Line transect lab next Monday How will we
Line transect lab next Monday • How will we distribute students among transects? • Expect cold weather and rain. Dress appropriately. • How will you record your data? In the rain?
Bias, Randomness, and Quadrats • Bias is unrelated to accuracy, • Accuracy known as measurement error, not a huge problem, part of overall variance • Bias is a large problem, can’t be fixed later
The 2 snipers Excellent aim, crooked sights Cross-eyed cat, Straight sights
Poor Accuracy vs. Bias • Bad accuracy will still give the correct mean with lots of samples • But will have a large variance • Harder to detect significance • Bias will never give the correct mean
Feline high-rise syndrome Whitney and Mehlhaff (1987) J. Amer. Vet. Med. Assoc. Could this be a biased sample?
Random Samples • Each observation is equally probable • Each observation is equally observable Non Random samples are likely biased
Choose samples randomly True mean = 4 Get an unbiased sample, can’t be fixed with clever stats!
Quadrats
Quadrat shape 1. Edge effects ? ? worst best
Quadrat shape 2. Variance 4 5 4 best 1
Quadrat size 1. Edge effects ? ? ? ? ? ? 3/5 on edge worst 3/8 on edge best
Quadrat size 2. Variance High variance Low variance
Quadrat size So should we always use as large a quadrat as possible? Tradeoff with cost (bigger quadrats take l o n g e r to sample)
Quadrat lab Use a cost (“time is money”): benefit (low variance) approach to determine the optimal quadrat design for 10 tree species. Cost: total time = time to locate quadrat + time to census quadrat Benefit: Variance Size & shape affect!
Quadrats In this example, 1. 5 x 1. 5 is best size Krebs, C. J. 1999. Ecological Methodology 2 ed. Addisson Wesley
Exam Q 2. 1 The average of pinon pine trees in California was investigated by placing a 10 hectare plot randomly on a distribution map using a computer. Researchers then measured the age of every pinon pine tree within the plot. The average within the plot was used to estimate the average of the California population a) What is the population of interest in this study? b) Were the trees sampled randomly from this population? Why or why not?
- Slides: 16