MSBO Certification course Rob Dickinson, MPAAA Executive Director Data Mining MSBO Certification course Rob Dickinson, MPAAA Executive Director

Data Mining Session Agenda Sources of data Data Mining tools/techniques XML editors Working with Access Working with Excel Questions

Data Mining How to data mine? No single answer Dig into data, looking for Patterns you haven’t seen before Breaks in existing patterns Always looking for ‘Why?’ Goal of data mining is to better understand the data you have, so you can make better inferences from it. Example: GRPS 9th Grade elevated enrollment - Don’t fully explain Ask group: What would you do to try to figure that out? Explain Example: 2005 challenge from Superintendent – Each school to enroll 10 new students (80 schools) Principals all produced lists of new student in their schools, District enrollment still down. How would you data mine that? Most of this session, is giving you tools and techniques for data mining, take through some examples.

Data Mining Sources of Data Your SIS CEPI submission downloads MiSchoolData Other sources

Sources of Data Your SIS Details not captured any other place Attendance details Historical data Discipline data not meeting reporting threshold Other?

Sources of Data CEPI Submission Downloads Files submitted and edited during submission process NOT just submitted files CEPI staging area CEPI clears staging area annually

Sources of Data CEPI MSDS login https://cepi.state.mi.us/msds/

Sources of Data MiSchoolData Site maintained by CEPI Public AND Private data Primarily summarized, charted data

Sources of Data MiSchoolData login https://www.mischooldata.org/ Sample problems: #1 9th and 10th grade enrollment dropped at GRPS in 2003/04, can you figure out why? Look at 2004/05, all grades comparison, trend #2: It’s spring on 2013/14 at GRPS, and my Superintendent wants to know if I can accurately predict how many residents will go to other Districts next year. Can I? How? Would I have been right? Look at Non-resident Status in 13/14 for whole District K-12, all non-resident reasons, trend. Then shift to 14/15 to see if I was right. Emphasize “Data files” under “Other Data”

Sources of Data Other sources? What other sources of data have you used? Where do you go to get data?

Data Mining Tools XML editors Best for opening, reviewing specific data Not really data extraction tool

XML Editors XML editors XML Notepad Notepad ++ Free applications Simple interface

XML Editors XML editors XML Notepad Notepad ++

XML Editors XML Notepad Notepad ++ CEPI Data Validation Guide http://www.michigan.gov/documents/cepi/ XML_validation_guide_357832_7.pdf

XML Editors (open sample file in XML Notepad)

Working with MS Access MS Access Powerful database program Easy to create queries, reports Not included in all versions of MS Office Steeper learning curve that Excel How many use Access? Do you like it? Thoughts for those not into it yet?

MS Access (open sample file in MS Access) Data Mining.accdb Explain structure - tables, queries, forms, reports Explain sample data tables Stucourse – Open and work with Add numbergrade and comp status Compute average GPA by course Compute same for 9th grade only Percent failed by teacher Excel exporter

MS Access Testcnt: iif([field being evaluated]=“test condition”,1,0) “Sum” in Total row

MS Access Failcnt: iif([comp status]=“failed condition”,0,1) “Sum” in Total row

Working with MS Excel Excel Spreadsheet program Easy to use Pivot tables – Very powerful As powerful as Access, easier to use How many use Excel? Do you like it? Thoughts for those not into it yet? How many have used Pivot tables? How many are scared of pivot tables? Excel training at Spring Conference – Janell teaching intermediate level

MS Excel (open sample file in Excel) Data Mining.xlsx Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=‘A’,4,’error’) Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=“A”,4,”error”) Condition (the thing being tested) Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=“A”,4,”error”) Value to show if the condition is true Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=“A”,4,”error”) Value to show if the condition is false Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=“A”,4,if(c3=“B”,3,”error”)) Copied whole line (after the ‘=‘), pasted in place of ‘Error’, changed condition and result if true Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=“A”,4,if(c3=“B”,3,if(c3=“C”,2,”e rror”))) Copied it again, changed condition and result if true Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=“A”,4,if(c3=“B”,3,if(c3=“C”,2,if( c2=“D”,1,”error”)))) Copied it again, changed condition and result if true Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel Nested IF statements =if(c3=“A”,4,if(c3=“B”,3,if(c3=“C”,2,if( c2=“D”,1,if(c2=“F”,0,”error”))))) Finished! Note that number of closing parenthesis must equal # of ‘if’ statements Show how to add number grades, comp status Show how to add pivot table Compute average GPA by course Compute same for 9th grade only Number failed by teacher

MS Excel ‘$’ Special character in Excel Suppresses reference movement when you copy & paste

MS Excel Pivot tables Makes Excel into a database tool ALMOST eliminates the need for Access (almost!)

Getting Help CEPI Helpdesk (517) 335-0505, Option 3 cepi@michigan.gov MPAAA Rob@mpaaa.org (517) 853-1413 Ask them, what do they do?