| 作成者 |
|
|
|
| 本文言語 |
|
| 出版者 |
|
|
|
| 発行日 |
|
| 収録物名 |
|
| 巻 |
|
| 開始ページ |
|
| 終了ページ |
|
| 出版タイプ |
|
| アクセス権 |
|
| Crossref DOI |
|
| 関連DOI |
|
|
|
| 関連URI |
|
|
|
| 関連情報 |
|
|
|
| 概要 |
We propose a new parametric regression model, Hybrid Linear Regression Model (or simply HLRM), which has partially additive and multiplicative covariate structure. In an ordinary linear regression mod...el or generalized linear model, it is assumed that the covariates have either an additive or multiplicative effect on the response. A family of HLRM includes an ordinary linear regression model, logarithmic linear model and generalized linear model with normal errors as special cases. In analysis of HLRM, estimating unknown parameters or searching for the best fitting optimal model, we assume the log-normal distribution. Some illustrative analyses applying HLRM to actual data sets are also demonstrated.続きを見る
|
Mendeley出力
