ESM 206 Problem set 2
Microexam will be due Tuesday, Jan. 22 2008
Instructions for software use are in the file
Computation for correlation and simple
regression.doc
The four datasets introduced in lecture are posted on the course webpage:
Chlorophyll.xls, NorwegianLakes.xls, ExoticSpecies.xls, and Gasmarket2.xls.
Associated text files describe the various columns.
The first three questions apply to the first three datasets (although you probably won’t
need to do all three to understand the process):
1)
Within each dataset there are multiple quantitative variables.
Calculate the
sample covariance and sample correlation between each pair of variables (the
correlations – but not covariances – can be calculated in R Commander as
described in lecture.
Both correlations and covariances are available in the Data
Analysis ToolPak of Excel).
2)
Create a scatterplot for each pair of variables.
Make sure that you understand the
relationship between the scatterplot, the covariance, and the correlation.
Based on
visual inspection of the data, identify cases where the linear correlation may not
be a good description of the association between the variables.
3)
Based on your general knowledge about the social and natural processes at work,
discuss the nature of causality (if any) that might be operating between each pair
of variables.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 KENDALL,BERKLEY
 Environmental Science, Statistics, Regression Analysis, Correlation and dependence, Pearson productmoment correlation coefficient, exotic species, Covariance and correlation

Click to edit the document details