An example of how to format analyses and plots for a scientific paper, using data on the relationship between the amount of pigment on lion snouts and their age from Whitman et al (2004). These data are featured in Chapter 17 of Whitlock & Shulter’s Analysis of Biological Data, 2nd ed.
The original data was presented in Figure 4, pg 2, of Whitman
References: Whitman, K, AM Starfield, HS Quadling and C Packer. 2004. Sustainable trophy hunting of African lions. Nature.
#The following sets up the data fro the analysis
#Set working directory
setwd("C:/Users/lisanjie2/Desktop/TEACHING/1_STATS_CalU/1_STAT_CalU_2016_by_NLB/Lecture/Unit3_regression/last_week")
Load data
dat <- read.csv("lion_age_by_pop.csv")
For information on the format of “Structured abstracts”, see https://www.nlm.nih.gov/bsd/policy/structured_abstracts.html
INTRODUCTION: Being able to accurately understand the age structure of population
OBJECTIVES: The primary of objective of this study was to determine if the age of lions can be predicted from the amount of pigementation on their noses, and whether this relationship varies between populations.
METHODS:(3-4 sentences on methods; likely to be longest or 2nd longest part of abstract)
RESULTS:(2-5 sentences on results; likely to be longest or 2nd longest part of abstract)
CONCLUSION(2-3 sentences stating the biological/ecological/scientific conclusions that can be drawn from the study).
I tested whether there was a significant relationship between nose pigmentation and lion age using linear regression. To determine if this relationship varied between lion populations I tested for an effect of population and a pigmentation*population interaction. Data were logged transformed to meet the assumptions of linear regression. All analyses were carried out in R 3.3.1 (R Core Team 2016).
Data on nose pigmentation and age was collected for 32 lions; 22 lions were from the Serengeti population and 10 from Ngorogoro. (Raw data are available in Table A1 in Appendix 1). The mean age of lions in The Serengeti sample population was 3 years (SE = 0.3; Figure 1) and the mean in the Ngorogoro sample was 7.13 (SE = 0.85). The distribution of ages for each population is shown in Figure A1.
There was a significant positive relationship between nose pigmentation and lion age (F = 44.364, p < 0.0001). The Serengeti and Ngorogoro populations had different intercepts (F = 23.17, p < 0.0001) but there was no evidence of a significant population by pigmentation interaction (F = 0.72, p = 0.40). The best fitting model therefore had separate intercepts for each population but a single slope (Figure 2; slope = 1.74, SE = 0.29).
R Core Team (2016). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/.
Figure 1: Mean ages in the two samples of lions. Error bars are approximate 95% confidence intervals.
Figure 2: Relationship between nose pigmentation and age of male African lions (Leo panthera) in the Serengeti (n=22) and Ngorogoro populations (n = 10), Tanzania.
Table A1: Raw data from 32 African lions (Panthera leo) from Tanzania. Originally published … [add reference]
[Add table]
Table A2: Distribution of ages in the samples used for regression analysis.
Table A1-1: Diagnostic plots for un-tranformed data
Table A1-2: Diagnostic plots for log-tranformed data
In your references include:
R Core Team (2016). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. https://www.R-project.org/.
This should be your 5th (or greater) reference. * You should have 4 other references from peer-reviewed scientific papers.
That is, you DO NOT need to say “I used the t.test function”, or “I used the plot2means function.”