AP2A61 - Experimental design and data analysis
Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit
AP2A61 - Experimental design and data analysis
Assessment brief – Experimental Design Exercise
Weighting of assessment
This assessment is worth 30% of your module mark.
Overview and learning outcomes assessed
This exercise aims to assess your ability to prepare an experimental design that would test a stated null hypothesis, explain your reason for choosing the experimental design and do a power analysis of this design.
Requirements
You are required to produce a written document containing details of an experiment that you have designed . The experiment you design should relate to one of two research questions described below.
Your written document should include:
• A statement of the null hypothesis that you would test with the experimental results
• A statement of the statistical method that you would use to analyse the results
• A diagram illustrating the experimental design, i.e. the layout of plots in thefields, or pens in the hen house
• A description of each step you have taken to develop your design and a brief statement of your rationalefor each step (you might choose to present this in a table – see example). This should also include evidence of the steps you took,for example a screen shot of the mock data you created (if you do this in Excel), or a copy of the R script you used (if you do this in R).
• A statement about the power of the design and whether this is a reasonable power or if the design would need improvement, if so you suggest how the design might be improved.
You can do your power analysis using a simulation approach (as covered in the lecturesfor this course) or an alternative approach if you prefer.
Choosefrom one of the two research questions below. You may need to make additional assumptions about the experiment, and if you do this you should state them in your description of the steps you took in developing the design.
EITHER
Research scenario 1:
A new variety of field-bean “Resisto” is advertised as giving 20% better yield than “Faithful”, the current best variety. Your trials company is commissioned by an advisory group to test this yield claim. The advisory group are suspicious of the yield claim. They suspect that while Resisto yields may be greater than Faithful on unfertilised crops this will not be the case for well fertilised crops.
You have been tasked with designing an experiment with sufficient power so that a difference between the two varieties could be detected if it exists, ideally using both fertilised plots and unfertilised plots if possible.
For the experiment, you have been assigned sections in two fields shown below, each with space for 14 plots, so 28 plots in total. These two fields have different soil types, but yields
across the field are fairly uniform.
After analysis of a bean trial from three years ago, using plots of the same size and accounting for the blocking and treatment structure in that trial, the standard deviation of the yield was 10% of the mean yield. This gives you a measure of the unexplained variability that you might expect to observe in your experiments.
OR
Research scenario 2:
A new breed of broiler chicken “Star Grow” has been bred and it is claimed that the average carcass weight after 34 days is 20% greater than that of the current standard breed “Smiths”. Your trials company is commissioned by an advisory group to test this claim. The advisory group are suspicious of the claim. They suspect that the average weight of Star Grow carcasses will only be greater than Smiths if a high lysine supplement is provided in the diet, but that this difference would not be observed if a typical, lower lysine supplement was given.
You have been tasked with designing an experiment with sufficient power that a difference between the carcass weights after 34 days could be detected between the two breeds if it exists, ideally also considering two diets; one with a low lysine supplement and one with a high lysine supplement.
For your experiment, you have available a supply of chicks of the two breeds, and a 3 housing sheds within a research facility each containing 10 pens as shown below. Both breeds were hatched on the same day.
In a previous feeding experiments 100 chicks of the same breed were allocated to each pen and the carcass weight was measured as an average for the pen. You should do the same – i.e. you will have one measurement of carcass weight for each pen that has already accounted for variability within the pen. After analysis of these feeding trials, the standard deviation of the carcass weight between pens was 10% of the mean carcass weight of pens. This gives you a measure of the unexplained variability that you might expect to observe in your experiments.
Assessment criteria
Your experimental design document will be marked in accordance with the University Wide Framework for Degree Classifications (available in your Undergraduate Student Handbook) and will be assessed against the following criteria:
• Appropriateness of the proposed design and analysis method for testing the stated null hypothesis (which should be relevant to the research scenario)
• Demonstration of a sensible and relevant design process used to develop this design, including a power analysis
• Demonstration of critical thinking by justifying decisions made in the design process
• Clear and concise
Submission details
Your assignment must be submitted electronically to Turnitin via Blackboard by midday on 24th January 2022 using the submission point provided on theAP2A61 Blackboard course.
Return date for marked work
It is expected that your marks and feedback will be released via Blackboard on Monday 14th February.
Penalties for late submission
The Module Convener will apply the following penalties for work submitted late, in accordance with the University policy.
• where the piece of work is submitted up to one calendar week after the original deadline (or any formally agreed extension to the deadline): 10% of the total marks available for the piece of work will be deducted from the mark for each working day (or part thereof) following the deadline up to a total of five working days;
• where the piece of work is submitted more than five working days after the original deadline (or any formally agreed extension to the deadline): a mark of zero will be recorded.
The University policy statement on penalties for late submission can be found at:
http://www.reading.ac.uk/web/FILES/qualitysupport/penaltiesforlatesubmission.pdf
You are strongly advised to ensure that coursework is submitted by the relevant deadline. You should note that it is advisable to submit work in an unfinished state rather than to fail to submit any work.
Plagiarism
Plagiarism is thefraudulent representation of another’s work as one’s own. This applies to whatever the source of the material (for example, a published source, the web, or the work of another student), whether the material is copied wordfor word or paraphrased, and whatever the extent of the material used (including ideas, arguments, words, diagrams, images or data).
Plagiarism is a form of academic misconduct and will be penalised accordingly.
By submitting your work online you are making the following declaration:
By submitting my work online, I certify that it is my own work and use of materialfrom other sources has been properly andfully acknowledged in the text. I have read the definition of plagiarism given above and the advice on good academic practice contained in the Programme Handbook. I understand that the consequence of committing plagiarism, if proven and in the absence of mitigating circumstances may includefailure in the Year or Part of my programme or removalfrom membership of the University. I also certify that neither this piece of work, nor any part of it, has been submitted in connection with another assessment.
2022-01-19