Predicting Terminal Velocity of Samaras based on Disk Loading - Prof. Cecile M. Ane, Assignments of Data Analysis & Statistical Methods

Instructions for an assignment in a university-level statistics course focused on predicting the terminal velocity of samaras based on disk loading. Students are required to examine mass data graphically, calculate means and standard deviations, plot terminal velocity against the square root of disk loading, fit regression models, and perform f-tests. The document also mentions the use of r for data analysis and the provision of a dataset named samara.txt.

Typology: Assignments

Pre 2010

Uploaded on 09/02/2009

koofers-user-jbh
koofers-user-jbh 🇺🇸

10 documents

1 / 2

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
Stat/F&W/Hort 572 Ane January 22, 2009
Assignment #2 Due Friday, Feb. 6, 2009, by 4pm
Turn in lecture, discussion, or to your TA’s mailbox. Please circle the discussion section you expect to pick up
this assignment:
311 312 313 314
Instructions. In a write-up of your solution to this assignment, you do not need to include graphs in your
solution unless the questions specifies this explicitly. You do not need to show Rcode used to create graphs.
In questions that require you to fit a model and comment on estimated coefficients, your solution should
describe the fitted model in an equation with words and units that is distinct from any Rcode used to fit the
model. For example, from the bats data set we discussed in lecture, we could express the model for fitting the
energy requirements for a bird of as a function of its mass as follows:
energy in Watts = 3.32 + 0.0678 ×(mass in grams 260)
Your solution should then also include a summary of the Rcode you used to fit the model and summarize the
results. You should edit the Routput to eliminate material that is not necessary to answer the question. For
example, if you use the summary function, you might choose to include in your solution the table of estimated
coefficients, but you should eliminate the excess output such as quantiles of residuals.
Background. A samara is the winged fruit from a tree that falls to the ground with a helicopter-like motion. A
forest scientist is interested in predicting the terminal velocity of falling samaras based on disk loading, the mass
of a samara divided by the area of the disk it passes through while spinning. A lower velocity could be related to
a larger average dispersal distance allowing samara to drop further from the maternal tree, potentially decreasing
competition for new resultant seedlings.
The scientist collected from 25–30 samaras from each of seven species and measured the disk loading and
terminal velocity of each. The species were white ash (Fraxinus americana), green ash (F. pennsylvanica), tulip
tree (Liriodendron tulipifera), sugar maple (Acer saccharum), boxelder (A. negundo), red maple (A. rubrum), and
silver maple (A. saccharinum). Samaras from the two ash species and the tulip tree are bilaterally symmetric and
roll as they spin. In contrast, the samaras from the maples and the boxelder (genus Acer ) are asymmetric and
they do not roll as they spin. Theoretical study of helicopter rotors suggests that the terminal velocity should be
linearly related with the square root of the disk loading.
The data set for this assignment is on the course web page and is named samara.txt. The columns are:
species: the common name of the species of tree
genus: the scientific genus
velocity: the terminal velocity in centimeters per second
mass: the mass of the samara in milligrams
area: area of the disk while spinning in square-centimeters
loading: the ratio of mass to area
symmetry: a factor indicating if the samara are bilaterally symmetric or not
pf2

Partial preview of the text

Download Predicting Terminal Velocity of Samaras based on Disk Loading - Prof. Cecile M. Ane and more Assignments Data Analysis & Statistical Methods in PDF only on Docsity!

Stat/F&W/Hort 572 Ane January 22, 2009

Assignment #2 — Due Friday, Feb. 6, 2009, by 4pm

Turn in lecture, discussion, or to your TA’s mailbox. Please circle the discussion section you expect to pick up this assignment: 311 312 313 314

Instructions. In a write-up of your solution to this assignment, you do not need to include graphs in your solution unless the questions specifies this explicitly. You do not need to show R code used to create graphs. In questions that require you to fit a model and comment on estimated coefficients, your solution should describe the fitted model in an equation with words and units that is distinct from any R code used to fit the model. For example, from the bats data set we discussed in lecture, we could express the model for fitting the energy requirements for a bird of as a function of its mass as follows:

energy in Watts = 3.32 + 0. 0678 × (mass in grams − 260)

Your solution should then also include a summary of the R code you used to fit the model and summarize the results. You should edit the R output to eliminate material that is not necessary to answer the question. For example, if you use the summary function, you might choose to include in your solution the table of estimated coefficients, but you should eliminate the excess output such as quantiles of residuals.

Background. A samara is the winged fruit from a tree that falls to the ground with a helicopter-like motion. A forest scientist is interested in predicting the terminal velocity of falling samaras based on disk loading, the mass of a samara divided by the area of the disk it passes through while spinning. A lower velocity could be related to a larger average dispersal distance allowing samara to drop further from the maternal tree, potentially decreasing competition for new resultant seedlings. The scientist collected from 25–30 samaras from each of seven species and measured the disk loading and terminal velocity of each. The species were white ash (Fraxinus americana), green ash (F. pennsylvanica), tulip tree (Liriodendron tulipifera), sugar maple (Acer saccharum), boxelder (A. negundo), red maple (A. rubrum), and silver maple (A. saccharinum). Samaras from the two ash species and the tulip tree are bilaterally symmetric and roll as they spin. In contrast, the samaras from the maples and the boxelder (genus Acer ) are asymmetric and they do not roll as they spin. Theoretical study of helicopter rotors suggests that the terminal velocity should be linearly related with the square root of the disk loading. The data set for this assignment is on the course web page and is named samara.txt. The columns are: species: the common name of the species of tree genus: the scientific genus velocity: the terminal velocity in centimeters per second mass: the mass of the samara in milligrams area: area of the disk while spinning in square-centimeters loading: the ratio of mass to area symmetry: a factor indicating if the samara are bilaterally symmetric or not

Stat/F&W/Hort 572 Ane January 22, 2009

  1. Examine the mass of the samaras for each species graphically. Summarize your observations. (Use R to solve, but no graphs or R code is necessary in your summary.)
  2. Find the mean and standard deviation of the terminal velocity and the disk loading separately for each species. Include R code for the calculation. Recall that the function tapply(var, factor, fun) will apply the function fun to a variable var, separately for each level of the factor factor.
  3. Plot terminal velocity versus the square root of disk loading. What features do you notice in the data? Use a different color or plotting symbol for each species. Also (either in separate plots or new plots), use a different color or plotting symbol for each genus, and a different color or plotting symbol for each type of symmetry. Add a legend to your plot(s), either with the function legend in R or manually. Include the plot(s) with your solution.
  4. Based on the visual inspection of these plots, which model best predicts terminal velocity?
  5. Fit five regression models to predict velocity from the square root of disk loading and these additional explanatory variables:

(a) none, (b) species, (c) species and an interaction species - square root of disk loading, (d) genus, (e) symmetry.

For each model, write the equation that predicts the terminal velocity for a sugar maple samara in the style above. Find a numerical prediction for the terminal velocity of a sugar maple samara with disk loading value 3.0 mg/cm^2 for each model.

  1. Use the regression model from (5e) above to predict the terminal velocity of an individual samara from each species where the disk loading is average for that species. (Use the mean found in the second question.)
  2. Use F-tests to compare models (5a), (5b) and (5c). Also use F-tests to compare models (5a), (5b), (5d) and (5e).
  3. Based on the tests in question 7, which model would you select? Does this choice match your answer to question 4? How many parameters are needed to describe this model? What percentage of the variability in velocity is explained by this model?
  4. Make a residual plot for the model you selected, and list any assumptions that might not be met for the regression analysis. If you think all assumptions are met, then briefly explain why you think so.
  5. Using the model selected in question 8, re-analyze the data using the non-transformed disk loading values instead of using the square root of disk loading. Then compare the results of the two analyses: from the square root transformed and non-transformed loading data. Which analysis explains the highest proportion of velocity variability?

Reading: Chapters 4 and 5.