Ch 12 &13

Card Set Information

Ch 12 &13
2014-07-30 11:27:40

Last bit of Intro Stats II before the final
Show Answers:

  1. Analysis of Variance (ANOVA)
    A procedure used to test the Null Hypothesis that the means of three of more populations are equal.
  2. The grand mean for all k-samples is
  3. SST, SSB AND SSW must always be...
    positive, since it's they're the sum of squares
  4. The point estimator for the unknown common variance σk2 is
    Mean Square within (MSW)
  5. Assumptions for ANOVA
    • a. k-samples are random and independent
    • b.Each of the k-samples came from a normal population
    • c. σ21, σ22, σ23, ,σ2k are unknown but equal
  6. The Statistical Linear Regression model is
  7. SSxx or SSyy must always be...
  8. Sxy can be...
    positive or negative
  9. To Construct a (1-)100% Confidence Interval for unknown B, use
    , where
  10. When solving for b in the estimated regression model...
    write the equation out in general form first. If there it is "a-bx" that means "a+(-b)x" which implies b is negative
  11. The population correlation
    denoted by and defined as the strength of the relationship between two variables, x&y.
  12. The sample correlation
    denoted by r. Since the population correlation Rho is usually unknown, the point estimator of the population correlation is the sample correlation r.
  13. The range for is
  14. if r~1
    we have a perfect relationship between x&y in a positive way. That is, if x increases, y increases.
  15. if r~-1
    if x increases, y decreases. Or if x decreases, y increases
  16. if r~0
    the variables x&y are not related
  17. Coefficient of Determination
    denoted by for the population and r2 for the sample. But or is usually unknown. The coefficient of determination for the samples represents the % of variation in the dependent variable y, explained by the independent variable (x) in the extimated least squares regression model ŷ. The higher the value of r2 the better it is.
  18. The test statistic for Ho: is
  19. If no value of is given, use
  20. For sample correlation r, approximately equal to 1...
    r≈1 for values of r>80% or .8