Experimentation Flashcards
What does the term accuracy mean ?
Data, or means of data sets, are close to the true value
What does the term precision mean ?
Measured values are close to each other
What does reliability mean ?
Consistent values in repeats and independent replicates
What does validity mean ?
Variables are controlled so that any measured effect is likely to be due to the independent variable
What is a pilot study ?
A pilot study is a small-scale investigation of a planned research project.
-They are integral to the development of an investigation
Why do a pilot study ?
-To ensure an appropriate range of values for the independent variable.
-Allows evaluation and modification of experimental design.
-Allows one to check techniques
-Help assess validity
-Help plan procedures
In addition, allows establishment of the number of repeat measurements required to give a representative value for each independent datum point.
What are variables ?
Variables are factors which can be changed, controlled or measured within an experiment.
There are usually three types within an experiment; Independent, dependent and confounding variables.
What is an independent variable ?
-The variable which is changed in a scientific experiment
-Experiments involve the manipulation of this variable by the investigator
What is a dependent variable ?
-The variable which is being measured in a scientific experiment
What categories can different types of variables be put into ?
Independent and dependent variables can be continuous or discrete
What is a discrete variable ?
Discrete variables can be grouped
What is a continuous variable ?
Continuous variables have a wide range of values that can be measured on a scale between a maximum and a minimum.
What is a confounding variable ?
Any variable, other than the independent variable, which can effect the dependent variable, due to the complexities of biological systems.
These must be held constant if possible, or at least monitored, so their effect on the results can be accounted for in the analysis.
Control of confounding variables help to ensure that investigation results are valid.
What happens if you cannot (easily) control a confounding variable ?
A randomised block design could be used
What is a randomised block design ?
-Experiment subjects are assigned into groups (“blocks”) before being assigned to a treatment group.
-Blocks of experimental and control groups can be distributed in such a way that the influence of any confounding variable is likely to be the same across the experimental and control groups.
What does the term treatment mean ?
-The treatment refers to the variable being investigated
-The experimental treatment group is compared to a control group
What is a simple experiment ?
One independent variable only
What is a multifactorial experiment ?
Involve a combination of more than one independent variable or combination of treatments.
In general, as experimental designs increase in complexity, more information can be obtained and analysed as welll as allowing the effects of different interactions to be detected
Discuss the use and limitations of a simple experiment
Advantages
-Laboratory conditions can be carefully controlled so allows simple experiments to be conducted more easily than in the field.
Limitations
-The findings may not be applicable to a wider setting.
Discuss the use and limitations of a multifactoral experiment
Advantages
-Complex interactions examined and allows generalisations to be made
Limitations
-More complex and time consuming.
-Difficult to control all variables.
-Data analysis is complex
What is an observational study ?
The independent variable is not directly controlled by the investigator, for ethical or logistical reasons.
Use of groups that already exist, so there is no truly independent variable
Observational studies are good at detecting correlation, but since they do not directly test a hypothesis, they are less useful for determining causation