Design of experiements

Question 1

Increasing replication

Answer 1

Reduces SE

Question 2

Why are controls necessary

Answer 2

To determine if the sample group is truly effected by what you are changing hence important to control other variables. ie reject null hypothesis that u1 = u2

Question 3

Size of sample?

Answer 3

Large enough = representative

Appropriate to be ethical and cost effective

Question 4

Excluding bias

Answer 4

Randomisation, controlling confounding factors, blinding

Question 5

Power

Answer 5

Probability to reject the null hypothesis

Function of difference in pop means (increase AD = increased power)

SD (Increased = reduced power)

Sample size ( increased sample = increased power)

Question 6

Larger populations

Answer 6

Need larger sample due to increase variability

Question 7

Computing the sample size from power

Answer 7

u1-u2)/o

Question 8

To determine the Power

Answer 8

1st = decide what difference need to be picked up ( This is often difficult to determine but crucially isn’t the difference in means or the latest literature - sometimes it isn’t possible to specify

2nd = Compute the SD
3rd = Decide on the power wanted

Question 9

(2𝜎^2 〖(𝑧_(𝛼/2)+𝑧_𝛽)〗^2)/〖(𝜇_1−𝜇_2)〗^2

Answer 9

(2𝜎^2 〖(𝑧_(𝛼/2)+𝑧_𝛽)〗^2)/〖(𝜇_1−𝜇_2)〗^2

Question 10

How do randomisation and replication control variance

Answer 10

Replication  = o/sqn
Randomisation = unbiased treatment estimator 

NB there may be problems relying on randomisation alone

Question 11

Restricted randomisation

Answer 11

Ie blocking/ stratification prevents poorly distributed groups ie in clinical trials equal number of diabetics, ages sexes in both arms

Removes confounding variables as both are present in both populations to equal extent

NB factors must be known

Question 12

ANOVA

Answer 12

Used for stiuations in between unpaired and paired t-test. 3+ variables. Stands for analysis of variance.

For example
1 All mice in same cage = unpaired t
2 Pairs of mice in single cage x 6 = paired t test
3 Four mice in a cage x 3= ANOVA

Question 13

Normal distribution

Answer 13

Independence of observations – this is an assumption of the model that simplifies the statistical analysis.
Normality – the distributions of the residuals are normal.
Equality (or “homogeneity”) of variances, called homoscedasticity — the variance of data in groups should be the same

Question 14

Factorial designs

Answer 14

Change of two variables at once ie fluid and salt level

High fluid, high Na
High fluid, low Na

Low fluid, high Na
Low fluid, low Na

Question 15

Benefits

Answer 15

Efficient, can investigate salt by fluid interaction

Question 16

Catch of factorial design

Answer 16

Unfeasible for more than 2 variants

Only works if both variants are linked and measure the same thing

Question 17

Interaction factorial design

Answer 17

Change in Na at low fluid vs change in Na at high fluid

Difference in Na as fluid level changes. Only possible with factorial design

Question 18

Pseudoreplication

Answer 18

Artificially inflating number of samples or replicates than what occurs naturally - often occurs insidiously and due to lack of independence in replicates

Question 19

Outcome of pseudoreplication

Answer 19

Underestimate of o hence SE. Hence more likely to get misleading small p-value

Question 20

Common source of pseudoreplication

Answer 20

Ignoring groupings!

Wt loss between GP practises - Underestimate of o due to same GP having same nurse, same group motivation, enviroment etc not independent

Question 21

Remove pseudoreplication

Answer 21

Experiment design