|
|
|
|
|
|
|
|
|
Состоятельный
| Глоссарий по эконометрике (англо-русский) |
Состоятельный , богатый, зажиточный
|
Consistent, английский
Peculiosus [a, um], латинский
Fortunatus [a, um], латинский
Copiosus [a, um], латинский
Offa, латинский
Beatus, латинский
Nummatus, латинский
Богатый, русский
Богатый, состоятельный, денежный; обильный, изобилующий чем; богач, богатей, капиталист, миллионер, толстосум, туз, крез, ротшильд. человек денежный, с достатком; денежная аристократия. "смотри, ты крезом стал". крыл. он теперь при деньгах. у не
|
Зажиточный, русский
- Зажиточный, безбедный, достаточный, состоятельный; человек с достатком, со средствами. дом -- полная чаша. "их дом блестящ и полн был, как чаша". некр. зажиточный не терпит недостатка, богатый имеет лишнее. ср. богатый.
- , -ая, -ое вермана, судзсяна, тырмана
|
Spline, английский
- A spline is a mathematical function defined over a compact region of a (continuous) variables range. it is generally continuous and is often represented by a low order polynomial function (or its integral). the knots of a spline are its points of inflection. its degree is a measure of the number of continuous derivatives. these functions underlie many data mining and nonparametric or semi-parametric regression functions. since they are only defined over a region of the full attribute range, they allow the function to adapt well to data in their region of support without strongly influencing the results in regions outside that region. techniques such as classification and regression trees (cart) and c4.5 that recursively partition the attribute space can be thought of as recursive spline functions with zero-order splines (constant values) fit in each region. the attributes in each sub-region so defined can then be searched for further places to partition that region adaptively for improved prediction. see also: c4.5, classification and regression trees, multivariate adaptive regression spline, nonparametric. split-sample validation a method for estimating the error in automated modeling techniques such as neural networks, recursive partitioning, and data mining. the data are split into two parts, a larger part for estimation and a small hold out sample used to estimate the true error. the technique is best used when there is a very large amount of data available as it reduces the size of the training data.
- A curved line, made up of segments and defined by control points.
Состоятельность, русский
|
|
|
|
|
|
|
