Abstract:
|
In 1998, the Oregon Department of Fish and Wildlife (ODFW) initiated a survey of coho salmon in Oregon coastal streams using a multi-panel survey, with panels having differing re-visit periods. Thus, some panels are re-visited every year, some after three years, and some after nine years. In this paper, I explore design-based, model-assisted ways of estimating change and trend using data available after four years of sampling. Thus, there is a panel that has been visited four times, a panel that has been visited twice (in years one and four), and four panels that have been visited only once (a different panel in each of years one through four).
One approach used here assumes that the response of interest is the site-specific least-squares estimate of slope based on 4 years of data, that is, y_i ~=~ (X?X)^{-1} X?Z_i, where X ~=~ (x_1, ~x_2), x_1 ~=~ (1, `1, `1,`1)?, x_2 ~=~ (1, `2, `3,`4), and Z_i~=~ (z_i1, `z_i2, `z_i3,`z_i4)?, where zij is the observed salmon density at site i at time j. The response is observable only for the panel visited in all four years, so I use the standard two-phase sample estimator (cf, Särndal, et al., 1992) to get a composite estimator using the panel observed at years one and four.
|