CLG Topic 02

CLG Topic 02 - Stat 502 Topic #2 CLG Handout Activity #1...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
Stat 502 Topic #2 – CLG Handout Activity #1 Data concerning statewide average SAT scores was obtained from www.amstat.org . A complete description of the data set may be found at http://www.amstat.org/publications/jse/datasets/sat.txt . Variables in this data set include (all for 1994-95 school year) 1. STATE = Name of the state (note: to read this into SAS we use “state$”) 2. EXPEND = Total expenditure per student (in thousands of dollars) 3. STRATIO = Average student/teacher ratio in schools in the Fall of 1994 4. AVSAL = Average annual salary for teachers 5. PERCELIG = Percentage of all eligible students who took the SAT 6. VERBAL = Average verbal SAT Score 7. MATH = Average math SAT Score 8. SCORE = Average total score on the SAT For the present, we will analyze only a few of these variables. Our response of interest will be the total SCORE, and we will consider expenditures and the percentage of eligible students taking the SAT as possible predictors. Using the output on the pages following, please discuss the following questions in your groups. Learning Goals : (1) Recognize important features of scatter plots; (2) utilize scatter plots to assist in determining an appropriate regression model; (3) be able to use SAS: PROC GPLOT. 2.1 Consider the plots shown on page 3. Taking the SAT score as the response variable, consider each of the two predictors (expend and percelig) and discuss the following questions a. Do you think there is a relationship between the variables? b. Is it reasonable to consider a linear relationship? c. Does the indicated direction of the relationship make sense? d. Assuming a regression relationship is deemed to be statistically significant, are there any problems that may be indicated from the scatter plots (e.g. outliers, etc) 2.2 Now consider the plot shown on page 4 and reassess your answers regarding the relationship between Average total score on the SAT and the percentage of eligible students taking the exam. 2.3 Are there any other scatter plots which you would like to review? For any plot you identify, discuss why you think it would be an important plot to consider?
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
SAS Coding for GPLOT (you will typically want to experiment with the SAS files outside of the class – I will generally not include all of the code in the learning activity handouts) data sat; infile '<insert correct path here>\sat.dat' ; input state$ expend STratio avsal percelig verbal math score; proc print data =sat; run ; *Scatter Plots: We will use the GPLOT procedure. SYMBOLn and AXISn statements will be used to make the plot look nice. The ORFONT is a very nice set of filled graphical symbols (you can see them by simply searching ORFONT in the SAS HELP. In a symbol statement, v=?? sets the symbol, i=?? sets a line type, c=?? sets color; symbol1 font =ORFONT v =G i =rl; title1
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 02/20/2012 for the course STAT 502 taught by Professor Staff during the Fall '08 term at Purdue.

Page1 / 10

CLG Topic 02 - Stat 502 Topic #2 CLG Handout Activity #1...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online