Science and Experimental Design

Question 1

How much weight should we place on the results of a study?

Answer 1

1. How well characterised are the reagents/experiment/method?
2. How well is the experiment designed?
   - good control
   - possible bias
3. How many times has the result been successfully repeated?

Question 2

Design of experiments

Answer 2

Controlled variables 
Control experiments (experimental controls)

Question 3

What are controlled variables?

Answer 3

variables that an experimenter keeps constant to prevent any confounding effect
ideally only independent variable should be affecting results of experiment

Question 4

Experimental controls- -ve controls

Answer 4

Negative control: sample or experiment to determine what happens without the experimental innervation

should ideally be identical to the experiment except for the one intervention being tested

Question 5

Experimental controls: +ve controls

Answer 5

sample or experiment to show that the experimental system will have an effect if the intervention really does have an effect

Question 6

Controls

Answer 6

control should differ from the experiment in one factor only
design of controls is crucial

Question 7

What are biases?

Answer 7

If you haven’t eliminated all biases from your experiments then any stats you calculate are meaningless

e.g. of inappropriate bias:
- using inappropriate control
-failing to take a truly random sample from population
human bias in observation
selecting which data to include after you’ve seen the results of the experiment

Question 8

Why do we perform replicates?

Answer 8

to detect anomalies due to human or experimental errors

to minimise the effect of random error and random variation by taking an average

Question 9

Why do we repeat experiments?

Answer 9

human errors, anomalies, random variation can potentially affect all observations in an experiment

only by repeating an experiment on multiple separate occasions can we have scientific confidence in the results

Question 10

What are systematic errors?

Answer 10

errors that bias the data in a particular direction
e.g. miscalibrated pipette always adds too low a volume of a sample

important to validate experiment, reagents and assays before starting experiment

Question 11

What are random errors?

Answer 11

Errors that may randomly increase or decrease your readings