COURSE CONTENT: COURSE REQUIREMENTS: READING LIST: LECTURE NOTES COURSE CODE: STS 352 COURSE TITLE: EXPERIMENTAL DESIGN 1 NUMBER OF UNIT: 2 UNITS
|
|
- Corey Lewis
- 5 years ago
- Views:
Transcription
1 COURSE CODE: STS 35 COURSE TITLE: EXPERIMENTAL DESIGN NUMBER OF UNIT: UNITS COURSE DURATION: TWO HOURS PER WEEK. COURSE COORDINATOR: MR G.A. DAUDU LECTURER OFFICE LOCATION: AMREC COURSE CONTENT: Basc concepts of expermentaton, Completel randomzed desgn, Randomsed complete block desgn, Latn Square Desgn, Graeco Latn Square Desgn, Smple factoral Desgn COURSE REQUIREMENTS: Ths s a compulsor course for all statstcs students. Students are expected to have a mnmum of 75% attendance to be able to wrte the fnal examnaton. READING LIST:.) Statstcal Desgn and Analss of Experments b P.W.M. John..) Expermental Desgns b Cochran and Cox. 3.) Desgns and Analss of Experments for Bolog and Agrc. Students b Oejola, B.A. 4.) Statstcal Methods b Snedecor and Cochran. 5.) Statstcal Procedures for Agrcultural Research b Gomez and Gomez. LECTURE NOTES Introducton An experment nvolves the plannng, executon and collecton of measurements or observatons. Examples of smple experment. Comparson of two teachng methods. Comparson of two varetes of maze The dfference among expermental unts treated alke s called expermental error, ths error s the prmar bass for decdng whether an observed dfference s real or
2 just due to chance. Clearl ever experment must be desgned to have a measure of the expermental error. Defntons Expermental Unt/plot Ths s the smallest to whch a treatment s appled, and on whch an observaton s made e.g. an anmal brd, an object, a cage, a feld plat and so on. - Defnton of a unt depend on the objectve of the experment. Factors These are dstnct tpes of condton that are manpulated on the expermental unt e.g. age, group, gender, varet, fertlzer and so on. Factor Levels Dfferent mode of the presence of a factors are called factor levels. - Factors can be quanttatve or qualtatve. Treatments Each specfc combnaton of the levels of dfferent factors s called the treatment. Replcaton These are the numbers of expermental unts to whch a gven treatment s appled. MAIN ASPECT OF DESIGNING EXPERIMENT a. Choose the factor to be studed n the experment and the levels of each factor that are relevant to the nvestgaton. b. Consder the scope of nference and choose the tpe of expermental unt on whch treatment are to be appled. c. From the perspectve of cost and desred precson of nference, decde on the number of unts to be used for the experment. d. Fnall, and most mportant, determne the manner n whch the treatments are to be appled to the expermental unts (.e. desgn of the experment). PRINCIPLES OF EXPERIMENTAL DESIGN
3 There are three basc statstcal requrements for a good experment: Randomzaton Replcaton Local Control or Blockng. RANDOMIZATION: Ths s the process b whch t s ensured that each treatment has an equal chance of beng assgned to an expermental unt e.g. Suppose two maze varetes, Yellow (Y) and Whte (W) are to be compared usng four expermental unts for each (I) (II) In laout (II) f the feld has fertlt gradent so that there s a gradual productvt from top to bottom. Then the whte varet wll be at advantage been n a relatvel more fertle area hence, the comparson wthn the varet would be based n favour of varet W. A better laout s obtaned b randomzaton as shown n laout (I).. REPLICATION: Each treatment beng appled to more than one expermental unt. Expermental error can be measured onl f there are replcatons. Also the more the expermental unts used for each treatment, the lower would be the standard error for the estmate for treatment effect and hence, the more precse the experment. Precson s the measurement of how close the observed values are to each other. 3. BLOCKING OR LOCAL CONTROL: Ths s the process of groupng together expermental unts that are smlar and assgnng all treatments nto each group or block separatel and ndependentl. Ths allows the measurement of varaton among blocks whch can be removed from the expermental error. Blockng s therefore one of the measure for reducng or mnmzng expermental error. The
4 ablt of detectng exstng or real dfferences among treatments ncrease as the sze of the expermental error decreases. COMPLETELY RANDOMIZE DESIGN (CRD) Introducton A CRD s a desgn n whch the treatments are assgned completel at random so that each expermental unt has equal chance of recevng an one treatment. An dfference among the expermental unts recevng the same treatment s consdered to be expermental error. Model:
5 j = μ + e j = μ + α + e j =,,, t and j =,,, r Where s the observed value for replcate j of treatment, μ s the populaton mean for treatment, μ s the populaton mean, s the effect of treatment and e j s the expermental error resultng from replcate j of treatment. Assumpton: are assumed normall dstrbuted about the mean, μ, and varance, σ or N (0, σ ).e. ndependentl and dentcall normall dstrbuted wth mean 0 and constant varance σ. Also α = 0, Estmaton of the Parameters ds = dμ j ( j μ α ) ( ˆ μ α ) = 0 j j j j j j ˆ μ α = 0 j j rt ˆ μ r α = 0 Impose the constran α = 0 ds = dα rtμˆ = j ( j ˆ j μ = =.. rt j μ α )
6 ˆ α = ( ˆ ˆ j μ α ) = 0 j ˆ ˆ j μ α = 0 j j j r j j j r ˆ μ r ˆ α = 0 ˆ μ j =... Randomzaton Procedure. Determne the total number of expermental unts or plots (N) where N = rt wth r beng the number of replcatons and t the number of treatments.. Assgn a plot number to each expermental unt n an convenent manner consecutvel to N. 3. Assgn the treatments to the expermental unts b an chosen randomzaton scheme e.g. usng table of random numbers, random number generator, drawng of lots and so on. Data Structure Treatments T L t.
7 L t. r L r r tr. r.. L t.. Analss of Varance The total varaton n CRD s parttoned nto two sources of varaton.e. varaton due to treatment and varaton due to the error. The relatve sze of the two varatons s used to ndcate whether the observed dfference among the treatment means s sgnfcant or due to chance, the treatment dfference s sad to be sgnfcant f the treatment varaton s sgnfcantl larger than the expermental error. Total sum of squares, SST, SST t n = j = j= j (..) = N.. Sum of squares due to treatment SSB t n SSB =. (...) = n (...) = n = j= t = t = N.. Sum of Square due to Error, SSE t n SSE = ( ) = j= j... C. F = = correctng factor N SST = SSB + SSE. e. SSE = SST SSB ASSIGNMENT
8 Show that: ( ) = ( ) + ( ) j..... j. j j j ANOVA TABLE Source of varaton Degree of freedom Sum of Squares Between treatment t- SSB Error N-t SSE Total N- SST Means squares SSB MSB = t SSE MSE = N t F-rato MSB Fc = = Fc MSE If there are no dfferences n the effect of the treatment Fc follows the F- dstrbuton. Hence, f F c > F T where F T s the table value from the F-Table wth t and N t degrees of freedom at a gven sgnfcance level, then the effect are sad to be sgnfcantl dfferent Or Reject H 0 f F C F T COMPARISON OF MEANS If a sgnfcant result s declared then there s need to dentfed the mean that are dfferent and ths can be done usng multple comparson of means such as LSD Least Sgnfcant Dfference DMRT Duncan s Multple Range Test Turke Scheffee etc. LSD = tsed
9 = r If the observe dfference between an two means s greater than the LSD value then those two means are sad to be sgnfcantl dfferent. COEFFICIENT OF VARIATION Ths s a measure of precson of the estmates obtaned from the data. It s also used to assess the qualt of the management of an experment. A low coeffcent of varaton ndcates hgh precson of estmate or effcent management of the experment. Example: In an effort to mprove the qualt of recordng tapes, the effect of four knds of coatng A, B, C, D on the reproducng qualt of sound are to be compared. The measurements of sound dstorton are gven below. A B C D Recommend the best coatng for the sound producton. ADVANTAGE OF CRD. The desgn s ver flexble. The statstcal analss s smple
10 3. It has hgh degrees of freedom relatve to other desgns 4. It s best for small experments DISADVANTAGE OF CRD Desgn s ver neffcent f unts are not homogenous. ASSIGNMENT. Analze the followng data from a feld experment wth four treatments usng % sgnfcance level. Carrout mean comparson f necessar. How good s the management of the experment. A B C D Three fertlzer sources A, B, C, were each appled to seven plots chosen at random n a feld of carrot. Analze the data usng 5% sgnfcance level. Carrout mean comparson f necessar. How effcent was the management of the experment A B C RANDOMISED COMPLETE BLOCK DESIGN (RCBD)
11 Introducton The desgn s used when the expermental unt can be grouped such that the number of unts n a group s equal to number of treatments. The groups are called blocks or replcates and the purpose of groupng s to have unts n a group as homogeneous as possble so that observed dfferences n a group are manl due to treatments. Varablt wthn group s expected to be lower than varablt between groups. Snce the number of unts per block equal the number of treatments, the blocks are of equal sze hence, the desgn s a complete block desgn. The prmar purpose of blockng s to reduce the expermental error b elmnatng the known sources of varablt. Model: j = μ + α + β j + e j =,,, t and j =,,, r where s the observed value for block j of treatment, μ s the populaton mean, s the effect of treatment, β j s the effect of block j and e j s the expermental error resultng from block j of treatment. Assumpton: - block and treatment effect are addtve, - N (0, σ ) - α = 0, β j = 0, Estmaton of Parameters A procedure smlar to that used n CRD can be utlzed here to obtan the desred estmates. Randomzaton and Laout The randomzaton process for randomsed complete block desgn s appled separatel and ndependentl to each of the block. - Dvde the expermental area nto r-blocks. - Sub-dvde the block nto t-expermental unts. Where t s the number of treatments.
12 - Number the plot consectvel from I to t and assgn the t-treatment at random to the t-unt wthn each block followng an randomzaton scheme. DATA STRUCTURE Blocks Treatment 3 r Total 3 t Total r r.. Analss of Varance The total varaton s parttoned nto the varaton due to blocks, varaton due treatments, and varaton due to error..e... j.. j SSTotal = ( ) = N SS SS Trt Block. = (...) = r j =. ( j ) =.. t SSE = SSTotal SSTrt SSBlock N.. N..
13 ANOVA TABLE Source Df SS MS F Block r SSB MSB = r Treatment t MST Error (r-)(t-) SSE SST = t Total rt Hpothess Or Comparng the calculated F-ratos to the table F-value at a gven sgnfcance level, we decde to reject or fal to reject the null hpothess..e. Reject f Reject f COMPARISON OF MEANS Use LSD to compare the treatments f the F-rato s found to be sgnfcant. where Coeffcent of varaton CAUSES OF MISSING VALUES AND THEIR ESTIMATIONS A mssng data can occur whenever a vald observaton s not avalable for an one of the expermental unts, occurrence of mssng data result n two major problems.e. loss of nformaton and non applcablt of standard analss of varance.
14 COMMON CAUSES OF MISSING DATA nclude:. When ntended treatment s not appled.e. mproper treatment.. When expermental plants are destroed probabl due to poor germnaton, phscal damage, pest damage etc. Ths causes total or hgh percentage of the plants n a plot to be destroed such that no meanngful observaton can be made on the plot. 3. Loss of harvested sample: Ths ma result from the fact that some plant characters cannot be convenentl recorded ether n the feld or mmedatel after harvest due to some other process requred. Hence some samples wll be lost between the tme of harvestng and actual recordng of data. 4. Ths happens after data have been recorded and transcrbed generall referred to a llogcal data. The value ma be too extreme as a result of msread observaton or ncorrect transcrpton. ESTIMATION OF MISSING VALUE FROM RCBD Let x be the mssng value,,, xˆ ˆ μ ˆ α β = 0, j =
15 , = 0 where G 0 s the grand total excludng the mssng value. T 0 s the total observed value for the treatment that contaned the mssng value. B 0 s the total observed value for the Block that contaned the mssng value. Note that: the degree of freedom must be adjusted b the number of mssng values.e. reduce the number of degrees of freedom b the number of mssng values. ADVANTAGES OF RANDOMIZED COMPLETE BLOCK DESIGNS. A reducton of experment error due to blockng s expected.. Estmaton of mssng value s eas to compute. 3. The ANOVA s also eas to compute. DISADVANTAGES OF RCBD. Not best for large number of treatments.. More taskng n the executon of the desgn than the CRD. 3. Mssng value can create problem especall n estmaton and non formal analss. 4. The precson wll be affected due to mssng values. RELATIVE EFFICIENCY Blockng maxmzes the dfference among blocks. Hence t s necessar to examne how much s ganed b the ntroducton of blockng nto the desgn. The magntude of the
16 reducton n the expermental error due to blockng over the CRD can be obtaned b computng relatve effcenc. Where s the block mean square and the s the error mean square.. Example: In an experment to examne the respond of maze to nutrent fertlzer applcaton. Sx treatments were used n four blocks. Analze the data and recommend the approprate fertlzer rate. F F F 3 F 4 F 5 F 6 TOTAL I II III IV TOTAL The followng data are eld of groundnut n a varet tral nvolvng fve varetes of groundnut usng four replcatons n randomzed complete block desgn. The data has one mssng value. Analze the data and make our recommendaton. V V V 3 V 4 V 5 I II * III IV ASSIGNMENT In an experment to test the effect of fve level of potash (ABCDE) on the eld of cotton the followng strength ndces were obtan as gven below. One of the data pont s mssng. Analze the data and compare the mean of the fve level of potash and make necessar recommendaton. How effectvel was the experment carred out. Was there an gan n precson n usng RCBD over CRD
17 A (7.6) C (*) E (7.46) D (7.7) B (8.4) E (7.68) B (8.5) C (7.73) D (7.57) A (800) C (7.47) E (7.0) A ( (7.93) B (7.87) D (7.80) LATIN SQUARE DESIGN Introducton The major feature of the latn square desgn s ts capact to smultaneousl handle two known sources of varaton among the expermental unts. These are commonl referred to as row blockng and column blockng. It s ensured that ever treatment occurs onl once n each row and once n each column. Hence the varaton due to row and column can be estmated and removed from the expermental error. Note that: the presence of row and column blockng also consttute a restrcton. Ths s due to the requrement that all treatment appear n each row and n each column. Ths s onl satsfed f the number of replcatons equal the number of treatments. Hence, for large number of treatments, the desgn s not practcable. Also when the number of treatments s small the degrees of freedom for the error becomes too small for the error to be relabl estmated, the desgn s therefore not generall, wdel adopted.
18 Model: jk = μ + α + β j + δ k + e jk where, j, k =,,, t where s the observed value from row j and column k recevng treatment. - s the overall mean - s the effect of treatment - s the effect of row j - s the effect of row k - s the random error component for row j and column k recevng treatment. Assumptons: The model s completel addtve.e. there s no nteracton between the rows, columns and treatments. N (0, σ ) and Estmaton of Parameters A procedure smlar to that used n CRD can be utlzed here to obtan the desred estmates. RANDOMIZATION PROCEDURE. Obtan a square feld parttoned nto t rows and t columns.. Arrange the treatment nto the unt n a standard form. 3. Randomze between the columns 4. Randomze between the rows Example: Consder an experment wth four treatments to be compared usng latn square desgn.e. 4 x 4 LS
19 col Standard form * A B C D * B C D A * C D A B * D A B C 3 4 Randomze btw B D C A 43 C A D B 3 D B A C 4 A C B D Randomze between row C A D B D B A C 34 3 A C B D 4 B D C A ANALYSIS OF VARIANCE The total varaton s parttoned nto components for row, column, treatment and error. The sum of squares are obtaned n the usual form. ANOVA TABLE Source Df SS MS F Rows t- SSR MSR Columns t- SSC MSC Treatments t- SS Trt MS Trt MSR / MSE MSC / MSE MS Trt / MSE Error (t-) (t-) SSE MSE Total t - SST BLOCKING EFFICIENCY The effcenc of both row and column blockngs n a latn square desgn ndcate the gan n precson relatve to ether the CRD or RCBD.
20 RELATIVE EFFICIENCY OF LSD TO CRD Relatve effcenc of a latn square desgn as compared to CRD s gven b Where Er, E c, E e are the mean squares row, column, and error respectvel wth t as the number of treatment. For an R.E = 35% t ndcates that the use of LSD s estmated to ncrease the expermental precson b 5% whle f the R.E s less than 00% means that there s no gan. RELATIVE EFFICIENCY LSD TO RCBD Relatve effcenc of latn square desgn as compared to RCBD can be computed n two was.e. when rows are consdered as blocks and when columns are consdered as blocks of the RCBD. I II III IV I II III IV ) = ) = Example: Suppose we have Result ndcate that, the addtonal column blockng b use of latn square desgn s estmated to have ncreased the precson over that of the RCBD wth row as block b 94%. However, the addtonal row blockng n the LS Desgn dd not ncrease the precson over the RCBD wth column as blocks. Hence for ths experment the Randomzed Complete Block Desgn wth column as blocks would have been as effcent as the LS Desgn. MISSING VALUE ESTIMATION Mssng value n the latn square experment can be estmated as follows
21 Where the R 0, C 0, T 0 are the total of the row, column and treatment respectvel that contan the mssng observaton. Agan one degree of freedom s subtracted from both total and error degrees of freedom n the case of one mssng value. ADVANTAGES AND DISADVANTAGES. The elmnaton of two sources of varaton often lead to a smaller error mean square than would be obtaned b use of CRD and RCBD.. ANOVA s smple 3. Mssng values can easl be handled Dsadvantages.. Assumpton of no nteracton between dfferent factors ma not hold.. Unlke the CRD and RCBD, the number of treatments s restrcted to the number of replcatons. Hence t s lmted n applcaton. 3. For large number of treatments such as t >, the square becomes too large and does not reman homogeneous. 4. For small number of treatments such as t < 3, degrees of freedom for the error s usuall too small for an meanngful comparson or concluson. 5. A square feld s often requred for the desgn and ths ma not be practcable. Example: The followng show the feld laout and eld of a 5 x 5 latn square experment on the effect of spacng on eld of mllet, the spacng are: A(cm), B(4cm), C(6cm), D(8cm) and E(0cm) Column Row Total B: 57 E: 30 A: 79 C: 87 D: 0 55 D: 45 A: 83 E: 45 B: 80 C: E: 8 B: 5 C: 80 D: 46 A: A: 03 C: 04 D: 7 E: 93 B: C: 3 D: 7 B: 66 A: 334 E:
22 Total GRAECO LATIN SQUARE DESIGN (GLSD) Introducton In the Graeco latn square desgn, the treatments are grouped nto replcates n three dfferent was: ths trple groupng s to elmnate from the error, three sources of blockng of blockng varaton. Recall the earler desgn: CRD - No blockng varaton RCBD - Sngle blockng varaton Latn Square - Double blockng varaton Graeco latn - Trpple blockng varaton Thus GLSD provde more opportunt than the other desgns n the reducton of error through skllful plannng. The expermental unt should be arranged and the experment conducted so that dfferences n the three drectons represent major sources of varaton. RANDOMIZATION Arrange the rows and the columns ndependentl at random ncludng the treatment. Assgn the subscrpt at random to ther respectve classfcaton. The treatment and subscrpt must appear once n a column and once n a row, and must appear together onl once. The laout can be dffcult to desgn but lke n the latn square desgn, once we obtan a standard form then we can randomze between the columns and between the rows. I II III I II III I A B 3 C C 3 A B II B C A 3 A B 3 C III C 3 A B B C A 3 Randomze between rows I II III A B C 3
23 B 3 C A C A 3 B Randomze between columns T = 4 A, B, C. D I II III IV I A C 4 B 3 D II B D 3 A 4 C III C 3 A D B 4 IV D 4 B C A 3 T = 5 A, B, C, D, E I II III IV V A B 3 C 5 D E 4 B C 4 D E 3 A 5 C 3 D 5 E A 4 B D 4 E A 3 B 5 C E 5 A B 4 C D 3 MODEL jkl = μ + α + β j + δ k + τ l + e jkl where, j, k, l =,,, t where s the observed value from row j and column k recevng treatment. s the grand mean s the effect of treatment
24 s the effect of row j s the effect of column k τ l s the effect of subscrpt factor l. s the random error component Assumptons: The model s completel addtve.e. no nteracton between the row, the column, the subscrpt factor and the treatment N (0, σ ), and τ l = 0 Estmaton of Parameters A procedure smlar to that used n CRD can be utlzed here to obtan the desred estmates. STATISTICAL ANALYSIS The total varaton s petton nto fve components.e. the row, column, subscrpt factor, treatment and error. The sum of square are obtan n the usual form.e. SSR = t. j..... N
25 ANOVA TABLE Source Df SS MS F Rows t- SSR MSR Column t- SSC MSC MSR / MSE MSC / MSE Subscrpt t- SS Subscrpt MS Subscrpt MS Subscrpt / MSE Treatments t- SS Trt MS Trt Error (t-) (t-3) SSE MSE Total t - SST MS Trt / MSE Note the followngs:. The number of replcatons equals the number of treatments hence for large number of treatments, the desgn s not practcable (t > ).. The expermental error s lkel to ncrease wth the sze of the square. 3. Small square provde onl a few degree of freedom for the error. 4. Expermental unts are dffcult to balance convenentl n all the three groupngs. Example Consder the followng data whch was obtan from an experment to stud the samplng error, the data consst of fve samplers (A E) beng controlled for order of samplng, area of samplng and qualfcaton of sampler. Analse the data. AREA Order Total A (3.5) B 3 (4.) C 5 (6.7) D (6.6) E 4 (4.) 5. B (8.9) C 4 (.9) D (5.8) B 3 (4.5) A 5 (.4) C 3 (9.6) D 5 (.7) E (.7) A 4 (3.7) B (6.0) D 4 (0.6) E (0.) A 3 (4.6) B 5 (3.7) C (5.) E 5 (3.) A (7.) B 4 (4.0) C (3.3) D 3 (3.5). Total
26 ASSIGNMENT The data below s obtaned from an experment usng Graeco Latn Square Desgn wth four det, (A, B, C, D). breed I, II, III, IV weght group {,, 3, 4} feed concentraton { v}. Is there an sgnfcant dfference between the dets. If an, compare them and make necessar recommendaton. Also comment on the management of the experment. Breeds I II III IV A (5.9) B 3 (4.) C 4 (0.) D (6.6) B (8.9) A 4 (4.5) D 3 (6.0) C (3.0) 3 C 3 (9.6) D (5.8) A (7.) B 4 (4.6) 4 D 4 (0.5) C (4.) B (3.5) A 3 (6.7) SIMPLE FACTORIAL EXPERIMENT Introducton Factoral experments are used n the stud of the effects of two or more factors. In factoral experments, all the possble combnatons of the level of the factors make up the treatments. For example, f there are two factor A, B each wth a and b levels respectvel, then we have ab treatment combnatons. A Maze varet B Fertlzer Rate There are 0 treatment combnatons. Also factoral experments allow us to nvestgate the nteracton between the factors. That s, how the levels of a factor perform n the presence of the levels of another factor. We are able to answer the queston on how the responses to one factor were affected b another. A B Maze Varet Fertlzer Rate a 0 Whte b 0 0 kg/ha a Yellow b 30 kg/ha
27 In analzng data from a factoral experment, we would be nterested n the man effect and the nteracton effect of a factor. The man effect of a factor s a measure of the change n response n the level of a factor averaged over all levels of the other factors. For example, let two factors A and B be at two level a 0, a and b 0, b respectvel wth treatment combnatons a 0 b 0, a 0 b, a b 0, a b. The man effect of A s a measure of change n A from a 0 to a averaged over the two levels of B..e. At level b 0 of B: the smple effect of A s a b 0 a 0 b 0. Smlarl, at level b of B: the smple effect of A s a b a 0 b.. Man effect of A = The r represent the replcaton, where each treatment total response s from r unts. Also at level a 0 of A: smple effect of B s a 0 b a 0 b 0. Smlarl, at level a of A smple effect of B s Thus Man effect of B = Each effect of a factor at a gven level of the other factor s known as smple effect. The nteracton effect s the dfferental response to one factor n combnaton wth varng levels of a second factor. That s, an addtonal effect due to the combned nfluence of two or more factors. For example, nteracton between A and B (AB) s estmated as the dfference between two smple effects. and.e. the nteracton effect AB = BA = Consder the followng result Mean Responses b 0 b b 0 b b 0 b a a () () ()
28 From above llustraton () shows the case of no nteracton, () shows the case of mld nteracton and () shows the case of strong nteracton. LAYOUT An of the earler desgn dscussed can be used, n partcular, the RCBD. The treatment combnatons are assgned to each block randoml For example, consder the case of two factors A and B, each at two levels a 0, a and b 0, b respectvel. The treatment combnatons are a 0 b 0, a 0 b, a b 0, a b. a 0 b
29 RCBD a b CRD MODEL CRD where s the observed value from the k th unt correspondng to level of factor A and the j th level of B s the grand mean s the effect of level of factor A s the effect of the j th of factor B s the effect of nteracton between and. s the random error component. MODEL RCBD Where T k s the effect of the k th block H 0 : H : atleast one H 0 : H : atleast one H 30 : H 3 : {there s nteracton between A and B} ANALYSIS OF VARIANCE
30 The total varaton s parttoned nto that due to factor A, factor B, the nteracton AB and the error.e. where the SST, SSA, SSB, SSAB and SSE are obtan n the usual form.e. -SSA- SSB ANOVA TABLE Source Df SS MS F A a- SSA MSA B b- SSB MSB AB (a-) (b-) SSAB MSAB ERROR ab(r-) SSE MSE Total abr- SST Example MSA / MSE MSB / MSE MSAB / MSE An engneer desgnng a batter for use n a devce that would be subjected to some extreme varaton n temperature has three tpes of plate materals to use. He decded to test the plate materals under three temperature settngs (5 0 F, 70 0 F, 5 0 F) to see ther effect on the lfe of a batter. Four test runs are to be made at each treatment combnaton. Test the effect of temperature and plate materal and ther possble nteracton on the batter lfe.
31 Temperature Tpe 5 0 F 70 0 F 5 0 F A B C ASSIGNMENT Three tpes of tres are to be compared usng four dfferent brand of cars. The threadng on the tres are measured after a perod of use. Below s the rescaled data. Are the tres sgnfcantl dfferent? Also does the performance of the tres depend on the brand of the car? Tres Car brand A B C 3
32 4
Topic 23 - Randomized Complete Block Designs (RCBD)
Topc 3 ANOVA (III) 3-1 Topc 3 - Randomzed Complete Block Desgns (RCBD) Defn: A Randomzed Complete Block Desgn s a varant of the completely randomzed desgn (CRD) that we recently learned. In ths desgn,
More informationDepartment of Statistics University of Toronto STA305H1S / 1004 HS Design and Analysis of Experiments Term Test - Winter Solution
Department of Statstcs Unversty of Toronto STA35HS / HS Desgn and Analyss of Experments Term Test - Wnter - Soluton February, Last Name: Frst Name: Student Number: Instructons: Tme: hours. Ads: a non-programmable
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experment-I MODULE VII LECTURE - 3 ANALYSIS OF COVARIANCE Dr Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Any scentfc experment s performed
More informationx = , so that calculated
Stat 4, secton Sngle Factor ANOVA notes by Tm Plachowsk n chapter 8 we conducted hypothess tests n whch we compared a sngle sample s mean or proporton to some hypotheszed value Chapter 9 expanded ths to
More informationTopic- 11 The Analysis of Variance
Topc- 11 The Analyss of Varance Expermental Desgn The samplng plan or expermental desgn determnes the way that a sample s selected. In an observatonal study, the expermenter observes data that already
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experment-I MODULE VIII LECTURE - 34 ANALYSIS OF VARIANCE IN RANDOM-EFFECTS MODEL AND MIXED-EFFECTS EFFECTS MODEL Dr Shalabh Department of Mathematcs and Statstcs Indan
More informationChapter 12 Analysis of Covariance
Chapter Analyss of Covarance Any scentfc experment s performed to know somethng that s unknown about a group of treatments and to test certan hypothess about the correspondng treatment effect When varablty
More informationMD. LUTFOR RAHMAN 1 AND KALIPADA SEN 2 Abstract
ISSN 058-71 Bangladesh J. Agrl. Res. 34(3) : 395-401, September 009 PROBLEMS OF USUAL EIGHTED ANALYSIS OF VARIANCE (ANOVA) IN RANDOMIZED BLOCK DESIGN (RBD) ITH MORE THAN ONE OBSERVATIONS PER CELL HEN ERROR
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experments- MODULE LECTURE - 6 EXPERMENTAL DESGN MODELS Dr. Shalabh Department of Mathematcs and Statstcs ndan nsttute of Technology Kanpur Two-way classfcaton wth nteractons
More informationIntroduction to Analysis of Variance (ANOVA) Part 1
Introducton to Analss of Varance (ANOVA) Part 1 Sngle factor The logc of Analss of Varance Is the varance explaned b the model >> than the resdual varance In regresson models Varance explaned b regresson
More informationReduced slides. Introduction to Analysis of Variance (ANOVA) Part 1. Single factor
Reduced sldes Introducton to Analss of Varance (ANOVA) Part 1 Sngle factor 1 The logc of Analss of Varance Is the varance explaned b the model >> than the resdual varance In regresson models Varance explaned
More informationSIMPLE LINEAR REGRESSION
Smple Lnear Regresson and Correlaton Introducton Prevousl, our attenton has been focused on one varable whch we desgnated b x. Frequentl, t s desrable to learn somethng about the relatonshp between two
More informationChapter 13: Multiple Regression
Chapter 13: Multple Regresson 13.1 Developng the multple-regresson Model The general model can be descrbed as: It smplfes for two ndependent varables: The sample ft parameter b 0, b 1, and b are used to
More informationLINEAR REGRESSION ANALYSIS. MODULE VIII Lecture Indicator Variables
LINEAR REGRESSION ANALYSIS MODULE VIII Lecture - 7 Indcator Varables Dr. Shalabh Department of Maematcs and Statstcs Indan Insttute of Technology Kanpur Indcator varables versus quanttatve explanatory
More informationBOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS. M. Krishna Reddy, B. Naveen Kumar and Y. Ramu
BOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS M. Krshna Reddy, B. Naveen Kumar and Y. Ramu Department of Statstcs, Osmana Unversty, Hyderabad -500 007, Inda. nanbyrozu@gmal.com, ramu0@gmal.com
More informationSTAT 511 FINAL EXAM NAME Spring 2001
STAT 5 FINAL EXAM NAME Sprng Instructons: Ths s a closed book exam. No notes or books are allowed. ou may use a calculator but you are not allowed to store notes or formulas n the calculator. Please wrte
More informationStatistics II Final Exam 26/6/18
Statstcs II Fnal Exam 26/6/18 Academc Year 2017/18 Solutons Exam duraton: 2 h 30 mn 1. (3 ponts) A town hall s conductng a study to determne the amount of leftover food produced by the restaurants n the
More informationChapter 11: I = 2 samples independent samples paired samples Chapter 12: I 3 samples of equal size J one-way layout two-way layout
Serk Sagtov, Chalmers and GU, February 0, 018 Chapter 1. Analyss of varance Chapter 11: I = samples ndependent samples pared samples Chapter 1: I 3 samples of equal sze one-way layout two-way layout 1
More information4 Analysis of Variance (ANOVA) 5 ANOVA. 5.1 Introduction. 5.2 Fixed Effects ANOVA
4 Analyss of Varance (ANOVA) 5 ANOVA 51 Introducton ANOVA ANOVA s a way to estmate and test the means of multple populatons We wll start wth one-way ANOVA If the populatons ncluded n the study are selected
More informationDepartment of Quantitative Methods & Information Systems. Time Series and Their Components QMIS 320. Chapter 6
Department of Quanttatve Methods & Informaton Systems Tme Seres and Ther Components QMIS 30 Chapter 6 Fall 00 Dr. Mohammad Zanal These sldes were modfed from ther orgnal source for educatonal purpose only.
More informationLINEAR REGRESSION ANALYSIS. MODULE IX Lecture Multicollinearity
LINEAR REGRESSION ANALYSIS MODULE IX Lecture - 30 Multcollnearty Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur 2 Remedes for multcollnearty Varous technques have
More informationChapter 14 Simple Linear Regression
Chapter 4 Smple Lnear Regresson Chapter 4 - Smple Lnear Regresson Manageral decsons often are based on the relatonshp between two or more varables. Regresson analss can be used to develop an equaton showng
More informationResource Allocation and Decision Analysis (ECON 8010) Spring 2014 Foundations of Regression Analysis
Resource Allocaton and Decson Analss (ECON 800) Sprng 04 Foundatons of Regresson Analss Readng: Regresson Analss (ECON 800 Coursepak, Page 3) Defntons and Concepts: Regresson Analss statstcal technques
More informationChapter 8 Indicator Variables
Chapter 8 Indcator Varables In general, e explanatory varables n any regresson analyss are assumed to be quanttatve n nature. For example, e varables lke temperature, dstance, age etc. are quanttatve n
More informationPsychology 282 Lecture #24 Outline Regression Diagnostics: Outliers
Psychology 282 Lecture #24 Outlne Regresson Dagnostcs: Outlers In an earler lecture we studed the statstcal assumptons underlyng the regresson model, ncludng the followng ponts: Formal statement of assumptons.
More information1. Inference on Regression Parameters a. Finding Mean, s.d and covariance amongst estimates. 2. Confidence Intervals and Working Hotelling Bands
Content. Inference on Regresson Parameters a. Fndng Mean, s.d and covarance amongst estmates.. Confdence Intervals and Workng Hotellng Bands 3. Cochran s Theorem 4. General Lnear Testng 5. Measures of
More informationANOVA. The Observations y ij
ANOVA Stands for ANalyss Of VArance But t s a test of dfferences n means The dea: The Observatons y j Treatment group = 1 = 2 = k y 11 y 21 y k,1 y 12 y 22 y k,2 y 1, n1 y 2, n2 y k, nk means: m 1 m 2
More informationNegative Binomial Regression
STATGRAPHICS Rev. 9/16/2013 Negatve Bnomal Regresson Summary... 1 Data Input... 3 Statstcal Model... 3 Analyss Summary... 4 Analyss Optons... 7 Plot of Ftted Model... 8 Observed Versus Predcted... 10 Predctons...
More informationExponential Type Product Estimator for Finite Population Mean with Information on Auxiliary Attribute
Avalable at http://pvamu.edu/aam Appl. Appl. Math. ISSN: 193-9466 Vol. 10, Issue 1 (June 015), pp. 106-113 Applcatons and Appled Mathematcs: An Internatonal Journal (AAM) Exponental Tpe Product Estmator
More informationTopic 10: ANOVA models for random and mixed effects Fixed and Random Models in One-way Classification Experiments
Topc 10: ANOVA models for random and mxed effects eferences: ST&D Topc 7.5 (15-153), Topc 9.9 (5-7), Topc 15.5 (379-384); rules for expected on ST&D page 381 replaced by Chapter 8 from Montgomery, 1991.
More informationStatistics for Economics & Business
Statstcs for Economcs & Busness Smple Lnear Regresson Learnng Objectves In ths chapter, you learn: How to use regresson analyss to predct the value of a dependent varable based on an ndependent varable
More informationChapter 4 Experimental Design and Their Analysis
Chapter 4 Expermental Desgn and her Analyss Desgn of experment means how to desgn an experment n the sense that how the obseratons or measurements should be obtaned to answer a query n a ald, effcent and
More informationEconomics 130. Lecture 4 Simple Linear Regression Continued
Economcs 130 Lecture 4 Contnued Readngs for Week 4 Text, Chapter and 3. We contnue wth addressng our second ssue + add n how we evaluate these relatonshps: Where do we get data to do ths analyss? How do
More informatione i is a random error
Chapter - The Smple Lnear Regresson Model The lnear regresson equaton s: where + β + β e for,..., and are observable varables e s a random error How can an estmaton rule be constructed for the unknown
More informationUCLA STAT 13 Introduction to Statistical Methods for the Life and Health Sciences. Chapter 11 Analysis of Variance - ANOVA. Instructor: Ivo Dinov,
UCLA STAT 3 ntroducton to Statstcal Methods for the Lfe and Health Scences nstructor: vo Dnov, Asst. Prof. of Statstcs and Neurology Chapter Analyss of Varance - ANOVA Teachng Assstants: Fred Phoa, Anwer
More informationComparison of Regression Lines
STATGRAPHICS Rev. 9/13/2013 Comparson of Regresson Lnes Summary... 1 Data Input... 3 Analyss Summary... 4 Plot of Ftted Model... 6 Condtonal Sums of Squares... 6 Analyss Optons... 7 Forecasts... 8 Confdence
More informationLecture Notes for STATISTICAL METHODS FOR BUSINESS II BMGT 212. Chapters 14, 15 & 16. Professor Ahmadi, Ph.D. Department of Management
Lecture Notes for STATISTICAL METHODS FOR BUSINESS II BMGT 1 Chapters 14, 15 & 16 Professor Ahmad, Ph.D. Department of Management Revsed August 005 Chapter 14 Formulas Smple Lnear Regresson Model: y =
More informationLecture 6 More on Complete Randomized Block Design (RBD)
Lecture 6 More on Complete Randomzed Block Desgn (RBD) Multple test Multple test The multple comparsons or multple testng problem occurs when one consders a set of statstcal nferences smultaneously. For
More informationEcon107 Applied Econometrics Topic 3: Classical Model (Studenmund, Chapter 4)
I. Classcal Assumptons Econ7 Appled Econometrcs Topc 3: Classcal Model (Studenmund, Chapter 4) We have defned OLS and studed some algebrac propertes of OLS. In ths topc we wll study statstcal propertes
More informationMethods of Detecting Outliers in A Regression Analysis Model.
Methods of Detectng Outlers n A Regresson Analyss Model. Ogu, A. I. *, Inyama, S. C+, Achugamonu, P. C++ *Department of Statstcs, Imo State Unversty,Owerr +Department of Mathematcs, Federal Unversty of
More informationThe Multiple Classical Linear Regression Model (CLRM): Specification and Assumptions. 1. Introduction
ECONOMICS 5* -- NOTE (Summary) ECON 5* -- NOTE The Multple Classcal Lnear Regresson Model (CLRM): Specfcaton and Assumptons. Introducton CLRM stands for the Classcal Lnear Regresson Model. The CLRM s also
More informationSTATISTICS QUESTIONS. Step by Step Solutions.
STATISTICS QUESTIONS Step by Step Solutons www.mathcracker.com 9//016 Problem 1: A researcher s nterested n the effects of famly sze on delnquency for a group of offenders and examnes famles wth one to
More informationChapter 15 - Multiple Regression
Chapter - Multple Regresson Chapter - Multple Regresson Multple Regresson Model The equaton that descrbes how the dependent varable y s related to the ndependent varables x, x,... x p and an error term
More informationCorrelation and Regression. Correlation 9.1. Correlation. Chapter 9
Chapter 9 Correlaton and Regresson 9. Correlaton Correlaton A correlaton s a relatonshp between two varables. The data can be represented b the ordered pars (, ) where s the ndependent (or eplanator) varable,
More informationChapter 3 Describing Data Using Numerical Measures
Chapter 3 Student Lecture Notes 3-1 Chapter 3 Descrbng Data Usng Numercal Measures Fall 2006 Fundamentals of Busness Statstcs 1 Chapter Goals To establsh the usefulness of summary measures of data. The
More informationUNIVERSITY OF TORONTO Faculty of Arts and Science. December 2005 Examinations STA437H1F/STA1005HF. Duration - 3 hours
UNIVERSITY OF TORONTO Faculty of Arts and Scence December 005 Examnatons STA47HF/STA005HF Duraton - hours AIDS ALLOWED: (to be suppled by the student) Non-programmable calculator One handwrtten 8.5'' x
More information# c i. INFERENCE FOR CONTRASTS (Chapter 4) It's unbiased: Recall: A contrast is a linear combination of effects with coefficients summing to zero:
1 INFERENCE FOR CONTRASTS (Chapter 4 Recall: A contrast s a lnear combnaton of effects wth coeffcents summng to zero: " where " = 0. Specfc types of contrasts of nterest nclude: Dfferences n effects Dfferences
More informationSampling Theory MODULE VII LECTURE - 23 VARYING PROBABILITY SAMPLING
Samplng heory MODULE VII LECURE - 3 VARYIG PROBABILIY SAMPLIG DR. SHALABH DEPARME OF MAHEMAICS AD SAISICS IDIA ISIUE OF ECHOLOGY KAPUR he smple random samplng scheme provdes a random sample where every
More informationSystematic Error Illustration of Bias. Sources of Systematic Errors. Effects of Systematic Errors 9/23/2009. Instrument Errors Method Errors Personal
9/3/009 Sstematc Error Illustraton of Bas Sources of Sstematc Errors Instrument Errors Method Errors Personal Prejudce Preconceved noton of true value umber bas Prefer 0/5 Small over large Even over odd
More information17 Nested and Higher Order Designs
54 17 Nested and Hgher Order Desgns 17.1 Two-Way Analyss of Varance Consder an experment n whch the treatments are combnatons of two or more nfluences on the response. The ndvdual nfluences wll be called
More informationLecture 6: Introduction to Linear Regression
Lecture 6: Introducton to Lnear Regresson An Manchakul amancha@jhsph.edu 24 Aprl 27 Lnear regresson: man dea Lnear regresson can be used to study an outcome as a lnear functon of a predctor Example: 6
More informationECONOMICS 351*-A Mid-Term Exam -- Fall Term 2000 Page 1 of 13 pages. QUEEN'S UNIVERSITY AT KINGSTON Department of Economics
ECOOMICS 35*-A Md-Term Exam -- Fall Term 000 Page of 3 pages QUEE'S UIVERSITY AT KIGSTO Department of Economcs ECOOMICS 35* - Secton A Introductory Econometrcs Fall Term 000 MID-TERM EAM ASWERS MG Abbott
More informationx yi In chapter 14, we want to perform inference (i.e. calculate confidence intervals and perform tests of significance) in this setting.
The Practce of Statstcs, nd ed. Chapter 14 Inference for Regresson Introducton In chapter 3 we used a least-squares regresson lne (LSRL) to represent a lnear relatonshp etween two quanttatve explanator
More information/ n ) are compared. The logic is: if the two
STAT C141, Sprng 2005 Lecture 13 Two sample tests One sample tests: examples of goodness of ft tests, where we are testng whether our data supports predctons. Two sample tests: called as tests of ndependence
More informationStatistics for Business and Economics
Statstcs for Busness and Economcs Chapter 11 Smple Regresson Copyrght 010 Pearson Educaton, Inc. Publshng as Prentce Hall Ch. 11-1 11.1 Overvew of Lnear Models n An equaton can be ft to show the best lnear
More informationNANYANG TECHNOLOGICAL UNIVERSITY SEMESTER I EXAMINATION MTH352/MH3510 Regression Analysis
NANYANG TECHNOLOGICAL UNIVERSITY SEMESTER I EXAMINATION 014-015 MTH35/MH3510 Regresson Analyss December 014 TIME ALLOWED: HOURS INSTRUCTIONS TO CANDIDATES 1. Ths examnaton paper contans FOUR (4) questons
More informationChapter 11: Simple Linear Regression and Correlation
Chapter 11: Smple Lnear Regresson and Correlaton 11-1 Emprcal Models 11-2 Smple Lnear Regresson 11-3 Propertes of the Least Squares Estmators 11-4 Hypothess Test n Smple Lnear Regresson 11-4.1 Use of t-tests
More information7.1. Single classification analysis of variance (ANOVA) Why not use multiple 2-sample 2. When to use ANOVA
Sngle classfcaton analyss of varance (ANOVA) When to use ANOVA ANOVA models and parttonng sums of squares ANOVA: hypothess testng ANOVA: assumptons A non-parametrc alternatve: Kruskal-Walls ANOVA Power
More informationChapter 2 - The Simple Linear Regression Model S =0. e i is a random error. S β2 β. This is a minimization problem. Solution is a calculus exercise.
Chapter - The Smple Lnear Regresson Model The lnear regresson equaton s: where y + = β + β e for =,..., y and are observable varables e s a random error How can an estmaton rule be constructed for the
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Exerments-I MODULE III LECTURE - 2 EXPERIMENTAL DESIGN MODELS Dr. Shalabh Deartment of Mathematcs and Statstcs Indan Insttute of Technology Kanur 2 We consder the models
More informationLecture 20: Hypothesis testing
Lecture : Hpothess testng Much of statstcs nvolves hpothess testng compare a new nterestng hpothess, H (the Alternatve hpothess to the borng, old, well-known case, H (the Null Hpothess or, decde whether
More informationRegression. The Simple Linear Regression Model
Regresson Smple Lnear Regresson Model Least Squares Method Coeffcent of Determnaton Model Assumptons Testng for Sgnfcance Usng the Estmated Regresson Equaton for Estmaton and Predcton Resdual Analss: Valdatng
More informationNumber of cases Number of factors Number of covariates Number of levels of factor i. Value of the dependent variable for case k
ANOVA Model and Matrx Computatons Notaton The followng notaton s used throughout ths chapter unless otherwse stated: N F CN Y Z j w W Number of cases Number of factors Number of covarates Number of levels
More informationOutline. EEC 686/785 Modeling & Performance Evaluation of Computer Systems. Lecture k r Factorial Designs with Replication
EEC 66/75 Modelng & Performance Evaluaton of Computer Systems Lecture 3 Department of Electrcal and Computer Engneerng Cleveland State Unversty wenbng@eee.org (based on Dr. Ra Jan s lecture notes) Outlne
More informationChapter 13 Analysis of Variance and Experimental Design
Chapter 3 Analyss of Varance and Expermental Desgn Learnng Obectves. Understand how the analyss of varance procedure can be used to determne f the means of more than two populatons are equal.. Know the
More informationStatistics Chapter 4
Statstcs Chapter 4 "There are three knds of les: les, damned les, and statstcs." Benjamn Dsrael, 1895 (Brtsh statesman) Gaussan Dstrbuton, 4-1 If a measurement s repeated many tmes a statstcal treatment
More informationBasic Business Statistics, 10/e
Chapter 13 13-1 Basc Busness Statstcs 11 th Edton Chapter 13 Smple Lnear Regresson Basc Busness Statstcs, 11e 009 Prentce-Hall, Inc. Chap 13-1 Learnng Objectves In ths chapter, you learn: How to use regresson
More informationFirst Year Examination Department of Statistics, University of Florida
Frst Year Examnaton Department of Statstcs, Unversty of Florda May 7, 010, 8:00 am - 1:00 noon Instructons: 1. You have four hours to answer questons n ths examnaton.. You must show your work to receve
More informationLecture 9: Linear regression: centering, hypothesis testing, multiple covariates, and confounding
Recall: man dea of lnear regresson Lecture 9: Lnear regresson: centerng, hypothess testng, multple covarates, and confoundng Sandy Eckel seckel@jhsph.edu 6 May 8 Lnear regresson can be used to study an
More informationA LINEAR PROGRAM TO COMPARE MULTIPLE GROSS CREDIT LOSS FORECASTS. Dr. Derald E. Wentzien, Wesley College, (302) ,
A LINEAR PROGRAM TO COMPARE MULTIPLE GROSS CREDIT LOSS FORECASTS Dr. Derald E. Wentzen, Wesley College, (302) 736-2574, wentzde@wesley.edu ABSTRACT A lnear programmng model s developed and used to compare
More informationPolynomial Regression Models
LINEAR REGRESSION ANALYSIS MODULE XII Lecture - 6 Polynomal Regresson Models Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Test of sgnfcance To test the sgnfcance
More informationLecture 9: Linear regression: centering, hypothesis testing, multiple covariates, and confounding
Lecture 9: Lnear regresson: centerng, hypothess testng, multple covarates, and confoundng Sandy Eckel seckel@jhsph.edu 6 May 008 Recall: man dea of lnear regresson Lnear regresson can be used to study
More informationStatistical tables are provided Two Hours UNIVERSITY OF MANCHESTER. Date: Wednesday 4 th June 2008 Time: 1400 to 1600
Statstcal tables are provded Two Hours UNIVERSITY OF MNCHESTER Medcal Statstcs Date: Wednesday 4 th June 008 Tme: 1400 to 1600 MT3807 Electronc calculators may be used provded that they conform to Unversty
More informationComparison of the Population Variance Estimators. of 2-Parameter Exponential Distribution Based on. Multiple Criteria Decision Making Method
Appled Mathematcal Scences, Vol. 7, 0, no. 47, 07-0 HIARI Ltd, www.m-hkar.com Comparson of the Populaton Varance Estmators of -Parameter Exponental Dstrbuton Based on Multple Crtera Decson Makng Method
More information1-FACTOR ANOVA (MOTIVATION) [DEVORE 10.1]
1-FACTOR ANOVA (MOTIVATION) [DEVORE 10.1] Hgh varance between groups Low varance wthn groups s 2 between/s 2 wthn 1 Factor A clearly has a sgnfcant effect!! Low varance between groups Hgh varance wthn
More informationStatistical Evaluation of WATFLOOD
tatstcal Evaluaton of WATFLD By: Angela MacLean, Dept. of Cvl & Envronmental Engneerng, Unversty of Waterloo, n. ctober, 005 The statstcs program assocated wth WATFLD uses spl.csv fle that s produced wth
More informationRockefeller College University at Albany
Rockefeller College Unverst at Alban PAD 705 Handout: Maxmum Lkelhood Estmaton Orgnal b Davd A. Wse John F. Kenned School of Government, Harvard Unverst Modfcatons b R. Karl Rethemeer Up to ths pont n
More informationStatistics for Managers Using Microsoft Excel/SPSS Chapter 13 The Simple Linear Regression Model and Correlation
Statstcs for Managers Usng Mcrosoft Excel/SPSS Chapter 13 The Smple Lnear Regresson Model and Correlaton 1999 Prentce-Hall, Inc. Chap. 13-1 Chapter Topcs Types of Regresson Models Determnng the Smple Lnear
More informationSampling Theory MODULE V LECTURE - 17 RATIO AND PRODUCT METHODS OF ESTIMATION
Samplng Theory MODULE V LECTURE - 7 RATIO AND PRODUCT METHODS OF ESTIMATION DR. SHALABH DEPARTMENT OF MATHEMATICS AND STATISTICS INDIAN INSTITUTE OF TECHNOLOG KANPUR Propertes of separate rato estmator:
More informationAnswers Problem Set 2 Chem 314A Williamsen Spring 2000
Answers Problem Set Chem 314A Wllamsen Sprng 000 1) Gve me the followng crtcal values from the statstcal tables. a) z-statstc,-sded test, 99.7% confdence lmt ±3 b) t-statstc (Case I), 1-sded test, 95%
More informationANALYSIS OF COVARIANCE
ANALYSIS OF COVARIANCE YOGITA GHARDE M.Sc. (Agrcultural Statstcs), Roll No. 4495 I.A.S.R.I., Lbrary Avenue, New Delh- 11 1 Charperson: Dr. V.K. Sharma Abstract: Analyss of covarance (ANCOVA) s a statstcal
More informationInterval Estimation in the Classical Normal Linear Regression Model. 1. Introduction
ECONOMICS 35* -- NOTE 7 ECON 35* -- NOTE 7 Interval Estmaton n the Classcal Normal Lnear Regresson Model Ths note outlnes the basc elements of nterval estmaton n the Classcal Normal Lnear Regresson Model
More informationISSN: ISO 9001:2008 Certified International Journal of Engineering and Innovative Technology (IJEIT) Volume 3, Issue 1, July 2013
ISSN: 2277-375 Constructon of Trend Free Run Orders for Orthogonal rrays Usng Codes bstract: Sometmes when the expermental runs are carred out n a tme order sequence, the response can depend on the run
More informationBasically, if you have a dummy dependent variable you will be estimating a probability.
ECON 497: Lecture Notes 13 Page 1 of 1 Metropoltan State Unversty ECON 497: Research and Forecastng Lecture Notes 13 Dummy Dependent Varable Technques Studenmund Chapter 13 Bascally, f you have a dummy
More informationChapter 5 Multilevel Models
Chapter 5 Multlevel Models 5.1 Cross-sectonal multlevel models 5.1.1 Two-level models 5.1.2 Multple level models 5.1.3 Multple level modelng n other felds 5.2 Longtudnal multlevel models 5.2.1 Two-level
More informationPubH 7405: REGRESSION ANALYSIS. SLR: INFERENCES, Part II
PubH 7405: REGRESSION ANALSIS SLR: INFERENCES, Part II We cover te topc of nference n two sessons; te frst sesson focused on nferences concernng te slope and te ntercept; ts s a contnuaton on estmatng
More informationx i1 =1 for all i (the constant ).
Chapter 5 The Multple Regresson Model Consder an economc model where the dependent varable s a functon of K explanatory varables. The economc model has the form: y = f ( x,x,..., ) xk Approxmate ths by
More informationSimulated Power of the Discrete Cramér-von Mises Goodness-of-Fit Tests
Smulated of the Cramér-von Mses Goodness-of-Ft Tests Steele, M., Chaselng, J. and 3 Hurst, C. School of Mathematcal and Physcal Scences, James Cook Unversty, Australan School of Envronmental Studes, Grffth
More informationLab 2e Thermal System Response and Effective Heat Transfer Coefficient
58:080 Expermental Engneerng 1 OBJECTIVE Lab 2e Thermal System Response and Effectve Heat Transfer Coeffcent Warnng: though the experment has educatonal objectves (to learn about bolng heat transfer, etc.),
More informationLINEAR REGRESSION ANALYSIS. MODULE IX Lecture Multicollinearity
LINEAR REGRESSION ANALYSIS MODULE IX Lecture - 31 Multcollnearty Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur 6. Rdge regresson The OLSE s the best lnear unbased
More informationPARTIALLY BALANCED INCOMPLETE BLOCK DESIGNS
PARTIALLY BALANCED INCOMPLETE BLOCK DESIGNS V.K. Sharma I.A.S.R.I., Lbrary Avenue, New Delh-00. Introducton Balanced ncomplete block desgns, though have many optmal propertes, do not ft well to many expermental
More information2016 Wiley. Study Session 2: Ethical and Professional Standards Application
6 Wley Study Sesson : Ethcal and Professonal Standards Applcaton LESSON : CORRECTION ANALYSIS Readng 9: Correlaton and Regresson LOS 9a: Calculate and nterpret a sample covarance and a sample correlaton
More informationexperimenteel en correlationeel onderzoek
expermenteel en correlatoneel onderzoek lecture 6: one-way analyss of varance Leary. Introducton to Behavoral Research Methods. pages 246 271 (chapters 10 and 11): conceptual statstcs Moore, McCabe, and
More informationCopyright 2017 by Taylor Enterprises, Inc., All Rights Reserved. Adjusted Control Limits for P Charts. Dr. Wayne A. Taylor
Taylor Enterprses, Inc. Control Lmts for P Charts Copyrght 2017 by Taylor Enterprses, Inc., All Rghts Reserved. Control Lmts for P Charts Dr. Wayne A. Taylor Abstract: P charts are used for count data
More informationSTAT 3014/3914. Semester 2 Applied Statistics Solution to Tutorial 13
STAT 304/394 Semester Appled Statstcs 05 Soluton to Tutoral 3. Note that s the total mleage for branch. a) -stage cluster sample Cluster branches N ; n 4) Element cars M 80; m 40) Populaton mean no. of
More informationChapter 6. Supplemental Text Material
Chapter 6. Supplemental Text Materal S6-. actor Effect Estmates are Least Squares Estmates We have gven heurstc or ntutve explanatons of how the estmates of the factor effects are obtaned n the textboo.
More informationOPTIMISATION. Introduction Single Variable Unconstrained Optimisation Multivariable Unconstrained Optimisation Linear Programming
OPTIMIATION Introducton ngle Varable Unconstraned Optmsaton Multvarable Unconstraned Optmsaton Lnear Programmng Chapter Optmsaton /. Introducton In an engneerng analss, sometmes etremtes, ether mnmum or
More informationLecture 4 Hypothesis Testing
Lecture 4 Hypothess Testng We may wsh to test pror hypotheses about the coeffcents we estmate. We can use the estmates to test whether the data rejects our hypothess. An example mght be that we wsh to
More informationModule 9. Lecture 6. Duality in Assignment Problems
Module 9 1 Lecture 6 Dualty n Assgnment Problems In ths lecture we attempt to answer few other mportant questons posed n earler lecture for (AP) and see how some of them can be explaned through the concept
More informationSystems of Equations (SUR, GMM, and 3SLS)
Lecture otes on Advanced Econometrcs Takash Yamano Fall Semester 4 Lecture 4: Sstems of Equatons (SUR, MM, and 3SLS) Seemngl Unrelated Regresson (SUR) Model Consder a set of lnear equatons: $ + ɛ $ + ɛ
More information