC STATISTICS (This is a multiple choice paper.) DCDM BUSINESS SCHOOL September Mock Eamatos STA 0-M BASIC STATISTICS (Ths s a multple choce paper.) Tme: hours 0 mutes INSTRUCTIONS TO CANDIDATES Do ot ope ths questo paper utl you have bee told to do

More information

STA302/1001-Fall 2008 Midterm Test October 21, 2008

STA302/1001-Fall 2008 Midterm Test October 21, 2008 STA3/-Fall 8 Mdterm Test October, 8 Last Name: Frst Name: Studet Number: Erolled (Crcle oe) STA3 STA INSTRUCTIONS Tme allowed: hour 45 mutes Ads allowed: A o-programmable calculator A table of values from

More information

Optimization Research of Batch Order Processing Queue in Internet Consumption Custom Marketing

Optimization Research of Batch Order Processing Queue in Internet Consumption Custom Marketing Jot Iteratoal Socal Scece, Educato, Laguage, Maagemet ad Busess Coferece (JISEM 205 Optmzato Research of Batch Order Processg Queue Iteret Cosumpto Custom Maretg Ru Wag, a, Jao Tag2,b* ad Ye Yag3,c, 2,

More information

Ordinary Least Squares Regression. Simple Regression. Algebra and Assumptions.

Ordinary Least Squares Regression. Simple Regression. Algebra and Assumptions. Ordary Least Squares egresso. Smple egresso. Algebra ad Assumptos. I ths part of the course we are gog to study a techque for aalysg the lear relatoshp betwee two varables Y ad X. We have pars of observatos

More information

A Method for Damping Estimation Based On Least Square Fit

A Method for Damping Estimation Based On Least Square Fit Amerca Joural of Egeerg Research (AJER) 5 Amerca Joural of Egeerg Research (AJER) e-issn: 3-847 p-issn : 3-936 Volume-4, Issue-7, pp-5-9 www.ajer.org Research Paper Ope Access A Method for Dampg Estmato

More information

Chapter 9 Jordan Block Matrices

Chapter 9 Jordan Block Matrices Chapter 9 Jorda Block atrces I ths chapter we wll solve the followg problem. Gve a lear operator T fd a bass R of F such that the matrx R (T) s as smple as possble. f course smple s a matter of taste.

More information

12.2 Estimating Model parameters Assumptions: ox and y are related according to the simple linear regression model

12.2 Estimating Model parameters Assumptions: ox and y are related according to the simple linear regression model 1. Estmatg Model parameters Assumptos: ox ad y are related accordg to the smple lear regresso model (The lear regresso model s the model that says that x ad y are related a lear fasho, but the observed

More information

Regresso What s a Model? 1. Ofte Descrbe Relatoshp betwee Varables 2. Types - Determstc Models (o radomess) - Probablstc Models (wth radomess) EPI 809/Sprg 2008 9 Determstc Models 1. Hypothesze

More information

L5 Polynomial / Spline Curves

L5 Polynomial / Spline Curves L5 Polyomal / Sple Curves Cotets Coc sectos Polyomal Curves Hermte Curves Bezer Curves B-Sples No-Uform Ratoal B-Sples (NURBS) Mapulato ad Represetato of Curves Types of Curve Equatos Implct: Descrbe a

More information

Research Article On the Number of Spanning Trees of Graphs

Research Article On the Number of Spanning Trees of Graphs e Scetfc World Joural, Artcle ID 294038, 5 pages http://dxdoorg/055/204/294038 Research Artcle O the Number of Spag Trees of Graphs F Burcu Bozkurt ad DurmuG Bozkurt Departmet of Mathematcs, Scece Faculty,

More information

VOL. 3, NO. 11, November 2013 ISSN ARPN Journal of Science and Technology All rights reserved.

VOL. 3, NO. 11, November 2013 ISSN ARPN Journal of Science and Technology All rights reserved. VOL., NO., November 0 ISSN 5-77 ARPN Joural of Scece ad Techology 0-0. All rghts reserved. http://www.ejouralofscece.org Usg Square-Root Iverted Gamma Dstrbuto as Pror to Draw Iferece o the Raylegh Dstrbuto

More information

(Monte Carlo) Resampling Technique in Validity Testing and Reliability Testing

(Monte Carlo) Resampling Technique in Validity Testing and Reliability Testing Iteratoal Joural of Computer Applcatos (0975 8887) (Mote Carlo) Resamplg Techque Valdty Testg ad Relablty Testg Ad Setawa Departmet of Mathematcs, Faculty of Scece ad Mathematcs, Satya Wacaa Chrsta Uversty

More information

Comparison of Parameters of Lognormal Distribution Based On the Classical and Posterior Estimates

Comparison of Parameters of Lognormal Distribution Based On the Classical and Posterior Estimates Joural of Moder Appled Statstcal Methods Volume Issue Artcle 8 --03 Comparso of Parameters of Logormal Dstrbuto Based O the Classcal ad Posteror Estmates Raja Sulta Uversty of Kashmr, Sragar, Ida, hamzasulta8@yahoo.com

More information

Cubic Nonpolynomial Spline Approach to the Solution of a Second Order Two-Point Boundary Value Problem

Cubic Nonpolynomial Spline Approach to the Solution of a Second Order Two-Point Boundary Value Problem Joural of Amerca Scece ;6( Cubc Nopolyomal Sple Approach to the Soluto of a Secod Order Two-Pot Boudary Value Problem W.K. Zahra, F.A. Abd El-Salam, A.A. El-Sabbagh ad Z.A. ZAk * Departmet of Egeerg athematcs

More information

The internal structure of natural numbers, one method for the definition of large prime numbers, and a factorization test

The internal structure of natural numbers, one method for the definition of large prime numbers, and a factorization test Fal verso The teral structure of atural umbers oe method for the defto of large prme umbers ad a factorzato test Emmaul Maousos APM Isttute for the Advacemet of Physcs ad Mathematcs 3 Poulou str. 53 Athes

More information

Chapter 5 Properties of a Random Sample

Chapter 5 Properties of a Random Sample Lecture 6 o BST 63: Statstcal Theory I Ku Zhag, /0/008 Revew for the prevous lecture Cocepts: t-dstrbuto, F-dstrbuto Theorems: Dstrbutos of sample mea ad sample varace, relatoshp betwee sample mea ad sample

More information

A Planning Approach of Engineering Characteristics Based on QFD-TRIZ Integrated

A Planning Approach of Engineering Characteristics Based on QFD-TRIZ Integrated A Plag Approach of Egeerg Characterstcs Based o QFD-TRIZ Itegrated Shag Lu, Dogya Sh,, ad Yg Zhag College Mechacal ad Electrcal Egeerg, Harb Egeerg Uversty, Harb 5, Cha Postdoctoral Research Stato of Istrumet

More information

Mean is only appropriate for interval or ratio scales, not ordinal or nominal.

Mean is only appropriate for interval or ratio scales, not ordinal or nominal. Mea Same as ordary average Sum all the data values ad dvde by the sample sze. x = ( x + x +... + x Usg summato otato, we wrte ths as x = x = x = = ) x Mea s oly approprate for terval or rato scales, ot

More information