Home

1 # Winsteps Tutorial 1 Mike Linacre, instructor

1. 85 100 0 91 1 James 1 06 a 85 85 7 91 1 Kim Numbers are very useful but difficult to visualize so let s s2 iosi 32 1101 23 er 165 C8311000 91 1 Rom 1 06 1 85 100 0 91 1 William 1 11 1 87 100 0 93 2 Anne look at a picture of these measures Saef Eii Sie asi oe Cm ls Cermooo 93 2 prensa 1 11 1 94 1 2 1 19 87 85 7 93 2 Don 1 11 18 1 3 08 871 100 0 93 2 Dorothy F Click on Winsteps on the Windows task bar If you see a Winsteps icon click on it and then on mikes1 txt Let s take a look at a picture a map of the measures we have estimated On the Winsteps menu bar E SS bl est L Variable maps click on Output Tables I 929 Datinn Inartial credit orale click on 1 Variable maps 10 Table 1 0 is a text file displayed in a NotePad window Winsteps has 34 Tables and most of these have sub tables If the Table is ragged in NotePad Format Font Courier New The Table number is in the first line of the Table red box A count of persons and items 1s shown on the second line If these numbers look wrong in your own analysis then investigate your control and data files carefully TABELE 1 0 KNOX CUBE TEST mike s analysis EQUSSEWS TXT Jul 11 6 51 2007 2 CATS WINS Ctrl End takes you to the bottom of this Table INEOT 3 KIDS 18 TAFE MEASURED 35 KIDE 18 TAPS TERS 3 53 2 Ctrl Home back to the
2. Winsteps chooses the number so we will need to El eee lim Example You plan to pnnt your output file on standard paper with 60 lines per page pages are 11 remember to reset MAXPAGE 0 back to that ES oe value j Close the Help window In the Specification box Control Specification Value MAXPAGE 40 specification Yalue Click OK MAKPAGE 40 OK and again OK Cancel In your analysis window the control variable is MAXPOAGE 40 reported back to you 12 Click on Winsteps menu bar Click on Output Tables Click on 1 Variable maps The variable map Wright map is now squashed Scroll down to Table 1 1 We can now see it clearly on our screen The X s show the children left hand side and item right hand side distributions Do you notice a problem with this test There are many kids at XX XX one for each X but there are few items close to them We need items at the It is an item targeting problem For dichotomies No nearby items gt Less precision of measurement gt Larger person Standard Errors But for polytomies this is more complicated because rating scales have a wider operational range equivalent to two or more dichotomies Let s reset MAXPAGE 0 so that it has its standard function Windows Menu bar Click on Specification MAXPAGE 0 Click on ORK You can see MAXPAGE 0 on your Winsteps analysis window Let s make the Winsteps Table more publication qua
3. adds the same amount is more complicated It means defining an operation that increases the amount we have by a certain constant amount With weight the constant amount 1s one gram or one pound and the operation is piling up With length the constant amount is one meter or one foot and the operation is putting end to end technically concatenation With temperature the constant amount is one degree and the operation is heating Norman Campbell could not imagine how we could define a unit of attitude and then construct a process that would increase an attitude by a known amount Nor could the social scientists of the 1930s so they gave up Campbell measurement requires a deliberate action a concatenation Measurement requires deliberate construction Stevens Measurement is the assignment of numbers according to rule The social scientists call measures whatever numbers they happen to have acquired Example 3 minutes on the clock 1s a Campbell measurement The clock 1s deliberately constructed to concatenate equal units of time A score of 3 on a Math test is a Stevens measurement The Math test is an accidental collection of items There is no deliberate concatenation of equal units of item difficulty 18 Georg Rasch 1900 1980 Georg Rasch was a poorly paid mathematics instructor in Denmark who consulted in statistics in order to support himself He didn t know that social science measu
4. 16 Practical Challenge Here s a version of the pathway KCT Pathway chart after some adjustments using Excel s own Underfit capabilities See if you can do bette r To adjust the labels in the bubbles please install the free Excel Add in XY Chart Labeler from http www appspro com Utilities ChartLabeler htm unpad qY 210 A huge amount of meaning is squeezed into one picture The bubble chart shows the locations measures of the persons and items on the latent variable vertically These indicate the predictive validity and the construct validity of the instrument We talk about these in this Lesson It shows the behavior fit of the persons and items horizontally In Lesson 2 we talk about fit It shows the certainty precision standard error of measurement of the persons and items by the size of the bubble In Lesson 3 we talk about precision Sanse Inad aqy 587 2 0 2 How about trying differently shaped bubbles In Excel 2007 and later www winsteps com winman bubblecharts htm section Autoshapes also in Winsteps Help Close the Excel window 17 F Practical Additive Measurement Norman Campbell and the Social Scientists There was a big argument back in the 1930s The question being debated was Is psychological measurement possible The hard scientists the physicists led by Norman Campbell said No measurement requires a deliberate action a concatenation such as putting sticks en
5. additive measurement Adding one more unit means the same amount extra no matter how much there is already If you want to read about how this is done and also obtain some other insights into what measurement really means please read my paper Measurement Meaning and Morality www rasch org memo71 pdf The linearity additivity that the Rasch model constructs differs from the assumed linearity of Classical Test Theory and much of Item Response Theory IRT For more about IRT see http en wikipedia org wiki Item_response_ theory Read more about the asserted rather than constructed linearity of the widely adopted interval measurement classification of S S Stevens in www rasch org rmt rmtl11n htm Stevens Revisited You may be wondering I signed up to learn a statistical method why are we wasting time with history and philosophy Let Lord Acton 1832 1902 answer The knowledge of the past the record of truths revealed by experience is eminently practical is an instrument of action and a power that goes to the making of the future Especially in the area of social science measurement the misconceptions of days gone by continually dog our steps and we find ourselves in disputes that should have been resolved long ago Indeed you will undoubtedly encounter sceptics who will tell you the Rasch model 1s wrong or the Rasch model doesn t work Make a note of www rasch org rmt rmt103e htm T
6. not Format Data Labels or Format Data Points If Format Data Series does not display move the mouse pointer a little lower down in the bubble and right click again 34 4 Microsoft Excel Z00466WS TXT E Fle Edit View Insert Format Tools Data Window Help Oe GRY SEBS o oA E A A al bw 100 Aral A1 v TAPS Mea ures t Outfit Zst S_E Labels Entry EaI 4 4 gt i _Bubble chart Worksheet m Aa maA a Pet Gn a a t Outfit Zstd 0 SOINses f Format Data Series 182 Click on Options tab Scale bubble size to Type in a value to reduce the bubble size such as 65 Click on OK All the bubbles change size Excel rescales all bubbles by the same amount both when it originally displays the bubbles and when you rescale them And we see a much better looking pathway The diameter of the biggest bubble is about 2 2 logits vertically You may need to go back and forth several times adjusting the bubble size to get it to look right s Inse This is now your plot You can beautify the plot using other Excel functions for coloration layout etc See Bond amp Fox Chapter 3 for a further explanation of this pathway 35 Appendix 5 Changing the text appearance in NotePad 185 1 87 190 Oops A Table may display too big or ragged or wrapped We need to display this text in a fixed space font such as Courier New and also
7. H ing problems S GG 99 a aoe E Click on Plots eave i Click on Bubble chart Pathway a ea Plot 30 TAP DIF Plot 31 KID DPF Plot 33 KID TAP DGF DIF amp DPF 15 Fit statistic type utfit unweighted C Infit informatio weighted Fit statistic expresgion standardiz fa it ZStd KMean sqWare interval scaled log guare chi square d tf 85 Click on Persons and Items to V check or tick oa aa Gee Eee v Persons Rows in data them EES Columns in data Display bubbles Cli ge a8 yweasures naa Fit A ick on OK C Measures horizontally Fit vertically Cancel Help Click on the Label button we want to see the ee oe ow are the plotted datapoints to be labeled person and item labels displayed ntrynumber Hep Label Entry Label Cancel Only part of the label a Chart processing is underway Loading winexcel exe 87 On the Winsteps Analysis screen it tells us that Bubble Processing Bubble Chart Bubble Chart process launched 88 After a few moments the Bubble Chart pathway plot is displayed by Excel There are many different versions and options in Excel so your plot may not look exactly like this You have full Excel editing capabilities for this plot seinsesyyj Most importantly Excel has a mind of its own and has displayed the bubbles with the incorrect sizes See 177 Appendix 4 Changing the size of the bubbles
8. Ty 9 eZ C9 CG TG 3 ivy 3 9 af ES U a Fle name ices r Jy Save as type All Files x s Output Tables Output Fies Batch Help Specfication Plots Dec 21 0 15 2008 C Winsteps time limited examples sis QutputTables QutputFiles Batch Help Spec Edit Control File C Winsteps tme imited examples mikes 1 bet Edit create new control file from C Winsteps time imited EXAMP 45 The Control and Data file displays in a NotePad window It is a text file You can change it with WordPad Word etc We need to display in Courier New with a reasonably small font If NotePad does not do this see 184 Appendix 5 The top section blue box contains the control variables They are variable value You will recognize many of them for instance TITLE The control variables end with amp END but do notice that there is no identification of the number of persons or cases In the Control file you do not need to tell Winsteps how many persons there are Winsteps discovers that for itself Then come the item labels green box with one item label per line in the same order as the columns of item responses You will recognize that the first item is 1 4 The item labels end with END LABELS or END NAMES Then comes the data red box Each line has a person identification label e g Anne and a string of responses 1100 Oops If you see that the item re
9. log 1 1 log 1 the logarithm of 1 is zero so log 1 0 this is the same as saying x 1 32 the logarithm of plus infinity is infinity log 0 the logarithm of zero is minus infinity log 0 o0 the logar thm to the base e of e is 1 loge e 1 the logar thms of negative numbers don t exist log 1 Oops 33 1 78 Appendix 4 Changing the size of Bubbles in Excel Bubble Charts Pathway maps This section is tricky The Excel plot displays The bubbles are located vertically by measure and horizontally by fit Their diameters are supposed to be twice their Standard Errors of measurement But Excel has chosen its own bubble sizing Click on the Worksheet Tab below the plot The standard errors are in Column D for the persons and Column I for the items Look at the biggest bubble item 1 3 2 4 1 3 Its Model S E is 1 07 so that the bubble diameter 2 S E should be 2 14 Click on the Bubble Chart Tab Look at the biggest bubble Its diameter is currently about 3 1 on the vertical axis on my screen That may be different on yours The bubbles is too large 3 1 on the vertical axis instead of 2 1 This is because Excel plots relative not absolute sizes Let s use the Excel functions to correct the plot If you are familiar with Excel turning on Gridlines helps with this Right click on the bubble Click on Format Data Series
10. Click on Refresh Data Display The members of our person sample are called KID meaning child The control variable name is PERSONS The location of the person identifying label in the data spreadsheet is controlled by NAMEI1 and NAMELEN GTH Variable names can be abbreviated or lengthened and can be upper or lower or mixed case PERSON PERS person Person etc Let s experiment change NAME 1 from 1 to 10 and change NAMELEN from 9 to 15 click on Refresh Data Display The blue person identifying stripe now overlaps the green item response stripe This is valid It can be helpful to include the responses in the person label so that the responses always appear when the persons are reported Reset to the original values change NAME 1 from 10 to 1 and change NAMELEN from 15 to 9 click on Refresh Data Display The control variables for the items are ITEM for the name give to the items ITEM 1 for the first item response column in the spreadsheet NE for the number of items in the test or instrument To find out more about the control variables on the menu bar click on Help when the Help screen displays click on Contents PERSONM A data row isa KID NAME First person label column 1 NAMELEN Person label length 4 MAMET First person label column w NAMELEN Person label length MAKE First person label column 1 MAMELENM Person label length 4 ITEM 4 data c
11. a smaller font so everything fits in the window On the NotePad menu bar Alt O or click on Format pull down menu Alt F to change the Font Font Courier New Font style Regular Font size 7 You can type in values not listed Click on OK The Table now displays neatly Alter the Font size if the Table is too big or too small Windows Start Click on Run Type in regedit Click on OK Registry Editor Click on the in front of HKEY CURRENT USER Click on the in front of Software Click on the in front of Microsoft Click on Notepad For the type face Double click on IfFaceName Type in Courier New or Letter Gothic Line Click on OK For the font size Double click on iPointSize Click on Decimal Type in 80 for point size 8 multiplied by 10 Click on OK Close registry Click on top right 36 ENTRY RAW Font Courier New O Comic Sans MS O Consolas MODEL INFIT INUMBER SCORE COUNT MEASURE S E OBS EXP ACT Font style OUTFIT PTMEA EXACT MATCH MNSQ ZSTDICORR OBS EXP ACT 4 11 9 01 00 40 5 65 0 Watch a rat 2 30 613 62 Poel 05 52 7 68 1 Find bottles and cans 1 50 1 23 5 14 94 6 93 4 Go on picnic 1 08 4l 301 90 5 88 0 Go to zoo 42 54 1 61 1 Watch bugs 45 66 5 83 71 Go to mus
12. at so far Applying na All questions are based on the Lessons or free downloaded documents The books are for those who wish to do additional study on their own In B amp F Ist Edn Chapters 1 and 2 and sections of the paz Preface correspond to what we have looked at so far oere In Best Test Design Wright amp Stone chapter 1 is the place but it is much more mathematical than our discussion here J Free PDF Wu M amp Adams R 2007 Applying the Rasch model to psycho social measurement A practical approach Educational Measurement Solutions Melbourne www edmeasurement com au Learnine html Free PDF MEASUREMENT ESSENTIALS Wright B D amp Stone M H 1999 Measurement and Edition Essentials www tasch org memos htm measess 28 p K QO Appendix 1 Displaying file name suffixes 149 On your desktop click on My Computer or any Pr folder ni My Computer 150 XP Click on Tools 151 XP Click on Folder Options 152 Vista 1 Click the Layout button to the left of the Views button 2 Click Folder Options Classic Menus v lol Preview Pane UE Reading Pane v GL Navigation Pane Folder Options Advanced Search Options Chose I i 153 Click on View Folder Opt General View File Types Tasks C common tasks il Use classic Browse folders a Open each inth Open each folder in its 154 Un check Hide extensions for know
13. may be because your control file is not in Text with It is easy to miscount the ITEM1 column Scroll to the top of the Winsteps scree Input in process mput Data Record 1234567890123456789012345678 Richard M 111111100000000000 ap aI a 35 KID AP marks the Name1 1 column position with Al marks the Item1 11 column position with 3 ITLEN maximum length AN marks the Ni 18 column position with oding of Example 1 The string of 56 items is contained in columns 20 to 75 of your data file ITEM1 lt 20 respons p e to item i in column 20 for 56 itens one column wide the standard SWWIDE columns per response I CODES Valid codes fo NI Number of Items VIDE columns per response 1 CODES Valid codes 01 This Window lets you enter the item label information 1 4 means tap onto cube 1 and then onto cube 4 As you look down the list you can see that the tapping patterns become longer and more complicated Click on Item Labels OK to close the Window Let s now do a Rasch analysis On the Setup menu bar click on Winsteps We changed the Title so Click on Save control with data file and exit to Winsteps Analysis On the Save screen Type in a new file name It can be whatever you like I m calling mine mikes1 txt Click on Save Notice that the suffix is txt All Winsteps control and data files are standard text files with line feeds They can be edited and created
14. top pe of Here is sub table 1 0 a E ee In the blue box on the left are the linear measures like a meter rule We ll talk about what these are very soon In the green box are the children located by their ability In the red box are the items located by their difficulty When a child aligns with an item then the child is predicted to have a 50 chance of succeeding or failing on the item For instance at 2 we predict child Dav to have a 50 chance of succeeding on item 1 4 3 The labels Dav and 1 4 3 have been abbreviated so fit this sub Table We could look at the data file to find out what actually happened but the purpose of measurement is to make inferences 1 e be useful beyond the data So based on these data we predict that children like Dav have a 50 chance of success on items like 1 4 3 Amn Boag Dan Dac Hal Jan Jag Lig Mar Pat Bie The We can already see improvements to make to this version of the Knox Cube Test Children in the yellow box near 0 have no items targeted at their ability level mauve And at 5 at the top there are 4 very difficult items but no children So this version of the Knox Cube Test needs more middle difficulty items and fewer very hard items 1 3 2 3 4 1 l 4 3 2 1 4 11 61 D More Readable Output Maps 62 Let s look at the variable map again to find out o about the child to 1tem targeting 7 EEY Click on Winstep
15. 21x Save in NO examples exam 17s txt exampled txt examsubs txt ket txt labels txt mikes 1 txt sf txt template txt ZOUS48WS TXT exam 10a txt exam 10b txt exam10c txt examil txt exam12 txt exam12hi txt exam12lo txt exam 13 txt exam14 txt exam14b txt exam14c txt exam 14dt txt exam15 txt exam16 txt exam 17r txt File name bond4control be Text Files be x Save as type a z Starti 10 Number of items NAMEL 12 Sta NAMLEN 4 Len ch want erson Label variables b Person 1E END Item Negation t 4 amp 3 C12W3 labels follow co egate Disjunction END NAMES 1111111111 001 1111111111 002 130 Then the Winsteps control and data file displays Itisa aS SSS text file in the familiar format You can edit it if you fata eke neta othe EAE NA Sra Close the bond4control txt window 1 32 Let s analyze the file we have just created 1 Excel Input for Winsteps On the Excel Processing for Winsteps Edit Click on Launch Winsteps Select Excel Construct Launch file Winstepe file Winsteps 133 The usual Winsteps analysis screen displays with the i bond COMES Fle Edit Diagnosis Output Tables Output Files Batch Help Specfication Plots control file already active WINSTEPS Version 3 65 1 Jun 22 19 58 2008 WINSTEPS expires on 9 1 2008 Current Directo
16. 4 Winsteps Tutorial 1 Mike Linacre instructor June 2012 Tutorial 1 Software operation and basic concepts Welcome e Winsteps software installation and operation e Basic measurement and Rasch concepts e Simple dichotomous analysis e Constructing data files This lesson includes a quick run through of the operation of the computer program Winsteps If you run into difficulties please ask questions and get guidance on the Discussion Forum No question is too dumb http www winsteps com forum I am also including important aspects of theory and practice so please go through the material carefully Think of yourself as the star of this movie You are reading the script and I am the director I can point you in the right direction but it is up to you to win the Oscar Unfamiliar words Rasch measurement has its own technical words Please see the explanations at http www winsteps com winman glossary htm You can click on the blue links to access the Internet c3 A Introductory Video Please view a few minutes of a movie introduction to Rasch and Winsteps by yours truly it is SOMB so may take a few minutes to download http www winsteps com a intro wmv This 1s a big file Add it to your Media Player playlist Or you may need to use a free download manager such as FDM Lite This movie was originally requested by the energetic Rasch folks in Hong Kong a great idea The movie contains slides separately viewa
17. I encounter an item of exactly the same difficulty as log 1 0 B Di my ability I can t predict whether I m going to Bn Di succeed of fail My prediction would be like tossing a coin Heads or Tails 21 111 If I m sure to succeed then my probability of success Paii Paio 1 is and my probability of failure is zero My logit Paii 1 Prio 0 ability will be plus infinity relative to any item of loge Pnit Paio log 1 0 finite difficulty log B Di Bn 112 If I m sure to fail then my probability of success is 0 Pai Pio 1 and my probability of failure is one My logit ability Paii 0 Prio 1 will be minus infinity relative to any item of finite loge Pnit Pio loge 0 1 difficulty log 0 Ba Di By 00 113 Suppose that I generally succeed 3 times out of 4 in hitting a target with an arrow Then my probability of Paii 0 75 success is P 3 4 0 75 And my probability of Paio 0 25 failure is 1 P 1 4 0 25 Then my odds of success is Pri Paio 3 P 1 P 0 75 0 25 3 loge Pnit Pnio log 3 1 1 And my ability is log 3 1 1 logits more than the 1 1 B Dj 1 1 target is difficult 114 Extending this idea we can draw a picture of the relationship between ability relative to an item and probability of success the relationship is called a logistic ogive You can see on the plot that a zero logit difference dot
18. Pad window If the Table text is wrapped or ragged please see 184 Appendix 5 If you prefer to use a different text editor see 158 Appendix 2 of this document AP STATISTICS MEASURE ORDER The Rasch measures are in the red box headed MEASURE The raw scores are in the blue box headed TOTAL SCORE We ll talk more about measures in a few minutes On the Windows taskbar usually on the bottom of your screen click on 2 Winsteps Then click on Winsteps mikes 1 txt on the Windows task bar On the Winsteps menu bar click on Output Tables ad click on 17 KID measure e 2 2 General Keyform 2 5 Category Averages 3 1 Summary statistics 10 TAP column fit order 6 KID row fit order 13 TAP measure 17 KID measure rar ABLE 17 1 KNOX CUBE TEST Mike s Analysis ZOU2S58WS TXT Dec 21 0 15 2008 Winsteps Table 17 the person measure Table displays INPUT 35 KIDS 18 TAPS MEASURED 35 KIDS 18 TAPS 2 CATS WINSTEPS 3 67 1 You can see it has the same format as the item measure Table Table 13 We know the difference between items moves wert overs er smasoae EXACT MATCH and persons but Rasch analysis doesn t In Rasch analysis sf cagas al 38 al 69 681 28 7 S r 951 36 1 5 751100 0 89 1 Blaise persons and items are usually treated the same way 0 ee ee ee a 98 1 74 i P J e 81 78 6 88 7 Walter 1 06 1
19. TA In a dialog box Winsteps asks if we want to enter the Setup procedure Yes we want to this time So Click on Control Data Setup Procedure Don t ask again The Winsteps Control File Set Up screen displays This is one of the many ways of constructing your Winsteps a RSON A data rowis a Person ITEM A data columnis a ftem control and data files NTEN Festimet T XWIDE columns per response f Winsteps Control File Set Up We will use a different way but this is the easiest one to get started for simple analyses We ll look at one of the example data files Please click on Files Click on Read control and data file The directory listing of c Winsteps time limited examples displays This contains the standard Winsteps examples They begin exam Read in control and data files Lz x The first data file is Bond4 xls It is an example from the book by Bond amp Fox Applying the Rasch Model They begin Bond amp Fox PU call this book B amp F Click on exam1 txt If you only see exam1 but want to see exam I txt please tell Windows to display suffixes See Error Reference source not found Appendix I toward the end of this document Click on Open E exams txt 2 exam9 txt E exam9dat txt B exam 10a txt B exam10b txt EE exam 10c txt B examii txt E exam12 txt S lexam 12bat bat fe lexam12cmd cmd E exam 12hi txt E exam 12io txt S e
20. adding powers We can do this with non integers 4 And powers work for negative numbers 2 2 4 2 27 2 27 2 9 5 So we have the general rule of powers of 2 166 This works exactly the same way if we change the 10 base value from 2 to 10 o 10 X Y 10 10 10 10 4140 14120 9 2 Pe 1 4142 2 square root 2 167 Now x and y are called exponents and 10 the X Z X x y x y base So this is an exponential form X Y 10 10 10 3 168 We can rewrite this exponential form into logio X logio 10 x logarithmic form Log is short for logio Y logy9 10 y Logarithm logio X Y logio 10 x y 169 This is very useful We can transform a multiplication X Y into and addition log X log Y This saves a huge amount of effort when the multiplication is done by hand and was why logarithms were invented around 1617 log1o 10 logio 10 E x y m logio 10 logio X T logio Y x y logio X Y 170 In Rasch work we use a special base called e x This has the value 2 718 And the logarithms a are 2 3026 logio X loge X logio X 0 4343 log X then called natural or Napierian logarithms 1 Once we alert the reader what base we are using log X log Y log X Y e from here on we can omit it 172 Here are some important facts about logarithms log 1 log 1
21. and ignored If you are not sure what codes are in your data file then click on Scan data for codes Experiment by blanking out the CODES value and clicking on the green button Click on the green button Item Labels Enter Edit 6 lt e gt A amp FF Hide Back Forward Home Print Options Contents index Search Favorites Control and data file setup window This interface simplifies setting up Winsteps control and data files It can be used for ent specifications or for constructing the specifications that match existing data 2 Control Variable Index by i E Control variables from Spe 2 output Table Index E Output Graphs and Plots Im 2 output Files Index Select Setup Procedure on Winsteps startup or use the Setup pull down menu Weicome to Winetape Would you like help sening up your analysis F Dont ask ogoni sorn instrectons ony No If you are already in Winsteps then on the menu bar Data Setup Start Control and data file setup Ctrl D Exit to Control and data file setup This displays the Control File Set Up screen a opics E Problems and Error Message mo 7 ITEM1 column number of first response required ifes the column position where the response string begins in your data file record a String begins in the new record formatted by FORMAT If you have the choice put the person identifiers first in each record and then the item re one column Error messages regarding ITEM1
22. ares are people The vertical axis is the measure the location on the latent variable The size of the circles and squares indicates the precision standard errors of the measures along the vertical axis the latent variable The horizontal axis is the fit Overfit on the left the responses are too predictable underfit on the nght the responses are too unpredictable The fit indicates the accuracy of the measures We will discuss this in Lesson 2 This Figure was drawn by an artist for B amp F We ll have Excel do approximately the same thing To keep the pathway from being too crowded let s select a few people and items to display elp Specification Plots EXCEL SAS 5P55 Graphs Data Setup put examples 20U018WS TAT Winsteps Menu Bar Click on Specification In the Specification box type or copy and paste from here idelete 4 5 10 15 OK and again ia OK Cancel Click on OK and again Your Winsteps Analysis window reports that idelete 4 5 10 15 4 items are selected 4 items for reporting 4 5 10 15 CURRENTLY REPORTABLE TAPS 4 ontrol Specification Value In the Specification box type or copy and paste pdelete 1 5 Click on OK specification Value done pdelete 1 5 OK and again This has selected the first 5 children 1 2 3 4 5 pdelete 1 5 CURRENTLY REPORTABLE KIDS 5 bs RS Winsteps Menu Bar ene Graphs Date setur HI LE L H H
23. arranged by easiness TI m trol and Data File Set i E asia Note These Tables can be copied and pasted into Excel spreadsheet By The Control and Data P s relevant control vari able S You can click on them Examples of Contrgy nd D rape opin e how you want on your screen by adjusting font gt Control Variables then use your PrintScreen key to make a copy of the screen Paste int gt The lterationcreen to find out what they are ab out Click on 2 Output Tables Items arranged by measure Look for the hierarchy of item names ti 2 Table heading at the bottom to hardest at the top MAXPAGE OED e 3E P Table 1 1 Distribution mi 2p ape ae 2 Table 1 4 Polytomous d 3 X Sx MAXPAGE same thing as MAXPAG because only the first few letters are needed sets the SSS number of lines per page Sau 8 8 Contents index Search Farvartes MAXPAGE the maximum number of lines per page 0 no limit 9 So let S set MA X PAGI 4 2 GAPFROM location of aj For no page breaks inside Tables leave MAXPAG 0 currite coza Giz0 J HEADER display or sa if you prefer a different number of ines per page of your output file to better match the requirements of he default 1S MA X PAGE 0 which me ans p naD o for processor give that value see Using a Word Processor or Text Editor in Section 2 if you prefer to ha 2 HLINES beading lines all plots at their maxomnum size leave MAXPAG 0 ILE t ox f
24. ble at http www winsteps com a slides htm If you have the current version of Winsteps then you only need the Course data files Please download them from Winsteps time limited http www winsteps com a course data zip Please download and run WinstepsPasswordInstall ecxe see Aen Do you want to run or save this file Name WinstepsTimeNmitedinstall exe From www winsteps com While files from the Internet can be useful this file type can potentially harm your computer If you do nottrust the source do notrun or save this software What s the risk Save the installation file WinstepsPasswordInstall exe to your desktop Double click on it if you need to re install this software You can delete it when you have installed Winsteps To install Winsteps Run the downloaded file or double click on the WinstepsPasswordInstall exe on your desktop The installation screen for Winsteps displays The installation password is copy and paste in your purchase receipt Then click on Next Please install Winsteps in C Winsteps or the folder of your choice Then click on Next Click on Next until the Installation is finished Click on Finish to launch Winsteps for the first time If you run into difficulties during the installation please refer to http www winsteps com problems htm You can also launch Winsteps at any time by double clicking the short cut on your desktop Or by dragging your contro
25. creen we can launch it Welcome to Winsteps from Data Setup green ellipse Would you like help setting up your analysis Now click No Data Setup Excel SAS Procedure SPSS STATA 125 On the Winsteps menu Click on EXCEL RSSST Click on EXCEL R statistics SAS SPSS STATA Your procedure is the same as Excel Your variable names are not in row 1 but the usual ones 126 When the Excel dialog box displays Click on Select Excel file se aver ee In the file dialog box Click on Bond4 xls Click on Open There are also datasets in the other formats for you to experiment with b 1n ma COTTE e Places I Open as read only 24 127 After a few moments the labels in the first row of the 128 Excel spreadsheet display Scroll up and down to see them They are shown here in the red box Sorry if you don t have Excel on your computer this won t happen Look down the list of column labels Some are person variables For instance column A Some are item labels We need to tell Winsteps which are which We do this by copying and pasting the column information into the correct place in this control dialog The person variable columns go under Person Label Variables blue arrow and the item columns go under Item Response Variables green arrow Do not change anything else OK so go ahead and copy and paste This is what happens when I do it Item 1 is in column B of the E
26. d to end to measure length or piling bricks one on top of another to measure weight and you can t concatenate people s heads The soft scientists the social scientists led by Stanley Stevens could not answer that so they devised their own definition for a new kind of measurement Measurement is the assignment of numbers to objects or events according to rule Stevens S S 1946 On the theory of scales of measurement Science 103 677 680 The social scientists call measures whatever numbers they happen to have acquired This has caused confusion ever since For social scientists any number is a measurement provided you can imagine some rule that it follows For everyone else measures have to conform to strict objective criteria But Georg Rasch solved the problem He showed how the strict criteria of the physical scientists can be applied to social science by means of Rasch models which Georg Rasch called Models for Measurement Let s go back to the debate with Norman Campbell He laid out the philosophy underlying physics in his book Physics The Elements Measurement is central to physics and Norman Campbell a practical man took an operational view of additive measurement To paraphrase Measurement means that adding one more unit adds the same amount extra no matter how much there is already Adding one more unit means the simple addition of 1 to the measurement number But
27. ded in the Person and Item variable lists wil Click on Construct Winsteps file when completed Item Response Variables Do not delete this line item variables on left s Person Label Variables Do not delete this line person variables on left Other Variables ignored Item Response Variables Person Label Variables Person 001 Person 001 Negation to negate identity 1 Reciprocal to negate identity 1 Implication 1 Incompatibility 1 Multiplicative compensation 1 Correlations 1 Correlations 1 Correlations 1 Do not delete this line item vari Negation to negate identity 1 Reciprocal to negate identity 1 Implication 1 Incompatibility 1 Multiplicative compensation 1 Correlations 1 Correlations 1 Correlations 1 Conjunction 1 Disjunction 1 Do not delete this line person var Other Variables ignored Variable Label First Cell Value Person 001 A B C Negation to negate identity 1 Reciprocal to negate identity 1 ee De ee ra E Excel Input for Winsteps Edit Control file Gorstuct z Data file Witsteps fle Choose t Ma Aiables listed below under Other Variables that you want to Cop Write Winsteps control and data file Num The Con Cli B c D E E G H I J K A Awp Ite ty Move y y te 5 e otoy a
28. eum 47 78 4 74 3 Grow garden 50 78 4 77 1 Listen to bird sing 51 47 3 59 0 Look in sidewalk cracks 511 60 8 57 3 Make a map SCORE COUNT MEASURE S E 2 x Type the name of a program folder document or Internet resource and Windows will open it for you Programs 2 Documents Settings Search Help and Support A Windows XP Home Edition ayy monanuwnuny tir H E MSPaper E MsvsDG es Multimedia E Narrator H E NetDDE ay Office Genuine Advantage EJ Outlook Express 2 PCHealth H E Photo Fditor Courier New aR nrinn J MovieMaker MPEG2Demultiplexer H E MS Design Tools H E MS Setup ACME H E MSDAIPP H E MsDetect H MSE J MSHandwritingTIP H E MSPaper C MSVSDG E Multimedia C Hexadecime foal Ntbackup 193 If you have a problem and need to send me a picture of what is on your screen Press the PrintScreen key on your keyboard This copies a picture of your screen on to the Windows clipboard 4 Open a new Word document Then Paste Ctrl v the clipboard into the document Save the document Attach it to an email to me Be sure to tell me the exact section in the Tutorial where the problem happens 37 Appendix 6 Print Screen then email in case of problems E A TENTAR T EAG SE Fle Edit View Insert Format Tools Table Window Help vi2 B z u E WINSTEPS Version 3 67 0 Dec 18 1 28 2008 W
29. gories 0 and display a These are for item 4 1 3 4 but they look the same for all dichotomous right wrong items B There s much much more to see but let s make it easier for you to set up your own data for Winsteps So close all windows You may see the WINSTEPS closing dialog This is a Do you want tof lose all output windows because you are closing the Winsteps analysis window for th closing analysis while Tables are displaying No Hep Click Yes because we want to close everything Yes and from now on No and from now on 23 121 H Winsteps Control and Data Setup with Excel R SAS SPSS and STATA 122 It really simplifies Winsteps control data file set up if E4 Microsoft Excel Bond4 xls you already have the response level data on your disk I fhe Bile Edit View Insert Format Tools Data Window Hel in a convenient form a Slo Let s start with an Excel spreadsheet Here 1s the layout One row for each person One column for each person identifying variable One column per item The first row has the identifying labels Here s an Excel spreadsheet for B amp F Chapter 4 It has one person identifying column A and 35 items 1 1 columns B AJ 1 0 1 1 P Double click on the Winsteps icon on your desktop 124 We don t need to see the Welcome dialog every time Click on Don t ask again Winsteps Welcome If we need the Data Setup s
30. h Help Specification Plots Ex WINSTEPS Version 3 67 1 Dec 21 0 15 2008 WINSTEPS expires on 3 1 2009 Current Directory C Winsteps time limited examples Name of control file C Winsteps time limited examples mikes1 txt Report output file name or press Enter for temporary file Extra specifications if any Press Enter to analyze CJ mikesi tct Name of control file C Winsteps examples mikes1 txt Report output file name or press Enter for temporary file Ctrl 0 for Dialog Box Extra specifications if any Press Enter to analyze porary Workfile Directory C DOCUME 1 Mike LOCALS 1 Temp Input in process Input Data Record Adam H 1111111000000009000 P I N H re are the 35 person response strings CONVERGENCE TABLE ikesi txt Output examples ZOUS24WS TXT YTDEM DON HAY 0 HAN MEASURES STRUCTURE Control Winsteps examp ITERATION KID 3 5264 2 0714 8243 35 INPUT 35 MEASURED OUTFIT SCORE COUNT MEASURE ERROR IMNSQ 2STD OMNSQ ZSTD 6 9 14 6 19 1 14 99 2 68 1 S D 2 1 8 1 97 32 REAL RMSE 1 18 ADJ SD 1 58 SEPARATION 18 INPUT 18 MEASURED 16 9 34 6 66 74 12 9 8 3 48 21 77 ADJ SD 3 39 SEPARATION 4 41 CODES 61 Measures constructed use Diagnosis and Output Tables menus 135 TAP measure 14 TAP entry Table 13 shows the tapping items in measure order with 23 5 8 Sue ain SS ae the most difficult at the top They are displayed in a cece Note
31. he Rasch Model Cannot Be Disproved as a resource for such occasions 19 100 G The Rasch Dichotomous Model Georg Rasch presents several mathematical Georg Rasch writes his model models in his book Probabilistic Models for Some Intelligence and Attainment Tests 9 v Chicago 1980 His model for dichotomous EL 6 right wrong yes no present absent responses by persons to items has become known as the Rasch Wikipedia writes his model model This is our starting point and is the model that we used to analyze exam 1 txt the Knox Cube Test Georg Rasch wrote his model in multiplicative form using Greek letters Later authors wrote it in exponential form also using Greek letters But both of these obscure the essential additive process so I prefer to write the model in log odds form using the more familiar Latin Roman letters The Rasch dichotomous model specifies the probability P that person n of ability Bn succeeds on item 7 of difficulty Dj Success means exhibits more of our intended latent variable Failure means exhibits less of our intended variable So we must score the observations in accordance wit this intention no matter what values are assigned to the observations during data collection h Log odds of person n succeeding on item 1 Ability of person n Difficulty of item 1 Log is the natural logarithm if you would like a quick refresher abou
32. imes called the 1 PL a a a IRT One Parameter Item Response Theory tem Response Theory Aspect Rasch Dichotomous Model One Parameter Logistic Model model This is because these models have a superficial mathematical similarity but they also have Abbreviation Rasch PLIT also 1PL a fundamental conceptual difference the Rasch model Pesci Dkkidontee Desi Compara sp deliberately implements the properties of additive Motivation person ably sides and egprosafon tothe Normal Ogive distribution free item difficulty Model of LL Thurstone D N Lawley measurement The data must conform to the Rasch estimates ona inear latent variable FM Lord model if they are to support additivity The 1 PL IRT Person nof aii Bo ee Persons objects tial model of Frederic Lord is a hoped for description of iS A a set of data If the data don t fit it then another model is tried http www rasch org rmt rmt193h htm tems agents prompts tem offic D or EPAR probes multiple choice Normaly distributed person sample of Person v Greek nu of ability B in ability distribution 0 conceptualized as ani N 0 1 in probits incidental parameters item 1 Greek iota of difficulty 8 in See also http www rasch org rmt rmt6 la htm That s the end of the Lesson Well done 2l 142 J Supplemental Readings on Rasch Measurement 143 In B amp F 2nd Edn Chapters 1 and 2 correspond to what we have looked
33. ing patterns There is more information at Hold down shift key and please click on www trasch org rmt rmt133 htm to open the webpage in a new window www hyperlinks may not always work from this PDF file If necessary copy and paste the link into your Internet browser a i s ia z a Let s see what Winsteps needs to know about your data First off is TITLE The Winsteps control variables are identified as a word followed by Here the TITLE is KNOX CUBE TEST This will appear on the top line of each report output Table Let s personalize this a tiny bit Winsteps Control Fi Type your name into the Title box TITLE Reporttitle is Look down at the data spreadsheet The person identifying information is in columns 1 to 9 These are highlighted with the blue stripe In column 9 is M or F This is the person gender indicator The item responses are in columns 11 to 28 There are 18 items they are indicated by the green stripe The observations are 1 for success and 0 for failure in repeating Dr Knox s tapping pattern Observation a response by a person to an item To see the item label Position the mouse pointer on the green stripe line between columns 11 and 12 Hold down the left mouse button Drag to the right gt The label for the first item is 1 4 This means Tap on the top of cube and then tap cube 4 To restore the look of the spreadsheet
34. insteps Welcome Welcome to Winsteps Would you like help setting up your analysis Import from Text File Help Dan Sony Excel SAS Instructions Ppke Paste as Hyperlink Clear Del Select All Ctri A SPSS STATA Find Ctrl F cA New Message gt File Edit View Insert Format Tools Message Help Jal x ey Od H Send Undo Check Spelling Attach Priority Sign Fro Someone somewhere com x E To Someone somewhereelse com GA ce Subject Look at my new sig Arial im 10 m
35. king for Failure means less of what we are looking for The difference between Success and Failure is qualitative The qualitative ordering of these different qualities 1s shown by scoring them 1 and 0 1 means indicating more of the latent variable 0 means indicating less of the latent variable Standard Rasch item scoring Success 1 more of what we seek Failure 0 less of what we seek what we seek is the latent variable Rasch models analyze qualitatively ordered data These data can be found everywhere J Baand D are distances in logits along the latent variable relative to the local origin A latent variable is something which we can have more or less of but which we cannot measure directly It is a variable such as mathematics ability or patient quality of life We conceptualize it to be a straight line marked out in equal interval units This line is infinitely long We can always imagine something or someone with more of the attribute than anything or anyone we have encountered so far and also something or someone with less of the attribute We conceptualize each observation in the data to indicate less or more of this latent variable Logits are log odds units Look at the Rasch equations log Ppi 1 Pni Bn Di On the left is loge this means the natural logarithm If you don t know abou
36. l file onto the icon File Download BAA Download Complete tepsTimeLimitedinstall exe from www winsteps com B winsteps time fimited Setup Installation Password No need to uninstall previous versions of Winsteps time limited Please type the installation password into the box below and click Nextto continue Installation Password Cance B Winsteps time limited Setup i x Installation Folder Where would you like Winsteps time limited to be installed Winsteps time limited will be installed in the folder directory shown in the box below To install in a different folder type in the new path or click Change to select another folder Click Next to continue Install Winsteps time limited to C Winsteps time limited D winsteps time limited Setup Installation Successful The Winsteps time limited 3 65 1 installation is complete It will now launch to test that itis properly installed Test it with the Knox Cube Test data Winsteps Welcome box click on No tput file Press Enter pedifications Press Enter Winsteps time limited 13 C Running the Winsteps Program 14 The main Winsteps window displays I WINSTEPS At the top of the screen 1s the Winsteps menu bar Winsteps Welcome Welcome to VYinsteps Would you like help setting up your analysis Control Import from Text File No Hel Data Setup Excel SAS Instructions P Procedure SPSS STA
37. lity Winsteps menu bar Click on Specification In the Dialog Box click on Help In Help find ASCII There are three options ASCII Yes this produces the Tables we have seen ASCII No this produces the Tables in the old MS DOS format It requires the Letter Gothic Line font installed with Winsteps ASCII Webpage this produces webpage output Let s try the Webpage 13 TABLE 1 1 KNOX CUBE TEST ZOUZ16WS5 TXT Jul 27 0 51 2007 INPUT 35 KIDS 18 TAPS MEASURED 35 KIDS 18 TAPS 2 CATS WINSTEPS 3 63 XX X X W XX J5 XX T X Y X X OK KIDS TABS Control Specification Value specification Value MAXPAGE 0 OK and again OK MAAPAGE 0 Se fe ton it File Batch Hel Plot cel 24 21 05 200 8 pS tim imited examples amI txt Press Enter for Dialbe iples examT7 txt e a S A Hide Back F Forward Home Contents index Search Favorites ASCII characters Yes Title PSR oded drawing characters can produce prettier looking 2 Control Variable Index ASCIl Yes use ASCII characters the standard 2 Control Variable Index b This option is always available 2 Control variables from s ASCII No use MS DOS box characters for dray Output Table Index This option is always available Output Graphs and Plots ASCll Webpage use HTML characters for draw 2 Output Files Index This option is available from the Output T Introductio
38. n I Installation and Frecuti Recommended typefaces Menus m control and Daba File Se ASCll Yes ASCI I Yes Letter Gothi alphabetic 1 acter Ha ASCII characters 2 ASYMPTOTE item upper BATCH Batch mode ana Winsteps Specification box type ASCII Webpage Click on OK Click on Table menu Click on 12 TAP item map Table 12 2 displays It is a webpage displayed by Internet Explorer or your web browser Table 12 is like Table 1 but the item TAP labels are shown in full on the right hand side The X s on the left are the person abilities You can copy and paste this into Microsoft Word Then highlight the text there and change the font SIZe You can use the ASCII options whenever you want to but let s return to the standard one Winsteps Specification box type ASCII Yes Click on OK 14 Control Specification Value Specification Value ASCH VYfebpage OF and again OEK Output Tables Output Files E 12 TAP map TABLE 12 2 KNOX CUBE TEST ZOU998WS TXT Ja INPUT 35 KIDS 18 TAPS MEASURED 35 KIDS 18 TAPS 2 CATS KIDS MAP TAPS lt more gt lt rare gt 4 1 4 2 3 1 4 1 4 3 1 2 4 Control Specification Value opecification Value ASCH Wes OF and again OF E Pathways amp Bubble Charts 79 Bond amp Fox have popularized pathway charts There s one on the front cover of their book Here it is The circles are items The squ
39. n file 9 Hidden files and folders O Do not show hidden files and folders Show hidden files and folders Hide extensions for known file types Hide protected operating system files Recommended Launch folder windows in a separate process C Managing pairs of Web pages and folders Click on OK 29 157 Suffixes will now display in folder file lists a O 9 B A m Address jo C FACETS examples gt Go 30 15 159 In the Winsteps main window Click on Edit Then Click on Edit initial settings In the top box type in the path to your preferred text editor or use the Browse button to locate it I ve entered the path to Wordpad Then click OK to save this setting For NotePad please blank out the Editor box Winsteps Initial Settings x zank oui tor Notel ad C Program Files Microsoft Office Office EXCEL EXE Browse SPSS path if SPSS does not launch change this Browse Filter for file selection 31 Appendix 2 Changing the text editor used by Winsteps Edit Diagnosis Output Tabl Edit Initial Settings Winsteps Initial Settings Editor path if output tables do not display change Initial settings for control variables ogram Files Windows NT Accessories wordpad exe Browse Excel path if Excel dogs not launch change this E Program Files Micrpsoft Office Office12 EXCEL Browse SPSS path if SPSS goes not lau
40. nch change this CAWINDOWS system32 NOTEPAD EXE Browse R Statistics path iffR does not launch change this e Program Files R R 2 6 2 bin R exe Browse Temporary directgry for work files C DOCUME 1 Mike LOCALS71 Temp V Prompt for R port output file name v Prompt for Extra Specifications Show Datafsetup dialog lv Display Report outfile file after estimation Close outputMvindows on exit C Yes No Ask Input Output Character that starts a comment i Fjeld separator or delimiter Al Decimal point or sign i OK Cancel Help To reset delete file Winsteps ini and restart Winsteps x 161 Appendix 3 What are Logarithms PPT http teachers henrico k12 va us math HCPSAlgebra2 Documents 10 2 2006_ 10 2 Video http www youtube com watch v mOQTWzLpCcW0 100 1000 107 10 10 100000 this is the same as log 100 log 1000 log 100000 Much of what we do during this Course is based on logarithms One reason is because logarithms transform multiplication into addition 162 Let s start with squares 2 x 2 4 and cubes 2x2x2 8 We can see that it takes two 2 s to make 4 so let s V 2x2 4 2 2x2x2 8 write them 27 and it takes three 2 s to make 8 so 73 9 2x2x2xK 2x2 32 4x8 27 x let s write them 2 Then what about 27 2 163 The superscripts and are called powers and we ve discovered that multiplying numbers is the same as
41. olumn is a TAP ITEM First item column yi Ml Number of terns E Winsteps Control and Data File Setup T E Files Edit Winsteps Help Wlinetanc Cantral Cil E WINSTEPS Help TITLE Repor LE NAMELEN f Ni 2 Control Variable Index Control Variable Index by Numb Control variables from Spe Output Table Index ia fis aero Winsteps Help for the Control and data file setup window displays Let s find out about the control variable about which we need more information In the left hand panel click on Control Variables Scroll down the left hand panel Click on ITEM1 The Help information for ITEM1 displays The Help information for each control variable includes a definition and examples of its use Notice the Search tab in the left hand panel Questions and suggestions from Winsteps users are constantly improving the Winsteps Help You will find that Help contains a wealth of information but you may need so search for it The information in the Help file is more current than in the Winsteps User Manual which you will find in c winsteps time limited winsteps pdf Close Help Click on Back on the Winsteps setup screen XWIDE defines how many columns there are per response Use column whenever possible as we do in exam 1 txt CODES contains the valid observations 0 and 1 for this dataset Any other values in the data such as X would be treated as missing data
42. ons We don t have any so Press Enter If you don t want to use the Enter key then you can click on File click on Enter The Winsteps analysis starts Green box the control and data file 1s processed green box The first data record is displayed This is useful for verifying that the data is correctly laid out P start of person label I start of item responses N end of item responses The number of data records 1s reported Here it 1s 35 KID Records input Wright amp Stone called the children in their sample kids and there were 35 of them All is well Red box Winsteps starts making its initial estimates red box The estimation process continues red box Each iteration is one pass through the data file After each pass the current set of Rasch measure estimates is improved This continues until the improvement has become negligible The estimation process has converged When estimation ceases the fit statistics are computed green boxes The fit statistics report how well the data correspond to the measure estimates The results of the analysis are summarized and reported in the blue box Usually we want to see much more information than is reported here Of course Winsteps outputs lots of numbers Let s take a quick look at a couple of Tables On the Winsteps menu bar click on Output Tables click on 13 TAP measure File Edit Diagnosis Output Tables Output Fles Batc
43. rement 1s impossible Instead he was faced with the practical problems of his clients problems that needed practical solutions The Danish Department of Defense had a particular problem with their educational tests Rasch came up with a practical solution based on log odds transformations It worked well but the social scientists found it too complicated as many still do and the mathematical statisticians found it too simplistic as many still do So Georg Rasch made little progress with his measurement ideas until he was invited to present a course of lectures at the University of Chicago in 1960 Only one person attended all the lectures and that was Benjamin D Wright and even he had more pressing things to do for the next several years Then in 1964 Ben had some data analysis problems of his own and he thought that perhaps Georg Rasch would have some ideas about how to solve them and besides a trip to Denmark would be fun This got Ben interested again and but you can read the story at www rasch org rmt rmt0 htm and it was Ben Wright who spread the Rasch model around the world So what had Georg Rasch discovered invented constructed that was able to overcome Norman Campbell s objections Georg Rasch didn t put it this way himself but we can now say that Georg Rasch devised a way of concatenating heads in a psychological way that parallels Campbell s way of concatenating rods in a physical way Rasch implements
44. ry C Winsteps time limited examples We don t want to perform this analysis right now so Close all windows 135 You can experiment doing the same procedure for SPSS sav files SAS sas7bdat files and STATA C Winsteps time limited examples bond4control txt Report output file name or press Enter for temporary f dta files and R rda or rdata files using datasets in the Examples folder SPSS STATA and R should work for everyone 136 SAS If this fails you probably need the SAS Local Data Provider free with free registration from http www sas com apps demosdownloads 92 SDL sysdep jsp packageID 000608 3 CE 26 138 I More to think about 139 It is now time to hear from that long time advocate of e Fundamental Measurement in Social Rasch measurement Ben Wright Unfortunately he Science and Education was incapacitated by a stroke in October 2001 and is http www rasch org memo33a htm struggling to do any productive work Fundamental Measurement for Read the document listed here that matches your Psychology interests but everyone glance at the first one it has a http www rasch org memo64 htm typical picture of Ben in action proclaiming useful Fundamental Measurement for Outcome measuring Evaluation http www rasch org memo66 htm 140 In the literature you will find that the Rasch Rasch Dichot Model vs 0 ter Logistic Model Dichotomous model is somet
45. s menu bar Click on Output Tables Click on 1 Variable maps Here is Table 1 0 Oops It is too big to conveniently look at on my screen Let s squash it reduce its size vertically Winsteps menu bar Click on Specification Control spene In the Dialog Box click on Help Specification a _OK and again OK Cancel Help I want to find out how to squash Table 1 so igen Some T Hide Back Ffrward Home Print Options In the Help window Contents index g arch Favorites Table 1 0 1 2 1 3 1 10 1 12 Distribution maps 2 Winsteps Program Manual amp controlled by MRANGE MAXPAGE NAMLMP ISORT PSORT In the Contents panel 2 Control Variable Index Table 1 2 is printed if tagem map can be squeezed into one page T trol Weriable f squeezed into one pag if person and item maps can be squeezed int Control arable Nees NAMLMP to limit j number of characters of each name reported M Click on Output Table S a A jolene Sper MRANGE confe6ls the displayed range of measures ISORT and PS 2 Outpyf Graphs and Plots Inc TSMST Zummarize the left hard and right hand distributions An M C li ck on Table 1 0 2 Outpht Files Index measyr S markers are placed one sample standard deviation away bd Intrdduction safle standard deviations away m Ingtallation and Execution The Help entry for Table 1 0 li sts a numb er of a Menus In subtables 10 and above the items are
46. sponses don t line up neatly in columns then please set the font to Courier New with a small font size For assistance see 184 Appendix 5 That s enough for the moment so close this NotePad window Back to the Winsteps analysis again Winsteps is asking for the Report output file name Press Enter blue arrow for a temporary file name You can always Save As temporary files to make them permanent if you want to keep them E This file ie DOM TAT TITLE KAN E TEST Mike Analysis PIRRE EOD 5 pec re tte TAF 5 ina oa THEA 812 col ot mpn to Pine item in IE 2 m r of ite E r column of fice character of paren identifying label E r Leegth of prENi latal Bop mehar oof colo pEr ie poe 71s valid codas in data fila E 5 ceteyocy label file for catagory mains th DSSS Hi sf CLIILI Lise Bm G0 s item meen for local IO 2 user eceliny for Legit i E cagpcenad decimal places for ger maling m FAITE E Cone revi jjer PIELER Poe r Geer indicator in column 3 of date caecord OIF PAEDR r Ome the Gendar for DIF Jatari 11001001 00000000 10101 100000000 118111111111 100000 1 111111 100000000 01 1 11 10 0000000Q sis Output Tables Output Fies Batch Help Specification Plots ion 3 67 1 Dec 21 0 15 2008 es on 3 1 2009 C Winsteps time limited examples lt lt output file name or press Enter for temporary f Winsteps asks for Extra specifications These are extra control instructi
47. t logarithms please look at 161 Appendix 3 to this document The logarithm is of Pai divided by Pio which is the ratio of two probabilities A ratio of probabilities is called the odds So on the left side of the equation we have log odds These provide the units for the right side of the equation so Ba and D are measured in log odds units logits pronounced ow its In Table 1 0 above the logit values have been linearly rescaled multiplied by a constant and then had another constant added to produce numbers that are easier for most people to think with This is like going from Celsius to Fahrenheit on a temperature scale The meaning hasn t changed only the numbering The local origin is the place we are measuring from In physical measurement for length it 1s one end of a tape measure For mountains 0 is at sea level For temperature it is 0 on a thermometer In Rasch measurement is usually in the center of the range of item difficulties but it can be wherever we prefer it to be as long as we make it clear to ourselves and everyone else where that 0 point is What if the probability of success 1s the same as the probability of failure Then both probabilities are 0 5 The odds of success are 0 5 0 5 1 and the logarithm Pai Prio 1 of the odds is log 1 zero So the ability and the Paii Paio 0 5 difficulty are the same Exactly what we expect When loge Pnit Prio loge 0 5 0 5
48. t logarithms please study 161 Appendix 3 of this document Probability I think of this in frequentist terms The probability of an event is the proportion of times the event would happen if we could repeat the operation a great many times A probability is always between 0 never happen and always happen P is the probability of success and 1 P is the probability of failure Since either success or failure must always happen when we add their probabilities they must sum to 1 Probability it happens Probability it doesn t happen P 1 P 1 Probabilities Logarithms and the Rasch Model To help with our understanding of Rasch models let s be explicit that success is a score of 1 and failure is a score of 0 on an item Then the Rasch dichotomous model specifies the probability Paii that person n of ability Bn scores 1 on item i of difficulty D and Pyio is the probability of scoring 0 loge Pnit Prio Bn Dj Ability is what we are looking for in the people In your Paii Paio 1 situation you can use other words Proclivity Motivation Health status Disability Difficulty is what we identify in the items In your situation you can use other words Challenge Impediment 20 109 110 An essential concept qualitatively ordered data qualitative ordering is good better best Success means more of what we are loo
49. ted line corresponds to a 0 5 probability of SUCCESS An ability advantage of 1 1 logits arrowed is equivalent to a probability of success of 0 75 This curve is monotonic ascending the probability of success always increases with increasing measure difference monotonously Probability of Success 4 115 Table of logits to probability Logit Probability Logit Probability Difference of Success Difference of Success 5 0 99 5 0 1 Notice that the range 0 100 approximates 10 logits 99 A 0 98 95 90 BE 80 75 73 70 52 50 116 Let s see this curve for exam 1 txt On the Winsteps menu click on Graphs Click on Category Probability Curves Cimdatve Prahshilitee 22 Probability Cat ieee pees l Empitical Cat The x axis is in logits relative to the difficulty of item 4 It has an infinite range from v0 to 00 The y axis 1s the probability This always has the range i Mange ter aitaa 0 to 1 nformation Click on line for description Double click to erase line _ Display Click for Legend Absolute x axis 6 6 7 86 9 __ Score ICE __ J Randomness Ewer Moa Empirical ICC Cumulative l Gondi ito 5 joo ltem Category Category Probability The red arrows show that 1 1 logits above the item difficulty corresponds to 75 chance of success on the a ae item el a aa ih gael roel Fa oA Set Color Help 117 The probability curves for cate
50. with Word NotePad WordPad and many other programs The Winsteps Set up procedure confirms that it saved your control and data file and asks if you want to analyze these Click on Yes The Winsteps analysis screen displays again The analysis is now identified arrowed as being of mikes1 txt or your choice of file name And the Name of control file red box has been set to c Winsteps time limited examples mikes1 txt Let s see what our Control and Data file looks like internally Click on the Winsteps Edit menu Click on Edit Control File Es Item Labels Enter Edit i Edit NI Number of Items fi 8 Save oniu w Mith data file and exit to Winsteps Analysis Save control file without data and exit to Winstens Save control and data file contents to Save in O examples e DE E Bond amp FoxAppendix2 txt exam3dat txt g examil txt Bond amp FoxChapter2 txt exam3idf txt E exam12 txt Bond amp FoxChapter3 txt Z exam4 txt E exam 12bat ba Bond amp FoxChapter4 txt exam4dat txt Bond amp FoxChapter5 txt examS txt Bond amp FoxChapterS PRTIII txt exam6 txt Bond amp FoxChapter6 txt exam7 txt exam 12e xls Bond amp FoxChapter7 txt exams txt exam12NT bat exam L txt exam9 txt 5 exam13 txt exam2 txt exam9dat txt E exam14 txt exam2dat txt exam10a txt exam14b txt exam2iaf txt exam 10b txt exami14c txt exam3 txt exam 10c txt exam 14dt txt
51. xam12NT bat 2 exam13 txt E exam14 txt E exami4 txt B exam 14c txt E exam 14dt txt EE exam 15 txt E exam 16 txt exam 17r txt 2 exam17s txt E example0 txt EE examsubs txt E ket tet O examples a E labels txt ESNTbatch bat E poets txt sastest sas7bdat B sf txt E spssdata sav statadata dta template txt 2 winbatchbat bat 2 winbatchcmd cmd The Winsteps Control File Set Up screen displays now populated with the information from exam 1 txt The top part of the screen inside the blue box contains the control instructions you can see there are 11 control variables displayed We tell the Set Up screen how many ara Dots nhs e rows and columns there are so that the input spreadsheet is the correct size The lower part of the screen inside the red box contains the person and item information and the responses At the bottom of the screen light blue box are additional control variables Winsteps has about 150 control variables So you will often have variables to enter here Exam1 txt is the Knox Cube Test discussed in Wright amp Stone s book Best Test Design 1979 available from http www rasch org btd htm It is a screening test designed by Dr Howard Knox on Ellis Island in New York harbor It assesses attention span and short term memory Dr Knox tapped out patterns on 4 blocks and the newly arrived immigrants were signaled to repeat the tapp
52. xcel spreadsheet It is Negation I pasted in Excel B K as the Item Response Variables Column A of the Excel spreadsheet in the person number I pasted it in as the Person Label Variable You don t have to use all the Excel columns You can change their order and you can also use the same column in both the person and item variable list To construct the Winsteps control and data file Click on Construct Winsteps File Enter the name of a new output file to be the Winsteps control and data file My name is bond4control txt Click on Save The Excel interface starts processing This can be slow because Winsteps is communicating with Excel through Windows 25 E Excel Input for Winsteps Edit Select Excel onstruc file Winsteps file Excel File C Winsteps time Limited examples Bond4 xls Dataset name Sheeti Number of Excel Cases 150 Number of Excel Variables 36 Choose the variables listed below under Other Variables that you want to ft Copy and paste those variables under Person Label Variables in the order yi There will be one space between the variables in the person labels Choose the variables listed below under Other Variables that you want to bt Copy and paste those variables under Item Response Variables in the order Numeric item variables are truncated to integers The same variables can be placed in both sections and in any order Constant values may be inclu

1 # Winsteps Tutorial 1 Mike Linacre, instructor

Contents

Download Pdf Manuals

Related Search

Related Contents