[R-sig-teaching] R Equivalent of SPSS "Split File" and "AutoRecode"

Fri Nov 14 06:35:26 CET 2008

I'd like to help, but your code isn't reproducible, and I'm not
familiar with the RODBC package so I get stuck at

CREF <- sqlQuery(channel = 1, select * from [cref_tabdelimited$])
Error: unexpected ']' in "CREF <- sqlQuery(channel = 1, select * from
[cref_tabdelimited$]"

If you make your code reproducible I'll be happy to take a look at it
and suggest improvements, as well as suggestions for dealing with the
particular issues you were having trouble with.

-Ista

On Thu, Nov 13, 2008 at 11:29 PM, Yihui Xie <xieyihui at gmail.com> wrote:
> The code is so long... Why not store the labels in another file and
> read them into a vector, then assign labels to columns in a loop?
>
> To split file means you have to do the same procedure on each subset
> of the data - this is easy in R: what you need are the splitting
> variable and corresponding conditions, then apply your functions to
> the subset of data in a loop (or use sapply(), ...)
>
> For autorecode, it is nothing but factor() in R!
>
> Regards,
> Yihui
> --
> Yihui Xie <xieyihui at gmail.com>
> Phone: +86-(0)10-82509086 Fax: +86-(0)10-82509086
> Mobile: +86-15810805877
> Homepage: http://www.yihui.name
> School of Statistics, Room 1037, Mingde Main Building,
> Renmin University of China, Beijing, 100872, China
>
>
>
> On Fri, Nov 14, 2008 at 7:31 AM, Albyn Jones <jones at reed.edu> wrote:
>>  I have no clue what "autorecode" means.  Selecting a subset of a file is
>> easy.  Suppose your data frame is named X, assuming REGION is numeric:
>>
>>    attach(X)
>>    X17 = X[REGION == 17,]
>>
>> albyn
>>
>> On Thu, Nov 13, 2008 at 05:18:24PM -0600, Richardson, Paul wrote:
>>>
>>> Greetings Fellow Teachers of R,
>>>
>>>
>>>  *
>>> I am working on a tutorial for a class to be taught at my college.
>>>  *
>>> First, I am going to provide a PowerPoint seminar for the faculty, and then I will create a series of Camtasia screen recordings with narration.
>>>  *
>>> The course is aimed at teaching those familiar with introductory level stats how to perform similar actions in R, that would normally be performed in SPSS.
>>>  *
>>> Is there an autorecode capability in R which is analogous to autorecode in SPSS?  I'm having trouble with item with item f below (second half) "autorecode".
>>>  *
>>> I am also having trouble with item "i" below, because I don't know how to split a data file, like you normally do in SPSS.
>>>  *
>>> Is there some equivalent way to do this in R?
>>>
>>> thanks much,
>>> Paul Richardson
>>> cell 806-543-0087
>>>
>>>
>>> a.       Go to AEIS data site:  http://www.tea.state.tx.us/perfreport/aeis/2007/DownloadData.html
>>> b.      Select Campus, Reference File, and Layout, and download; then do the same for the Reference data file.  Download Campus Financial Statistics, both layout and download.  Download Student Statistics, both layout and download.
>>> c.       Import the data files into R.
>>> d.      Using the layout file, create variable labels; create value labels (if possible).  Assign 0 as a missing value for variable BPETALLC.
>>> e.       Merge the Reference, Financial, and Student files
>>> f.       Recode variable C_RATING into a new, numeric variable named campus.rating in R.  Recode GRDTYPE in a new, numeric variable called grade.type in R.  Use autorecode (if there is something similar in R) to recode CNTYNAME into county.name.  Create a new variable called log.cperra1r, which is the logarithm of CPERRA1R.
>>> g.      Do summary statistics (minimum, maximum, range, mean, median, variance, standard deviation, skewness, kurtosis).
>>> h.      Run histograms, boxplots, scatterplots, scatterplot matrices
>>> i.        Select only cases from Region 17 (using REGION variable) and do the analyses for j-r below; using the equivalent of split file (if possible) to do same analysis for each region separately (using REGION variable).
>>> j.        Conduct 1-way ANOVA using campus.rating as IV and CPETECOP as DV
>>> k.      Conduct repeated measures ANOVA using BPFEAOPRT and CPFEAOPRT (although these are measuring different things, I am having you use them for purely instructional purposes)
>>> l.        Conduct factorial ANOVA using campus.rating and grade.type as IV's and CPETECOP as DV
>>> m.    Conduct correlation using CPFPGSPET and CPFPGGIFT.
>>> n.      Conduct bivariate regression using CPFPGGIFK and CPFPGSPEK
>>> o.      Conduct multiple regression using CPFPGREGT as criterion/outcome variable and CPFPAVOCT, CPFPASPET, and CPFPABILT as predictor variables
>>> p.      Conduct the following regression diagnostics
>>>                                 i.            Numerical diagnostics
>>> 1.      Variance inflation factors
>>> 2.      Breusch-Pagan test for heteroscedasticity
>>> 3.      Durbin-Watson test for autocorrelation
>>> 4.      RESET test for nonlinearity
>>> 5.      Bonferonni outlier test
>>>                               ii.            Graphs
>>> 1.      Basic diagnostic plots
>>> 2.      Residual quantile comparison plot
>>> 3.      Component+residuals plot
>>> 4.      Added variables plot
>>> 5.      Influence plot
>>> 6.      Effects plot
>>> q.      Conduct chi-square using campus.rating and grade.type.
>>> r.        Aggregate all the variables in the file by region (using REGION) and save to a new file called cref_cfin_cstud_agg.rdat
>>>
>>>
>>>
>>>
>>> Below is the actual syntax for the above tasks:
>>> ======================// beginning of R syntax //=======================
>>> # Import CREF
>>> CREF <- sqlQuery(channel = 1, select * from [cref_tabdelimited$])
>>> attach(CREF)
>>> # SORT
>>> CREF<- order(+CREF$campus)
>>> CREF
>>> # variable labels
>>> library(Hmisc)
>>> label(CREF$DISTNAME)<- "District Name"
>>> label(CREF$CAMPNAME)<- "Campus Name"
>>> label(CREF$CACKDTL)<- "Campus 2007 Ratings: GPA Acknowledgment Detail"
>>> label(CREF$CAMPUS)<- "CURRENT 9-DIGIT CDC NUMBER"
>>> label(CREF$DISTRICT)<- "6 Digit County District Number"
>>> label(CREF$COUNTY)<- "3 Digit County Number"
>>> label(CREF$REGION)<- "2 Digit ESC Region"
>>> label(CREF$CNTYNAME)<- "County Name"
>>> label(CREF$GRDTYPE)<- "Campus Type (B,E,M,S) Total Enrollment"
>>> label(CREF$GRDSPAN)<- "Grade Span (Total Enrollment)"
>>> label(CREF$CFLCHART)<- "CAMPUS 2007 Flag-Chater School (Y/N)"
>>> label(CREF$PAIRCAMP)<- "CAMPUS 2007 Flag-Campus/District No. of TAKS Giver"
>>> label(CREF$PAIRNAME)<- "CAMPUS 2007 Flag-Campus/District Name of TAKS Giver"
>>> label(CREF$C_RATING)<- "Campus 2007 Ratings: Final Accountability Rating"
>>> #Import CSTUD
>>> CSTUD <- read.table("C:/Users/Matt/Desktop/TTU/Courses/EPSY 5385_Stats Packages/DATA FILES/cstud.dat", header=TRUE, sep=",", na.strings="NA", dec=".", strip.white=TRUE)
>>> attach(CSTUD)
>>> # SORT
>>> CSTUD<- order(+CSTUD$campus)
>>> CSTUD
>>> # variable labels
>>> library(Hmisc)
>>> label(CSTUD$CA0GR06N)<- "Campus 2006 Graduates: All Students Count"
>>> label(CSTUD$CA0GH06N)<- "Campus 2006 Graduates: Recom HS Pgm All Students Count"
>>> label(CSTUD$CA0GM06N)<- "Campus 2006 Graduates: Min HS Pgm All Students Count"
>>> label(CSTUD$CB0GR06N)<- "Campus 2006 Graduates: African American Count"
>>> label(CSTUD$CH0GR06N)<- "Campus 2006 Graduates: Hispanic Count"
>>> label(CSTUD$CW0GR06N)<- "Campus 2006 Graduates: White Count"
>>> label(CSTUD$CI0GR06N)<- "Campus 2006 Graduates: Native American Count"
>>> label(CSTUD$CP0GR06N)<- "Campus 2006 Graduates: Asian/Pacific Islander Count"
>>> label(CSTUD$CS0GR06N)<- "Campus 2006 Graduates: Special Ed Count"
>>> label(CSTUD$BPETALLC)<- "Group 2007 Student: All Students Count"
>>> label(CSTUD$BA0GR06N)<- "Group 2006 Graduates: All Students Count"
>>> label(CSTUD$BB0GR06N)<- "Group 2006 Graduates: African American Count"
>>> label(CSTUD$BH0GR06N)<- "Group 2006 Graduates: Hispanic Count"
>>> label(CSTUD$BW0GR06N)<- "Group 2006 Graduates: White Count"
>>> label(CSTUD$BI0GR06N)<- "Group 2006 Graduates: Native American Count"
>>> label(CSTUD$BP0GR06N)<- "Group 2006 Graduates: Asian/Pacific Islander Count"
>>> label(CSTUD$BS0GR06N)<- "Group 2006 Graduates: Special Ed Count"
>>> label(CSTUD$BA0GH06N)<- "Group 2006 Graduates: Recom HS Pgm All Students Count"
>>> label(CSTUD$BA0GM06N)<- "Group 2006 Graduates: Min HS Pgm All Students Count"
>>> label(CSTUD$BPETDISC)<- "Group 2006 DAEP: Count"
>>> label(CSTUD$CPERRAKR)<- "Campus 2006 Retention: Regular Ed KG Rate"
>>> label(CSTUD$CPERRA1R)<- "Campus 2006 Retention: Regular Ed 01 Rate"
>>> label(CSTUD$CPERRA2R)<- "Campus 2006 Retention: Regular Ed 02 Rate"
>>> label(CSTUD$CPERRA3R)<- "Campus 2006 Retention: Regular Ed 03 Rate"
>>> label(CSTUD$CPERRA4R)<- "Campus 2006 Retention: Regular Ed 04 Rate"
>>> label(CSTUD$CPERRA5R)<- "Campus 2006 Retention: Regular Ed 05 Rate"
>>> label(CSTUD$CPERRA6R)<- "Campus 2006 Retention: Regular Ed 06 Rate"
>>> label(CSTUD$CPERRA7R)<- "Campus 2006 Retention: Regular Ed 07 Rate"
>>> label(CSTUD$CPERRA8R)<- "Campus 2006 Retention: Regular Ed 08 Rate"
>>> label(CSTUD$CPERSAKR)<- "Campus 2006 Retention: Special Ed KG Rate"
>>> label(CSTUD$CPERSA1R)<- "Campus 2006 Retention: Special Ed 01 Rate"
>>> label(CSTUD$CPERSA2R)<- "Campus 2006 Retention: Special Ed 02 Rate"
>>> label(CSTUD$CPERSA3R)<- "Campus 2006 Retention: Special Ed 03 Rate"
>>> label(CSTUD$CPERSA4R)<- "Campus 2006 Retention: Special Ed 04 Rate"
>>> label(CSTUD$CPERSA5R)<- "Campus 2006 Retention: Special Ed 05 Rate"
>>> label(CSTUD$CPERSA6R)<- "Campus 2006 Retention: Special Ed 06 Rate"
>>> label(CSTUD$CPERSA7R)<- "Campus 2006 Retention: Special Ed 07 Rate"
>>> label(CSTUD$CPERSA8R)<- "Campus 2006 Retention: Special Ed 08 Rate"
>>> label(CSTUD$CPETDISC)<- "Campus 2006 DAEP: Count"
>>> label(CSTUD$CPETDISP)<- "Campus 2006 DAEP: Percent"
>>> label(CSTUD$CPETLEPP)<- "Campus 2007 Student: LEP Percent"
>>> label(CSTUD$CPETECOP)<- "Campus 2007 Student: ECO Percent"
>>> label(CSTUD$CPETECOC)<- "Campus 2007 Student: ECO Count"
>>> label(CSTUD$CPETLEPC)<- "Campus 2007 Student: LEP Count"
>>> label(CSTUD$CPETSPEC)<- "Campus 2007 Student: SPE Count"
>>> label(CSTUD$CPETGIFC)<- "Campus 2007 Student: GIF/TAL Count"
>>> label(CSTUD$CPETBILC)<- "Campus 2007 Student: BIL Count"
>>> label(CSTUD$CPETALLC)<- "Campus 2007 Student: All Students Count"
>>> label(CSTUD$CPETVOCC)<- "Campus 2007 Student: VOC Count"
>>> label(CSTUD$CPETINDC)<- "Campus 2007 Student: Native American Count"
>>> label(CSTUD$CPETPACC)<- "Campus 2007 Student: Asian/Pacific Islander Count"
>>> label(CSTUD$CPETBLAC)<- "Campus 2007 Student: African American Count"
>>> label(CSTUD$CPETHISC)<- "Campus 2007 Student: Hispanic Count"
>>> label(CSTUD$CPETWHIC)<- "Campus 2007 Student: White Count"
>>> label(CSTUD$CPETGEEC)<- "Campus 2007 Student: EE Count"
>>> label(CSTUD$CPETGPKC)<- "Campus 2007 Student: PK Count"
>>> label(CSTUD$CPETGKNC)<- "Campus 2007 Student: KG Count"
>>> label(CSTUD$CPETG01C)<- "Campus 2007 Student: 01 Count"
>>> label(CSTUD$CPETG02C)<- "Campus 2007 Student: 02 Count"
>>> label(CSTUD$CPETG03C)<- "Campus 2007 Student: 03 Count"
>>> label(CSTUD$CPETG04C)<- "Campus 2007 Student: 04 Count"
>>> label(CSTUD$CPETG05C)<- "Campus 2007 Student: 05 Count"
>>> label(CSTUD$CPETG06C)<- "Campus 2007 Student: 06 Count"
>>> label(CSTUD$CPETG07C)<- "Campus 2007 Student: 07 Count"
>>> label(CSTUD$CPETG08C)<- "Campus 2007 Student: 08 Count"
>>> label(CSTUD$CPETG09C)<- "Campus 2007 Student: 09 Count"
>>> label(CSTUD$CPETG10C)<- "Campus 2007 Student: 10 Count"
>>> label(CSTUD$CPETG11C)<- "Campus 2007 Student: 11 Count"
>>> label(CSTUD$CPETG12C)<- "Campus 2007 Student: 12 Count"
>>> label(CSTUD$CPEMALLC)<- "Campus 2007 Student: 06 Mobility Numerator (Campus Only)"
>>> label(CSTUD$CPETWHIP)<- "Campus 2007 Student: White Percent"
>>> label(CSTUD$CPETBLAP)<- "Campus 2007 Student: African American Percent"
>>> label(CSTUD$CPETHISP)<- "Campus 2007 Student: Hispanic Percent"
>>> label(CSTUD$CPETINDP)<- "Campus 2007 Student: Native American Percent"
>>> label(CSTUD$CPETPACP)<- "Campus 2007 Student: Asian/Pacific Islander Percent"
>>> label(CSTUD$CPETSPEP)<- "Campus 2007 Student: SPE Percent"
>>> label(CSTUD$CPETVOCP)<- "Campus 2007 Student: VOC Percent"
>>> label(CSTUD$CPETBILP)<- "Campus 2007 Student: BIL Percent"
>>> label(CSTUD$CPETGIFP)<- "Campus 2007 Student: GIF/TAL Percent"
>>> label(CSTUD$CPETGEEP)<- "Campus 2007 Student: EE Percent"
>>> label(CSTUD$CPETGPKP)<- "Campus 2007 Student: PK Percent"
>>> label(CSTUD$CPETGKNP)<- "Campus 2007 Student: KG Percent"
>>> label(CSTUD$CPETG01P)<- "Campus 2007 Student: 01 Percent"
>>> label(CSTUD$CPETG02P)<- "Campus 2007 Student: 02 Percent"
>>> label(CSTUD$CPETG03P)<- "Campus 2007 Student: 03 Percent"
>>> label(CSTUD$CPETG04P)<- "Campus 2007 Student: 04 Percent"
>>> label(CSTUD$CPETG05P)<- "Campus 2007 Student: 05 Percent"
>>> label(CSTUD$CPETG06P)<- "Campus 2007 Student: 06 Percent"
>>> label(CSTUD$CPETG07P)<- "Campus 2007 Student: 07 Percent"
>>> label(CSTUD$CPETG08P)<- "Campus 2007 Student: 08 Percent"
>>> label(CSTUD$CPETG09P)<- "Campus 2007 Student: 09 Percent"
>>> label(CSTUD$CPETG10P)<- "Campus 2007 Student: 10 Percent"
>>> label(CSTUD$CPETG11P)<- "Campus 2007 Student: 11 Percent"
>>> label(CSTUD$CPETG12P)<- "Campus 2007 Student: 12 Percent"
>>> label(CSTUD$CPEMALLP)<- "Campus 2007 Student: 06 Mobility Percent (Campus Only)"
>>> label(CSTUD$BPETWHIP)<- "Group 2007 Student: White Percent"
>>> label(CSTUD$BPETBLAP)<- "Group 2007 Student: African American Percent"
>>> label(CSTUD$BPETHISP)<- "Group 2007 Student: Hispanic Percent"
>>> label(CSTUD$BPETINDP)<- "Group 2007 Student: Native American Percent"
>>> label(CSTUD$BPETPACP)<- "Group 2007 Student: Asian/Pacific Islander Percent"
>>> label(CSTUD$BPETECOP)<- "Group 2007 Student: ECO Percent"
>>> label(CSTUD$BPETLEPP)<- "Group 2007 Student: LEP Percent"
>>> label(CSTUD$BPETSPEP)<- "Group 2007 Student: SPE Percent"
>>> label(CSTUD$BPETVOCP)<- "Group 2007 Student: VOC Percent"
>>> label(CSTUD$BPETBILP)<- "Group 2007 Student: BIL Percent"
>>> label(CSTUD$BPETGIFP)<- "Group 2007 Student: GIF/TAL Percent"
>>> label(CSTUD$BPETGEEP)<- "Group 2007 Student: EE Percent"
>>> label(CSTUD$BPETGPKP)<- "Group 2007 Student: PK Percent"
>>> label(CSTUD$BPETGKNP)<- "Group 2007 Student: KG Percent"
>>> label(CSTUD$BPETG01P)<- "Group 2007 Student: 01 Percent"
>>> label(CSTUD$BPETG02P)<- "Group 2007 Student: 02 Percent"
>>> label(CSTUD$BPETG03P)<- "Group 2007 Student: 03 Percent"
>>> label(CSTUD$BPETG04P)<- "Group 2007 Student: 04 Percent"
>>> label(CSTUD$BPETG05P)<- "Group 2007 Student: 05 Percent"
>>> label(CSTUD$BPETG06P)<- "Group 2007 Student: 06 Percent"
>>> label(CSTUD$BPETG07P)<- "Group 2007 Student: 07 Percent"
>>> label(CSTUD$BPETG08P)<- "Group 2007 Student: 08 Percent"
>>> label(CSTUD$BPETG09P)<- "Group 2007 Student: 09 Percent"
>>> label(CSTUD$BPETG10P)<- "Group 2007 Student: 10 Percent"
>>> label(CSTUD$BPETG11P)<- "Group 2007 Student: 11 Percent"
>>> label(CSTUD$BPETG12P)<- "Group 2007 Student: 12 Percent"
>>> label(CSTUD$BPEMALLP)<- "Group 2007 Student: 06 Mobility Percent (Campus ONLY)"
>>> label(CSTUD$BPERRAKR)<- "Group 2006 Retention: Regular Ed KG Rate"
>>> label(CSTUD$BPERRA1R)<- "Group 2006 Retention: Regular Ed 01 Rate"
>>> label(CSTUD$BPERRA2R)<- "Group 2006 Retention: Regular Ed 02 Rate"
>>> label(CSTUD$BPERRA3R)<- "Group 2006 Retention: Regular Ed 03 Rate"
>>> label(CSTUD$BPERRA4R)<- "Group 2006 Retention: Regular Ed 04 Rate"
>>> label(CSTUD$BPERRA5R)<- "Group 2006 Retention: Regular Ed 05 Rate"
>>> label(CSTUD$BPERRA6R)<- "Group 2006 Retention: Regular Ed 06 Rate"
>>> label(CSTUD$BPERRA7R)<- "Group 2006 Retention: Regular Ed 07 Rate"
>>> label(CSTUD$BPERRA8R)<- "Group 2006 Retention: Regular Ed 08 Rate"
>>> label(CSTUD$BPERSAKR)<- "Group 2006 Retention: Special Ed KG Rate"
>>> label(CSTUD$BPERSA1R)<- "Group 2006 Retention: Special Ed 01 Rate"
>>> label(CSTUD$BPERSA2R)<- "Group 2006 Retention: Special Ed 02 Rate"
>>> label(CSTUD$BPERSA3R)<- "Group 2006 Retention: Special Ed 03 Rate"
>>> label(CSTUD$BPERSA4R)<- "Group 2006 Retention: Special Ed 04 Rate"
>>> label(CSTUD$BPERSA5R)<- "Group 2006 Retention: Special Ed 05 Rate"
>>> label(CSTUD$BPERSA6R)<- "Group 2006 Retention: Special Ed 06 Rate"
>>> label(CSTUD$BPERSA7R)<- "Group 2006 Retention: Special Ed 07 Rate"
>>> label(CSTUD$BPERSA8R)<- "Group 2006 Retention: Special Ed 08 Rate"
>>> label(CSTUD$BPETDISP)<- "Group 2006 DAEP: Percent"
>>> CSTUD$BPETALLC [CSTUD$BPETALLC == 0] <- NA
>>> CSTUD$BPETALLC [is.na(CSTUD$BPETALLC)] <- 0
>>> # Import CFIN
>>> CFIN <- read.table("C:/Users/Matt/Desktop/TTU/Courses/EPSY 5385_Stats Packages/DATA FILES/cfin.dat", header=TRUE, sep=",", na.strings="NA", dec=".", strip.white=TRUE)
>>> attach(CFIN)
>>> # SORT
>>> CFIN<- order(+CFIN$campus)
>>> CFIN
>>> # variable labels
>>> library(Hmisc)
>>> label(CFIN$CPFEGADST)<- "Campus 2006 Finance: Expenditure by Function-School Leadership, General Fund"
>>> label(CFIN$CPFEGADIT)<- "Campus 2006 Finance: Expenditure by Function-Instructional Leadership, General Fund"
>>> label(CFIN$CPFEAADST)<- "Campus 2006 Finance: Expenditure by Function-School Leadership, All Funds"
>>> label(CFIN$CPFEAADIT)<- "Campus 2006 Finance: Expenditure by Function-Instructional Leadership, All Funds"
>>> label(CFIN$CPFPGREGT)<- "Campus 2006 Finance: Expenditure by Program-Regular, GeneralFund"
>>> label(CFIN$CPFPGVOCT)<- "Campus 2006 Finance: Expenditure by Program-Career & Technology, General Fund"
>>> label(CFIN$CPFPGSPET)<- "Campus 2006 Finance: Expenditure by Program-Special Education, General Fund"
>>> label(CFIN$CPFPGGIFT)<- "Campus 2006 Finance: Expenditure by Program-Gifted & Talented, General Fund"
>>> label(CFIN$CPFPGBILT)<- "Campus 2006 Finance: Expenditure by Program-Bilingual, General Fund"
>>> label(CFIN$CPFPAREGT)<- "Campus 2006 Finance: Expenditure by Program-Regular, All Funds"
>>> label(CFIN$CPFPAVOCT)<- "Campus 2006 Finance: Expenditure by Program-Career & Technology, All Funds"
>>> label(CFIN$CPFPASPET)<- "Campus 2006 Finance: Expenditure by Program-Special Education, All Funds"
>>> label(CFIN$CPFPAGIFT)<- "Campus 2006 Finance: Expenditure by Program-Gifted & Talented, All Funds"
>>> label(CFIN$CPFPABILT)<- "Campus 2006 Finance: Expenditure by Program-Bilingual, All Funds"
>>> label(CFIN$CPFEGINST)<- "Campus 2006 Finance: Expenditure by Function-Instruction, General Fund"
>>> label(CFIN$CPFEAINST)<- "Campus 2006 Finance: Expenditure by Function-Instruction, All Funds"
>>> label(CFIN$CPFEGOPRT)<- "Campus 2006 Finance: Expenditure by Function-Total Operating,General Fund"
>>> label(CFIN$CPFEAOPRT)<- "Campus 2006 Finance: Expenditure by Function-Total Operating, All Funds"
>>> label(CFIN$CPFPGALLT)<- "Campus 2006 Finance: Expenditure by Program-Total, General Fund"
>>> label(CFIN$CPFPAALLT)<- "Campus 2006 Finance: Expenditure by Program-Total, All Funds"
>>> label(CFIN$CPFEGINSK)<- "Campus 2006 Finance: Expenditure by Function-Instruction PerPupil, General Fund"
>>> label(CFIN$CPFEGADIK)<- "Campus 2006 Finance: Expenditure by Function-Instructional Leadership Per Pupil, General Fund"
>>> label(CFIN$CPFEGADSK)<- "Campus 2006 Finance: Expenditure by Function-School Leadership Per Pupil, General Fund"
>>> label(CFIN$CPFEGOPRK)<- "Campus 2006 Finance: Expenditure by Function-Total OperatingPer Pupil, General Fund"
>>> label(CFIN$CPFPGREGK)<- "Campus 2006 Finance: Expenditure by Program-Regular Per Pupil, General Fund"
>>> label(CFIN$CPFPGVOCK)<- "Campus 2006 Finance: Expenditure by Program-Career & Technology Per Pupil, General Fund"
>>> label(CFIN$CPFPGBILK)<- "Campus 2006 Finance: Expenditure by Program-Bilingual Per Pupil, General Fund"
>>> label(CFIN$CPFPGGIFK)<- "Campus 2006 Finance: Expenditure by Program-Gifted & Talented Per Pupil, General Fund"
>>> label(CFIN$CPFPGSPEK)<- "Campus 2006 Finance: Expenditure by Program-Special Education Per Pupil, General Fund"
>>> label(CFIN$CPFPGALLK)<- "Campus 2006 Finance: Expenditure by Program-Total Per Pupil,General Fund"
>>> label(CFIN$CPFEAINSK)<- "Campus 2006 Finance: Expenditure by Function-Instruction PerPupil, All Funds"
>>> label(CFIN$CPFEAADIK)<- "Campus 2006 Finance: Expenditure by Function-Instructional Leadership Per Pupil, All Funds"
>>> label(CFIN$CPFEAADSK)<- "Campus 2006 Finance: Expenditure by Function-School Leadership Per Pupil, All Funds"
>>> label(CFIN$CPFEAOPRK)<- "Campus 2006 Finance: Expenditure by Function-Total OperatingPer Pupil, ALL Funds"
>>> label(CFIN$CPFPAREGK)<- "Campus 2006 Finance: Expenditure by Program-Regular Per Pupil, All Funds"
>>> label(CFIN$CPFPAVOCK)<- "Campus 2006 Finance: Expenditure by Program-Career & Technology Per Pupil, All Funds"
>>> label(CFIN$CPFPABILK)<- "Campus 2006 Finance: Expenditure by Program-Bilingual Per Pupil, All Funds"
>>> label(CFIN$CPFPAGIFK)<- "Campus 2006 Finance: Expenditure by Program-Gifted & Talented Per Pupil, All Funds"
>>> label(CFIN$CPFPASPEK)<- "Campus 2006 Finance: Expenditure by Program-Special Education Per Pupil, All Funds"
>>> label(CFIN$CPFPAALLK)<- "Campus 2006 Finance: Expenditure by Program-Total Per Pupil,All Funds"
>>> label(CFIN$CPFEGRELT)<- "Campus 2006 Finance: Expenditure by Function-Instructional-Related Services, General Fund"
>>> label(CFIN$CPFEARELT)<- "Campus 2006 Finance: Expenditure by Function-Instructional-Related Services, All Funds"
>>> label(CFIN$CPFEGSUPT)<- "Campus 2006 Finance: Expenditure by Function-Support Services-Student, General Fund"
>>> label(CFIN$CPFEASUPT)<- "Campus 2006 Finance: Expenditure by Function-Support Services-Student, All Funds"
>>> label(CFIN$CPFPGCOMT)<- "Campus 2006 Finance: Expenditure by Program-Compensatory, General Fund"
>>> label(CFIN$CPFPACOMT)<- "Campus 2006 Finance: Expenditure by Program-Compensatory, All Funds"
>>> label(CFIN$CPFPGOTHT)<- "Campus 2006 Finance: Expenditure by Program-Other, General Fund"
>>> label(CFIN$CPFPAOTHT)<- "Campus 2006 Finance: Expenditure by Program-Other, All Funds"
>>> label(CFIN$CPFEGOPRP)<- "Campus 2006 Finance: Expenditure by Function-Total OperatingPercent, General Fund"
>>> label(CFIN$CPFEGINSP)<- "Campus 2006 Finance: Expenditure by Function-Instruction Percent, General Fund"
>>> label(CFIN$CPFEGRELP)<- "Campus 2006 Finance: Expenditure by Function-Instructional-Related Services Percent, General Fund"
>>> label(CFIN$CPFEGADIP)<- "Campus 2006 Finance: Expenditure by Function-Instructional Leadership Percent, General Fund"
>>> label(CFIN$CPFEGADSP)<- "Campus 2006 Finance: Expenditure by Function-School Leadership Percent, General Fund"
>>> label(CFIN$CPFEGSUPP)<- "Campus 2006 Finance: Expenditure by Function-Support Services-Student Percent, General Fund"
>>> label(CFIN$CPFEAOPRP)<- "Campus 2006 Finance: Expenditure by Function-Total OperatingPercent, All Funds"
>>> label(CFIN$CPFEAINSP)<- "Campus 2006 Finance: Expenditure by Function-Instruction Percent, All Funds"
>>> label(CFIN$CPFEARELP)<- "Campus 2006 Finance: Expenditure by Function-Instructional-Related Services Percent, All Funds"
>>> label(CFIN$CPFEAADIP)<- "Campus 2006 Finance: Expenditure by Function-Instructional Leadership Percent, All Funds"
>>> label(CFIN$CPFEAADSP)<- "Campus 2006 Finance: Expenditure by Function-School Leadership Percent, All Funds"
>>> label(CFIN$CPFEASUPP)<- "Campus 2006 Finance: Expenditure by Function-Support Services-Student Percent, All Funds"
>>> label(CFIN$CPFPGALLP)<- "Campus 2006 Finance: Expenditure by Program-Total Percent, General Fund"
>>> label(CFIN$CPFPGBILP)<- "Campus 2006 Finance: Expenditure by Program-Bilingual Percent, General Fund"
>>> label(CFIN$CPFPGVOCP)<- "Campus 2006 Finance: Expenditure by Program-Career & Technology Percent, General Fund"
>>> label(CFIN$CPFPGCOMP)<- "Campus 2006 Finance: Expenditure by Program-Compensatory Percent, General Fund"
>>> label(CFIN$CPFPGGIFP)<- "Campus 2006 Finance: Expenditure by Program-Gifted & Talented Percent, General Fund"
>>> label(CFIN$CPFPGREGP)<- "Campus 2006 Finance: Expenditure by Program-Regular Percent,General Fund"
>>> label(CFIN$CPFPGSPEP)<- "Campus 2006 Finance: Expenditure by Program-Special Education Percent, General Fund"
>>> label(CFIN$CPFPGOTHP)<- "Campus 2006 Finance: Expenditure by Program-Other Percent, General Fund"
>>> label(CFIN$CPFPAALLP)<- "Campus 2006 Finance: Expenditure by Program-Total Percent, All Funds"
>>> label(CFIN$CPFPABILP)<- "Campus 2006 Finance: Expenditure by Program-Bilingual Percent, All Funds"
>>> label(CFIN$CPFPAVOCP)<- "Campus 2006 Finance: Expenditure by Program-Career & Technology Percent, All Funds"
>>> label(CFIN$CPFPACOMP)<- "Campus 2006 Finance: Expenditure by Program-Compensatory Percent, All Funds"
>>> label(CFIN$CPFPAGIFP)<- "Campus 2006 Finance: Expenditure by Program-Gifted & Talented Percent, All Funds"
>>> label(CFIN$CPFPAREGP)<- "Campus 2006 Finance: Expenditure by Program-Regular Percent,All Funds"
>>> label(CFIN$CPFPASPEP)<- "Campus 2006 Finance: Expenditure by Program-Special Education Percent, All Funds"
>>> label(CFIN$CPFPAOTHP)<- "Campus 2006 Finance: Expenditure by Program-Other Percent, All Funds"
>>> label(CFIN$CPFEGRELK)<- "Campus 2006 Finance: Expenditure by Function-Instructional-Related Services Per Pupil, General Fund"
>>> label(CFIN$CPFEARELK)<- "Campus 2006 Finance: Expenditure by Function-Instructional-Related Services Per Pupil, All Funds"
>>> label(CFIN$CPFEGSUPK)<- "Campus 2006 Finance: Expenditure by Function-Support Services-Student Per Pupil, General Fund"
>>> label(CFIN$CPFEASUPK)<- "Campus 2006 Finance: Expenditure by Function-Support Services-Student Per Pupil, All Funds"
>>> label(CFIN$CPFPGCOMK)<- "Campus 2006 Finance: Expenditure by Program-Compensatory PerPupil, General Fund"
>>> label(CFIN$CPFPACOMK)<- "Campus 2006 Finance: Expenditure by Program-Compensatory PerPupil, All Funds"
>>> label(CFIN$CPFPGOTHK)<- "Campus 2006 Finance: Expenditure by Program-Other Per Pupil,General Fund"
>>> label(CFIN$CPFPAOTHK)<- "Campus 2006 Finance: Expenditure by Program-Other Per Pupil,All Funds"
>>> label(CFIN$BPFEAOPRT)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Total Operating, All Funds"
>>> label(CFIN$BPFEAINST)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instruction, All Funds"
>>> label(CFIN$BPFEARELT)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instructional-Related Services, All Funds"
>>> label(CFIN$BPFEAADIT)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instructional Leadership, All Funds"
>>> label(CFIN$BPFEAADST)<- "Campus 2006 Finance: Group Total-Expenditure by Function-School Leadership, All Funds"
>>> label(CFIN$BPFEASUPT)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Support Services--Student, All Funds"
>>> label(CFIN$BPFPAALLT)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Total, All Funds"
>>> label(CFIN$BPFPABILT)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Bilingual, All Funds"
>>> label(CFIN$BPFPAVOCT)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Career & Technology, All Funds"
>>> label(CFIN$BPFPACOMT)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Compensatory, All Funds"
>>> label(CFIN$BPFPAGIFT)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Gifted & Talented, All Funds"
>>> label(CFIN$BPFPAREGT)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Regular, All Funds"
>>> label(CFIN$BPFPASPET)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Special Education, All Funds"
>>> label(CFIN$BPFPAOTHT)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Other, All Funds"
>>> label(CFIN$BPFPAALLP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Total Percent, All Funds"
>>> label(CFIN$BPFPAREGP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Regular Percent, All Funds"
>>> label(CFIN$BPFPABILP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Bilingual Percent, All Funds"
>>> label(CFIN$BPFPACOMP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Compensatory Percent, All Funds"
>>> label(CFIN$BPFPAGIFP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Gifted & Talented Percent, All Funds"
>>> label(CFIN$BPFPAVOCP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Career & Technology Percent, All Funds"
>>> label(CFIN$BPFPASPEP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Special Education Percent, All Funds"
>>> label(CFIN$BPFPAOTHP)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Other Percent, All Funds"
>>> label(CFIN$BPFEAOPRP)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Total Operating Percent, All Funds"
>>> label(CFIN$BPFEAINSP)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instruction Percent, All Funds"
>>> label(CFIN$BPFEARELP)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instructional-Related Services Percent, All Funds"
>>> label(CFIN$BPFEAADIP)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instructional Leadership Percent, All Funds"
>>> label(CFIN$BPFEAADSP)<- "Campus 2006 Finance: Group Total-Expenditure by Function-School Leadership Percent, All Funds"
>>> label(CFIN$BPFEASUPP)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Support Services--Student Percent, All Funds"
>>> label(CFIN$BPFEAOPRK)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Total Operating Per Pupil, All Funds"
>>> label(CFIN$BPFEAINSK)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instruction Per Pupil, All Funds"
>>> label(CFIN$BPFEARELK)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instructional-Related Services Per Pupil, All Funds"
>>> label(CFIN$BPFEAADIK)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Instructional Leadership Per Pupil, All Funds"
>>> label(CFIN$BPFEAADSK)<- "Campus 2006 Finance: Group Total-Expenditure by Function-School Leadership Per Pupil, All Funds"
>>> label(CFIN$BPFEASUPK)<- "Campus 2006 Finance: Group Total-Expenditure by Function-Support Services--Student Per Pupil, All Funds"
>>> label(CFIN$BPFPAALLK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Total Per Pupil, All Funds"
>>> label(CFIN$BPFPABILK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Bilingual Per Pupil, All Funds"
>>> label(CFIN$BPFPAVOCK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Career & Technology Per Pupil, All Funds"
>>> label(CFIN$BPFPACOMK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Compensatory Per Pupil, All Funds"
>>> label(CFIN$BPFPAGIFK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Gifted & Talented Per Pupil, All Funds"
>>> label(CFIN$BPFPAREGK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Regular Per Pupil, All Funds"
>>> label(CFIN$BPFPASPEK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Special Education Per Pupil, All Funds"
>>> label(CFIN$BPFPAOTHK)<- "Campus 2006 Finance: Group Total-Expenditure by Program-Other Per Pupil, All Funds"
>>> # merge two datasets by CAMPUS
>>> total <- merge(CREF,CSTUD, by="CAMPUS", all=T)
>>> attach(total)
>>> total2 <- merge(total,CFIN, by="CAMPUS", all=T)
>>> attach(total2)
>>> # Sort
>>> total2 <- order(+total2$campus)
>>> total2
>>> #Recodes
>>> total2$campus.rating <- recode(total2$C_RATING, '"A" = 1; "E" = 2; "R" = 3; "X" = 4; "L" = 5; ', as.factor.result=TRUE)
>>> total2$campus.rating <- factor(total2$campus.rating,levels=c("1","2","3","4","5"),labels=c("Acceptable","Exemplary","Recognized","Unacceptable","Unknown"))
>>> total2$grade.type <- recode(total2$GRDTYPE, '"B" = 1; "E" = 2; "M" = 3; "S" = 4; ', as.factor.result=TRUE)
>>> total2$grade.type <- factor(total2$grade.type,levels=c("1","2","3","4"),labels=c("Both","Elementary","Middle","Senior"))
>>> total2$CPERRA1R <- as.numeric(total2$CPERRA1R)
>>> total2$log.cperra1r <- with(total2, log10(CPERRA1R))
>>> # auto-recode -- county.name
>>> #Summary statistics
>>> summary(total2)
>>> # Histogram
>>> Hist(total2$BA0GH06N, scale="frequency", breaks="Sturges", col="darkgray")
>>> #Scatterplot
>>> scatterplot(BA0GR06N~BA0GM06N, reg.line=FALSE, smooth=FALSE, labels=FALSE, boxplots='xy', span=0.5, data=total2)
>>> #Scatterplot matrices
>>> scatterplot.matrix(~BA0GH06N+BA0GR06N+BH0GR06N+BP0GR06N+BPETDISC, reg.line=FALSE, smooth=FALSE, span=0.5, diagonal = 'density', data=total2)
>>> # Split File -- CAN'T IN R
>>> # 1-way ANOVA
>>> total2$CPETECOP <- as.numeric(total2$CPETECOP)
>>> .Anova<- lm(CPETECOP ~ campus.rating, data=total2)
>>> anova(.Anova)
>>> tapply(total2$CPETECOP, total2$campus.rating, mean, na.rm=TRUE) # means
>>> tapply(total2$CPETECOP, total2$campus.rating, sd, na.rm=TRUE) # std. deviations
>>> tapply(total2$CPETECOP, total2$campus.rating, function(x) sum(!is.na(x))) # counts
>>> remove(.Anova)
>>> # Repeated measures ANOVA?
>>> GLM.1 <- glm(BPFEAOPRT  ~ CPFEAOPRT, family=binomial(logit), data=total2)
>>> summary(GLM.1)
>>> # Factorial ANOVA
>>> # Correlation
>>> library(RODBC)
>>> total2$CPFPGSPET <- as.numeric(total2$CPFPGSPET)
>>> total2$CPFPGGIFT <- as.numeric(total2$CPFPGGIFT)
>>> cor.test(total2$CPFPGSPET , total2$CPFPGGIFT, use="pairwise.complete.obs", alternative="two.sided", method="pearson")
>>> # Bivariate Regression
>>> total2$CPFPGGIFK <- as.numeric(total2$CPFPGGIFK)
>>> total2$CPFPGSPEK <- as.numeric(total2$CPFPGSPEK)
>>> RegModel.1 <- lm(CPFPGGIFK~CPFPGSPEK, data=total2)
>>> summary(RegModel.1)
>>> anova(RegModel.1)
>>> plot(RegModel.1)
>>> termplot(RegModel.1)
>>> bptest(CPFPGGIFK~CPFPGSPEK, varformula = ~ fitted.values(RegModel.1), studentize=FALSE, data=total2)
>>> dwtest(CPFPGGIFK~CPFPGSPEK, alternative="greater", data=total2)
>>> resettest(CPFPGGIFK~CPFPGSPEK, power=2:3, type="regressor", data=total2)
>>> outlier.test(RegModel.1)
>>> #Graphs
>>> oldpar <- par(oma=c(0,0,3,0), mfrow=c(2,2))
>>> plot(RegModel.1)
>>> par(oldpar)
>>> qq.plot(RegModel.1, simulate=TRUE, labels=FALSE)
>>> cr.plots(RegModel.1, ask=FALSE)
>>> av.plots(RegModel.1, ask=FALSE, identify.points=TRUE)
>>> influencePlot(RegModel.1)
>>> trellis.device(theme="col.whitebg")
>>> plot(all.effects(RegModel.1), ask=FALSE)
>>> # Multiple Regression
>>> total2$CPFPGREGT <- as.numeric(total2$CPFPGREGT)
>>> total2$CPFPAVOCT <- as.numeric(total2$CPFPAVOCT)
>>> total2$CPFPASPET <- as.numeric(total2$CPFPASPET)
>>> total2$CPFPABILT <- as.numeric(total2$CPFPABILT)
>>> RegModel.2 <- lm(CPFPGREGT~CPFPAVOCT+CPFPASPET+CPFPABILT, data=total2)
>>> summary(RegModel.2)
>>> anova(RegModel.2)
>>> plot(RegModel.2)
>>> termplot(RegModel.2)
>>> vif(RegModel.1)
>>> bptest(CPFPGREGT~CPFPAVOCT+CPFPASPET+CPFPABILT, varformula = ~ fitted.values(RegModel.1), studentize=FALSE, data=total2)
>>> dwtest(CPFPGREGT~CPFPAVOCT+CPFPASPET+CPFPABILT, alternative="greater", data=total2)
>>> resettest(CPFPGREGT~CPFPAVOCT+CPFPASPET+CPFPABILT, power=2:3, type="regressor", data=total2)
>>> outlier.test(RegModel.1)
>>> #Graphs
>>> oldpar <- par(oma=c(0,0,3,0), mfrow=c(2,2))
>>> plot(RegModel.2)
>>> par(oldpar)
>>> qq.plot(RegModel.2, simulate=TRUE, labels=FALSE)
>>> cr.plots(RegModel.2, ask=FALSE)
>>> av.plots(RegModel.2, ask=FALSE, identify.points=TRUE)
>>> influencePlot(RegModel.2)
>>> trellis.device(theme="col.whitebg")
>>> plot(all.effects(RegModel.2), ask=FALSE)
>>> # Chi-square
>>> chisq.test(total2$campus.rating, total2$grade.type))
>>> # Aggregate
>>> attach(total2)
>>> cref_cfin_cstud_agg <-aggregate(total2, by=list(REGION),
>>>   FUN=mean, na.rm=TRUE)
>>>
>>> _______________________________________________
>>> R-sig-teaching at r-project.org mailing list
>>> https://stat.ethz.ch/mailman/listinfo/r-sig-teaching
>>>
>>
>> _______________________________________________
>> R-sig-teaching at r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-sig-teaching
>>
>
> _______________________________________________
> R-sig-teaching at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-teaching
>