Normal distribution

1
Normal distribution
2
Assessment of normality

• Outliers
• Skewness Platycurtic and leptocurtic
• Kurtosis peakedness
• Dichotomies

3
Assessment of normality Visual assessment

• Histograms
• A graph of empirical by theoretical cumulative
  distribution functions (cdf's)
• P-P plot

4
Assessment of normality Tests

• Shapiro-Wilks W test is the standard test of
  normality (offered in the SPSS and SAS).
• Kolmogorov-Smirnov D test or K-S Lilliefors test,
  is an alternative test of normality for large
  samples (also available in SPSS and SAS)

5
Transformations
6
Outliers

• 1) Errors of data entry proofread your data
  for out-of-range entries and other errors.
• 2) Not defining missing values?
• 3) Unintended sampling eliminate
  non- population members from the sample.
• 4) True non-normal distribution.
• 5) Simple outliers

7
Experiments

• Mensurative
• Manipulative

8

• Advantage of mensurative experiment
• Relevant biological variation (we have not
  altered it)
• Disadvantage of mensurative experiment
• We may conclude that there is a link between
  factors when there is no direct link

9

• Advantages of manipulative experiment
• Avoids problems of mensurative experiments
• Disadvantages of manipulative experiment
• Experiment may not be biologically realistic

10
Pseudoreplication

• Pseudoreplication is defined as the use of
  inferential statistics to test for treatment
  effects with data from experiments where either
  treatments are not replicated (though samples
  maybe) or replicates are not statistically
  independent.
• Remember to take a look at Hurlberts paper when
• you have time.