Unit 6 Repeated Measures ANOVA

Question 1

Whats a repeated measures design

Answer 1

When a subject is tested, on the same variable, over time: repeated measures design.
Living objects change in time: we need to measure them repeatedly.
Design used to evaluate results when we know a baseline (initial state before an event of manipulation)

Question 2

Whats a repeated measures ANOVA looking at

Answer 2

When we want to demonstrate that the changes in values of the dependent variable depend on the treatment applied.
Similar to a paired sample t-test but with more than two levels for grouping variable and several measurements for those levels (i.e. the repeated measurements)

Question 3

Whats a dependent variable

Answer 3

what we measure e.g. number of infaunal species in seabed

Question 4

Whats an independent variable

Answer 4

Factor, with levels e.g. fishing pressure.
No fishing, dredge, pots. Or time: baseline vs Time 1 vs Time 2…to assess recovery (AKA ‘Within-subjects factor’)

Question 5

Whats a subject

Answer 5

different levels of the variable ‘Subject’,
e.g. Fixed quadrats in an experimental area of similar biotic and abiotic conditions

Question 6

Advantages of repeated measures ANOVA

Answer 6

similar to paired samples t-tests it requires fewer subjects (test species, quadrats, plots) and eliminate between-subjects differences from the residual (unexplained) variance (error or noise)

Question 7

What does repeated measures ANOVA consider

Answer 7

Considers the temporal autocorrelation (non-independence of samples)

Question 8

Conditions in repeated measures

Answer 8

Reduces no. of independent samples needed by measuring the same individual several times or giving different treatments.
If variation among individuals is large, there’ll be large unexplained variation in the model if considered independent samples.

Question 9

Disadvantage of repeated measures.

Answer 9

Samples are not independent, carryover effects.
(leave enough time for the treatment to wear off if interested in the treatment (not on time as a factor))

Question 10

Why are repeat measures ANOVA more powerful

Answer 10

more powerful as a result of a partitioning of the error term. F factor statistic is thereby increased.
This is balanced by a decrease in df error.

Question 11

Whats the assumption of spericity

Answer 11

Sphericity is the condition where the variances of the differences between all combinations of related groups (levels) are equal.

Question 12

What is Mauchly’s Test of Sphericity

Answer 12

Used to test whether or not the assumption of sphericity is met in a repeated measures ANOVA. Sphericity refers to the condition where the variances of the differences between all combinations of related groups are equal.

Question 13

What does the Bonferroni correction for post hoc tests do

Answer 13

This multiple-comparison post-hoc correction is used when you are performing many independent or dependent statistical tests at the same time.
The problem with running many simultaneous tests is that the probability of a significant result increases with each test run.

Question 14

What is the Non-parametric alternative to repeated
measures ANOVA

Answer 14

Friedman’s Test

Question 15

Whats the Friedman’s Test do

Answer 15

Non-paramteric equivalent of a repeated measures ANOVA.
Tests whether the medians of two or more sets of related measurements are different from each other.

Question 16

Assumptions of Friedman’s test

Answer 16

One group is measured on 3 or more occasions.
The scale of the measurement within the variables must be at least ordinal in nature.
The subjects represent a random sample of subjects.

Question 17

What does ANOVA stand for

Answer 17

ANOVA stands for Analysis of Variance. It’s a statistical test that was developed by Ronald Fisher in 1918 and has been in use ever since. Put simply, ANOVA tells you if there are any statistical differences between the means of three or more independent groups. One-way ANOVA is the most basic form.