This document contains information, questions, R code, and plots.
Hints and reminders are bold
Questions appear in blue.
While questions are in blue, there might be some extra tasks in the text of the exercise. These extra tasks are not mandatory but might help you achieve the blue task or explain why the next blue task is being done.
Group work - while you should submit just one exercise per group, it is a good idea that either all members run all of the code on their own computers and then collectively write the answers. Or, all members help to write the code on one computer. Remember that a lot of the answers require words or an answer not just code!
Definitions of question words. We received feedback that it is not always clear what you need to do for each question, there are definitions of the question words in the Glossary on Blackboard (but we know it is hard to find!). Link to glossary
Needs to be completed and handed in by 26th March 23:59
This week we want you to make some decisions on when to do each analysis. Therefore, we have included code help and hints in separate HTMLs with code not here in the exercise.
As we are getting further through the course, these exercises will start to ask you to make more decisions for yourself. The aim of the course is that you will be able to analyse your own data, so it is good to have some practice doing this without us telling you every step.
All R parts explained in extra code htmls.
lm() as alwaysbestglm()AIC()BIC()anova()Might need to install the bestglm package.
You are the board of directors of a new zoo opening in Norway. You want your zoo to be both exciting and educational, to teach visitors about all different kinds of plants and animals from throughout time. You have been very excited by new advances in cloning technology that you saw in Jurassic Park (you are not very up to date). You have set up a team of biologists to try and clone some dinosaurs to complete your “Ancient History” exhibit. They have been trialling different cloning techniques to try and work out the best protocol.
You have also set up another team to investigate public opinion of dinosaurs. It is very expensive to clone and to keep dinosaurs so you want to make sure that you are investing in the right ones.
Both teams have sent their results back you. Now you must analyse the data and decide on how to set up your dinosaur exhibit.
Your job is to find out how to use resources most efficiently to create an exciting dinosaur exhibit.
This week, we will begin with some very general conceptual points. As you are
part of a board of directors for the zoo, you will need to answer to your
investors. Therefore, you need to begin your recommendation for which
dinosaurs to include with a brief introduction into the statistics you will
use to make this decision and why.
Remember to think about your audience. The shareholders are not scientists, or statisticians. So, make sure your explanation is suitable for non-scientists too.
A1. Why do we have model selection in statistics?
A2. What are two of the different aims of model selection?
A3. How do you perform model selection for each of these? i.e. name the technique don't give all the details
These data have been collected by your team of scientists in the cloning facility. They have been trying to clone several different species of dinosaur using fossils of different ages and different lab procedures. They have recorded the 'success' of the cloning as an index created from the number of viable embryos created, longevity of embryos, and the cost of the cloning method. The index has positive and negative values, positive indicating greater success from the investment. This is called SuccessIndex in the data and is the response variable.
The explanatory variables they collected are: Age this is age of the fossil being cloned in million years, Size this is the average adult body weight of the dinosaur species being cloned in metric tons, Herbivore this is an indicator of whether the species is a herbivore (TRUE) or a carnivore (FALSE).
Think about what kind of data (continuous or categorical) each of these are. It will help you with interpreting.
It is thought that some of these variables might explain the variation in cloning success index. But it is not yet known which.
The dataset for this questions can be found at https://www.math.ntnu.no/emner/ST2304/2021v/Week10/CloneData_2021v.csv
As always, the first step is to import the data and assign it to an object. You can use the whole web link above to import the data. It is a csv file with column names (header) included.
B1. Look at the question at the start of this section (in the title of Part B). Is this question confirmatory or exploratory? Why?
Based on your answer to question B1, open the appropriate help HTML for this section. These are listed in the Resources section.
You do not have to use the HTML document, the code is included in the module for week 10. See if you can try and list the steps you need for B2 before looking at the HTML.
B2. Conduct model selection for answering “which variables influence cloning success?” and Write a report of the steps you took to do this, why, and state what the result was.
To answer this question include a bullet point list of the steps you take to do this. You can include a line or two of R code with each bullet point but you should not need a lot (so, you also need to use words to explain why you are doing each step not only the R code).
Image that you are writing a report to be read by the investors in the zoo when you answer B2. They will want to know the results of each step but also have some idea why you are running certain lines of code.
B3. Interpret the results from the model selection. Include reference to model selection and the final model you end up with. I.e. you should also mention what the effect any variables have
These data were collected from a large survey of the general public. The participants were asked to rate, on a continuous scale (0-100), how much they liked different dinosaur species. The species all differed in size. The board members (your team) think that visitors to your zoo will be more excited to see bigger dinosaurs because bigger dinosaurs are more popular.
The dataset has columns: PopularityScore the popularity score of the d inosaur species, Weight weight of the species in metric tons (a measure of size).
The data for this question can be found at https://www.math.ntnu.no/emner/ST2304/2021v/Week10/DinoData_2021v.csv
As always, the first step is to import the data and assign it to an object. You can use the whole web link above to import the data. It is a csv file with column names (header) included.
C1. Look at the question at the start of this section (in the title for Part C). Is this question confirmatory or exploratory? Why?
C2. Conduct model selection for answering “does the size (weight) of a dinosaur affect its popularity?” and Write a report of the steps you took to do this, why, and what the result was.
To answer this question include a bullet point list of the steps you take to do this. You can include a line or two of R code with each bullet point but you should not need a lot. (Again, R code alone will not answer this question, also say why you do each step).
Image that you are writing a report to be read by the investors in the zoo when you answer C2. They will want to know the results of each step but also have some idea why you are running certain lines of code.
C3. Interpret the results from the model selection. Include reference to model selection and the final model you end up with. I.e. you should also mention what the effect of any variables are
D1. Based on all of your results, what would you recommend as a way to create an efficient and exciting exhibit?
E1. If you were to do this analysis in real life, is there anything you would change about the experimental design or the analysis? Was anything missing? Any extra steps you would take or extra information you might want?
These next questions are to help you think critically about your own work, as well as to help us to give you feedback that is actually useful. It is a chance to sit back and think about how well you think you did on the exercise.
E2. How do you think your group did on this exercise? Are there areas you are pretty sure you got correct? Any you are not very sure? Anything new you learned while doing the exercise?
E3. How does this compare to last week?
E4. Any particular areas you find challenging?
E5. What would you like feedback on this week?