PSPP, Review, Etc.

1
PSPP, Review, Etc.

• Class 9

2
Presentations

• Jennell
• Danielle
• Katie
• Liz

• 2 historical/qualitative brief sharing ?

3
Correlation b/w Dichotomous and Continuous
Variables

• The point biserial correlation coefficient, here
  symbolized as rpb, pertains to the case where one
  variable is dichotomous and the other is
  non-dichotomous. By convention, the dichotomous
  variable is treated as the X variable, its two
  possible values being coded as X0 and X1 and
  the non-dichotomous variable is treated as the Y
  variable.

• http//vassarstats.net/pbcorr.html

4
2 Way Factorial Designs (2 independent variables
often one manipulated, one attribute)
5
Interpreting Results of 2x2 ANOVA

• (columns-main effect) Kodaly was more effective
  than Traditional methods for both bilingual and
  non-bilingual students
• (rows-main effect) Bilingual students scored
  significantly higher than non-bilingual students,
  regardless of teaching method
• Could be a significant interaction between
  language and teaching method
• If there was significant interaction, we would
  need to do post hoc Tukey or Sheffe do determine
  where the differences lie.

6
Post Hoc (ANOVA to Tukey)

• Main Effects for LANG METHOD
• Interaction b/w LANG METHOD (treatment may have
  only worked for one LANG group)
• BT lt BK Plt.01 (no surprise m.e. for meth)
• BT lt NBT Plt.01 (no surprise m.e. for lang)
• BT lt NBLK Plt.01 (no surprise m.e. for meth
  lang)
• NBLT BK nonsignificant
• NBLT NBLK nonsignificant (treatment only
  makes a difference for bilingual students!!)
• BK lt NBLK Plt.01

7
PSPP

• Limited number of tests
• Accurate and fast
• Import CSV EXCEL files
• Comma delimited
• Surveys