Lecture 7 - Quick review of parametric assumptions In order...

Info iconThis preview shows pages 1–7. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Quick review of parametric assumptions In order to use parametric statistics your data must comply with certain assumptions
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Parametric assumptions • Data must be of interval quality or better – Creates ambiguity with Likert scale - if data are normally distributed use parametric test • Normality - Data must be normally distributed. Determined through: – Histogram with large samples can give indication - remains subjective Kolmogorov- Smirnov test - If the p value is statistically significant assumption of normality is unsafe to make
Background image of page 2
3 Parametric assumptions Kurtosis - measures peaked ness -ve indicates too many cases in the tails of the distribution, +ve indicates too few cases in the tails. Assume normality if in range of ±2 Skewness - extent to which data are overly bunched in one tail only. Negative skew is right-leaning, positive skew left-leaning. Assume normality if in range of ±2
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
4 • Homogenity of variance - the variance between groups must be ‘equivalent’ – Formal test when using a between groups test is the Levene’s test. If p is significant then need to change formula slightly or use nonparametric • Independence of observations - performance of one participant should not influence that of another Parametric assumptions
Background image of page 4
5 Analysing frequency data Inferential statistics for nominal data - Chi-square ( χ 2 )
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
6 Options for nominal data • Nominal data involves categories only • If we have an IV which has two levels, both of nominal quality, then we would have an expectation as to how many of each category would be present e.g., males and
Background image of page 6
Image of page 7
This is the end of the preview. Sign up to access the rest of the document.

Page1 / 20

Lecture 7 - Quick review of parametric assumptions In order...

This preview shows document pages 1 - 7. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online