B) Testing assumptions: normality and outcomes

Question 1

interpreting Shapiro-wilk

Answer 1

• if the assumption of normality has not been violated, the significant value will be greater than .05
• if the assumption of normality has been violated, the significant value will be less than .05. this means your sample distribution is significantly different from a normal distribution.

Question 2

histogram - checking normality from frequency distribution of DV

Answer 2

• when inspecting a histogram for normality, you are looking for a ‘bell curve’

Question 3

skatterplot - checking normality on Q-Q plot

Answer 3

if our data is from a normal distribution, we should see points forming a line that is roughly straight

Question 4

box plot - checking normality

Answer 4

a box plot is a standardised way of displaying the distribution of data based on the median and quartiles. it can tell you if your data is symmetrical, how tightly your data is grouped and if and how your data is skewed.

Question 5

normality summary of skewness and kurtosis z-values

Answer 5

should be somewhere in span of -1.96 to +1.96.
if over +/- 1.96 then statistically different from normal distribution at p<0.05 level

Question 6

normality summary of Shapiro-wilk test p value

Answer 6

should be above .05 to indicate the data is not significantly different from normal distribution=it normally distributed

Question 7

normality summary of histograms, Q-Q plots, boxplots

Answer 7

should visually indicate that our data are approximately normally distributed and can indicate whether there are outliers