GoConqr has a new look! Let us know what you think.

Flashcards

Requirements for tests

kiren bains English 10 cards

Cards in this deck (10)

  1. 1Paired t-test-Parametric
    -Within
    -Scale, normal distribution
    -Purpose is to test if two means within the same group of pp's are significantly different.
  2. 2Independent t-test-Parametric
    -Between
    -Scale, normal distribution, equal variances.
    -Purpose is to test if two means between different groups of pp's are significantly different.
  3. 3Pearson Correlation-Parametric
    -Within
    -Scale, normal distribution
    -Used to test if the scores on two separate variables vary proportionately (+ve, -ve).
  4. 4Wilcoxon-Non Parametric
    -Within
    -Ordinal (skewed) data
    -used to test if ranks in one condition are significantly larger or smaller than the ranks in the other condition.
  5. 5Mann Whitney-Non Parametric
    -Between
    -Ordinal data
    -To test if ranks in one condition are significantly larger or smaller than the ranks in the other condition.
  6. 6Spearman Correlation-Non parametric
    -Within
    -Ordinal data
    -Purpose is to test if the scores on two separate variables vary proportionately.
  7. 7Chi SquareNon parametric
    Between
    Nominal data
    -to test if the no. of pp's in one category is significantly different from the no. in another.
  8. 8McNemarNon parametric
    Between
    nominal data
    -To test if the no. of pp's in one category is significantly different from the no. in another.
  9. 9Type 1 ErrorThe null is rejected when it should be retained.
    Conclude that there IS a significant difference when there is NOT.
  10. 10Type 2 ErrorNull is retained when it should be rejected.
    We can conclude that there is NO significant effect when there IS.

Information

Description
Flashcards on Requirements for tests, created by kiren bains on 02/05/2016.
Created by
kiren bains · May 2016
Updated
May 5, 2016
Views
3
Rating

Feedback

What is it about?

What do you think of the new look?

How do you like it?