Curve Fitting of Averaged Data (Q3324860)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3856229
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Curve Fitting of Averaged Data |
scientific article; zbMATH DE number 3856229 |
Statements
1984
0 references
curve fitting of averaged data
0 references
least squares
0 references
parameter estimations
0 references
equivalence of methods
0 references
methods of aggregation
0 references
Curve Fitting of Averaged Data (English)
0 references
0.6927103400230408
0 references
0.6859710216522217
0 references
0.6801865100860596
0 references
In manipulating data for estimating parameters for models of physical phenomena several methods of aggregation can be employed. This article shows the conditions under which three typical methods of aggregation of data for such purposes are equivalent. More importantly it shows when these methods are not equivalent. The methods investigated are: 1. Aggregating all the observations made by several individuals, and estimating the parameters. 2. Using the average of each individual's successive observation as data to make the parameter estimate. 3. Averaging the parameter estimates generated by each individual's data set. The authors point out that method one and method two are equivalent if the numbers of data points in each observation set are equal or if the fitted curve passes through the average observation of each individual data set. Method three is equivalent to the other two if the curve determined is a linear function of the parameter and the number of observations in each data set aggregated are equal.
0 references