Ed161 
Start-up Problem
Due Jan 7 2000



The High School and Beyond data set (HSB) is provided in the course  
directory.                                                                           

The student-level file is HSB1.dat and the school-level file is HSB2.dat             
path: /usr/class/ed260/HSB*.dat  or 
/afs/ir.stanford.edu/class/ed260/HSB*.dat 

Update 1/5. In addition to the web-access indicated on the main page,
the data sets are available in both the ed161 and ed260 class 
directories.  To wit:

           elaine6.Stanford.EDU% cd /usr/class/ed161
           elaine6.Stanford.EDU% ls
           HSB1.DAT     HSB2.DAT     WWW          
           elaine6.Stanford.EDU% cd
           elaine6.Stanford.EDU% cd /usr/class/ed260
           elaine6.Stanford.EDU% ls
           HSB1.DAT  HSB2.DAT  WWW                     

Level-1 file. The student level-1 file has 7185 cases (rows) and                     
four variables (not including the school ID).                                        
In HSB1.dat the columns are                                                          
School ID                                                                            
minority, an indicator for student ethnicity (1 =  minority, 0 = other)              
female, an indicator for student gender (1 female, 0 = male)                         
ses, (a standardized scale constructed from variables measuring 
                    parental education, occupation, and income)                                          
mathach, a measure of mathematics achievement                                        

In HSB2.dat, which contains 160 schools with 6 variables per school,     
the columns are                                                          
School ID                                                                
size (school enrollment)                                                 
sector (1 = Catholic, 0 = public)                                        
pracad (proportion of students in the academic track)                    
disclim (a scale measuring disciplinary climate)                         
himnty (1 = more than 40% minority enrollment, 0 = less than 40%)        
meanses (mean of the SES values for the students in this school who 
         are included in the level-1 file; typical of the HLM guys 
         these don't match exactly)                                                           

For this exercise take the data from first public school and the first 
catholic school listed in these data sets.  
1. For each school construct a descriptive plot of mathematics achievement:
a stem-and-leaf, a dot plot, or other plot.  Comment.
2. For each school construct a numerical descriptive summary of mathematics 
achievement (e.g. the Minitab describe command). Comment.
3. Taking the students in the first public school to be a sample from the 
population of public school students and the students in the first catholic 
school to be a sample from the population of catholic school students, use an
appropriate statistical procedure to compare mathematics achievement
in public schools and catholic schools.  (e.g. 95% interval estimate for the
difference between public schools and catholic schools).
4. Within each school, plot math achievement against SES and obtain the
sample correlation coefficient. Which school has a larger value for the slope
of a Math on SES regression?                                           
--------------
END