一只药用昆虫的产卵数\(y\)与一定范围内的温度\(x\)有关,现收集了该种药用昆虫的\(6\)组观测数据如表:
温度\(x/^{\circ}C\) | \(21\) | \(23\) | \(24\) | \(27\) | \(29\) | \(32\) |
产卵数\(y/\)个 | \(6\) | \(11\) | \(20\) | \(27\) | \(57\) | \(77\) |
经计算得:\( \overline {x}= \dfrac {1}{6} \sum\limits_{i=1}^{6}x_{i}=26\),\( \overline {y}= \dfrac {1}{6} \sum\limits_{i=1}^{6}y_{i}=33\),\( \sum\limits_{i=1}^{6}(x_{i}- \overline {x})(y_{i}- \overline {y})=557\),\( \sum\limits_{i=1}^{6}(x_{i}- \overline {x})^{2}=84\),\( \sum\limits_{i=1}^{6}(y_{i}- \overline {y})^{2}=3930\),线性回归模型的残差平方和\( \sum\limits_{i=1}^{6}(y_{i}- \overset{\hat{} }{y}_{i})^{2}=236.64\),\(e^{8.0605}≈3167\),其中\(x_{i}\),\(y_{i}\)分别为观测数据中的温度和产卵数,\(i=1\),\(2\),\(3\),\(4\),\(5\),\(6\).
\((\)Ⅰ\()\)若用线性回归模型,求\(y\)关于\(x\)的回归方程\( \overset{\hat{} }{y}= \overset{\hat{} }{b}x+ \overset{\hat{} }{a}(\)精确到\(0.1)\);
\((\)Ⅱ\()\)若用非线性回归模型求得\(y\)关于\(x\)的回归方程为\( \overset{\hat{} }{y}=0.06e^{0.2303x}\),且相关指数\(R^{2}=0.9522\).
\((\) \(i\) \()\)试与\((\)Ⅰ\()\)中的回归模型相比,用\(R^{2}\)说明哪种模型的拟合效果更好.
\((ii)\)用拟合效果好的模型预测温度为\(35^{\circ}C\)时该种药用昆虫的产卵数\((\)结果取整数\()\).
附:一组数据\((x_{1},y_{1})\),\((x_{2},y_{2})\),\(…\),\((x_{n},y_{n})\),其回归直线\( \overset{\hat{} }{y}= \overset{\hat{} }{b}x+ \overset{\hat{} }{a}\)的斜率和截距的最小二乘估计为\( \overset{\hat{} }{b}= \dfrac { \sum\limits_{i=1}^{n}(x_{i}- \overline {x})(y_{i}- \overline {y})}{ \sum\limits_{i=1}^{n}(x_{i}- \overline {x})^{2}}\),\( \overset{\hat{} }{a}= \overline {y}- \overset{\hat{} }{b} \overline {x}\);相关指数\(R^{2}=1- \dfrac { \sum\limits_{i=1}^{n}(y_{i}- \overset{\hat{} }{y}_{i})^{2}}{ \sum\limits_{i=1}^{n}(y_{i}- \overline {y})^{2}}\).