ML Crosssword #9

  1. 4. calculated by dividing MSR (mean squared regression) by MSE (mean squared error), or explained variance by unexplained variance
  2. 7. Having or having to do with a single variable
  3. 10. a family of curves indexed by a parameter called the degrees of freedom, which can take the values 1, 2, …
  4. 11. a measure of the joint variation between variables
  5. 13. The difference between a datum and the value predicted for it by a model
  6. 14. error occurs if the null hypothesis is not rejected when it is in fact false
  7. 15. error occurs when the null hypothesis is rejected erroneously when it is in fact true
  8. 16. A "dummy" treatment that has no pharmacological effect
  9. 17. calculations that provide information about levels of variability within a regression model and form a basis
  10. 18. tests of significance
  1. 1. A time series where underlying generating process does not have a constant mean and/or a constant variance
  2. 2. a sample where subsets of sampling units are selected separately from different strata, rather than from the frame as a whole
  3. 3. the smallest significance level for which any of the tests would have rejected the null hypothesis
  4. 5. A distribution that is not symmetrical
  5. 6. What is true for the parts is not necessarily true for the whole
  6. 8. Having exactly one mode
  7. 9. indicates how much of the dependent variable’s total variation is accounted for by the predictor variable
  8. 12. An hypothesis test based on approximating the probability histogram of the Z statistic under the null hypothesis by the normal curve