Stats assignment 01 (mostly fiction):
Julie_Freeman_POLM036_20150213

this helps with choice of variable and tests: http://www.statsdirect.com/help/default.htm#methods/relationship_two_variables_measured_on_same_group.htm

My notes:
The null hypothesis is that there is NO association between the two variables. (i.e. women are not more likely to vote left than men)

We want to measure the significance of the association between varX and varY – do this using chi-squared test).
The closer to 1 means the LESS significant the relationship. Use for for category variables — i,e, gender vs the scale
In SPSS, the column marked Asymp. Sig. (2-sided) is the P value

P (probability) value breakdown:

P > 0.10 No evidence against the null hypothesis. The data appear to be consistent with the null hypothesis.
0.05 < P < 0.10 Weak evidence against the null hypothesis in favor of the alternative. 0.01 < P < 0.05 Moderate evidence against the null hypothesis in favor of the alternative. 0.001 < P < 0.01 Strong evidence against the null hypothesis in favor of the alternative. P < 0.001 Very strong evidence against the null hypothesis in favor of the alternative. We want to measure the strength and direction of the relationship using correlation coefficients direction can be positive or negative (tendency) strength is (i think ) the outcome of the Pearson or Spearman or other test:

  • Pearson’s R – interval (scale) variables [use this for age vs L-R scale, do not use with gender]
  • Spearman’s Rank – ordinal (ordered) variables

correlations: -1, 0, +1 (towards either end of scale (closer to 1/-1) = stronger relationship, signs indicate the direction NOT the strength)