EvaluationDashboard.com

I am the teaching assistant for EPSY 8262 Statistical Methods II: Regression and the General Linear Model, taught by Dr. Jeffrey D. Long. is the statistical software that we use in the course. Installing and using R can be difficult at first, so I’ve gathered some helpful resources for students and others who are getting started.

• Installing R video tutorials by Milton Mayfield
• Statistics with R video tutorials by Mohammad Ehsanul Karim
• Contributed documentation in many languages
• R Reference Card by Tom Short
• Simple R by John Verzani
• Practical Regression and Anova using R by Julian Faraway
• Using R for Data Analysis and Graphics by John Maindonald
• R-help search engine (highly recommended) by Seyed Reza Jafarzadeh, which searches the mailing list archives.
• For spatial statistics (not pertinent to EPSY 8262), I created an R-sig-Geo search engine to retrieve information from those archives.
• R Commander graphical user interface (GUI) by John Fox
• Data Analysts Captivated by R’s Power, a New York Times article by Ashlee Vance

Minnesota newspapers have been covering a Wilder Research study that I helped conduct. Here are some of the news articles:

• Kids not ready for kindergarten cost Minnesota schools $113 million a year
• Unprepared kindergartners cost districts millions
• Study: Lack of early education costly
• New study estimates unprepared kindergarteners cost Minnesota K-12 school system $113 million annually

Bush Foundation commissioned the report because several experimental and quasi-experimental studies have shown that disadvantaged children and society benefit greatly from quality preschool experiences, but the costs and benefits had not been tallied for the K-12 system specifically. Temple and Reynolds (2007) provide a good overview of the larger costs and benefits. Schools incur costs when students repeat grades or drop out before graduation ($66.4 million annually); when student behavior problems and low achievement lead to teacher absenteeism, turnover, and extra compensation ($28.9 million); when English Language Learners enter kindergarten with no educational introduction to English ($11 million); and when schools are forced to combat delinquency ($6 million). Expanding quality preschool experiences in Minnesota would likely reduce the $113 million shouldered annually by the state’s K-12 education system.

What factors influence a school district’s ability to improve student achievement? With that as my guiding research question, I decided to explore whether demographic and financial variables represent latent factors. If not, then each may influence achievement individually. Using school district information published the Minnesota Department of Education, I explored the latent factor structure of 12 theoretically important predictors of school district success. Before conducting the EFA, I transformed variables with skewed distributions and removed multivariate outliers exhibiting high Mahalanobis distance.

Results from the factor analysis suggest that the predictors load on three latent factors that explain about 51 percent of total variation in the predictors.
1. Social stratification manifests in higher economic and racial/ethnic segregation and in higher state and federal funding, including appropriations for economically disadvantaged students.
2. Educational enhancement is reflected by higher spending on special education, instructional support services, and pupil support services; lower spending on student activities and athletics; and higher property tax revenue.
3. Regular instruction is apparent in higher spending for regular instruction and in local revenue from sources other than property taxes, although the latter is weakly related. Unclassified local revenue could be removed, reducing it and regular instruction to single, observed variables.

Next steps will include conducting a confirmatory factor analysis with a different year of data and developing a spatio-temporal model of student achievement at the district level.

Data sources
Minnesota Department of Education. (2007a). 2007 Minnnesota Comprehensive Assessment results: Public schools. Saint Paul, MN: Author. Retrieved from: http://education.state.mn.us/MDE/Data/Data_Downloads/Accountability_Data/Assessment_MCA_II/index.html
Minnesota Department of Education. (2007b). School district financial profiles. Saint Paul, MN: Author. Retrieved from: http://education.state.mn.us/MDE/Accountability_Programs/Program_Finance/Financial_Management/School_District_Financial_Profiles/index.html

Minnesota school district demographics, revenues, and expenditures in 2007

Loadings (promax rotated):
           Factor1 Factor2 Factor3
PCT_P.t     0.744  -0.216  -0.043 
PCT_MIN.t   0.583   0.464   0.165 
ADMSPLIS.t -0.475   0.555   0.052 
PROPTREV.t -0.142   0.513  -0.064 
LOCREVO.t  -0.127   0.129  -0.243 
STATEREV.t  0.729  -0.141  -0.157 
FEDREV.t    0.883   0.136   0.053 
RI         -0.046   0.071   0.994 
SE.t        0.211   0.623  -0.310 
SAA.t      -0.233  -0.792  -0.140 
ISS.t      -0.221   0.398  -0.046 
PSS        -0.140   0.447   0.039 

               Factor1 Factor2 Factor3
SS loadings      2.636   2.267   1.230
Proportion Var   0.220   0.189   0.102
Cumulative Var   0.220   0.409   0.511

Factor correlations:
        Factor1 Factor2 Factor3
Factor1   1.000  -0.178   0.122
Factor2  -0.178   1.000   0.192
Factor3   0.122   0.192   1.000