生物统计12.pptVIP

生物统计学 2009年度 计算生物所 置信区间 例题8.3 x=c(35.5, 34.1, 31.7, 40.3, 36.8, 40.2, 31.7, 39.2, 44.2) y=c(12, 16, 9, 2, 7, 3, 13, 9, -1) confint(lm(y~x)) 2.5 % 97.5 % (Intercept) 24.600910 72.4977284 x -1.741776 -0.4574679 例题 8.3 summary(lm(y~x)) Call: lm(formula = y ~ x) Residuals: Min 1Q Median 3Q Max -4.691 -1.345 -0.946 2.487 4.948 Coefficients: Estimate Std. Error t value Pr(|t|) (Intercept) 48.5493 10.1278 4.794 0.00198 ** x -1.0996 0.2716 -4.049 0.00488 ** --- Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Residual standard error: 3.266 on 7 degrees of freedom Multiple R-squared: 0.7008, Adjusted R-squared: 0.6581 F-statistic: 16.4 on 1 and 7 DF, p-value: 0.004876 置信区间与预测区间 plot(x,y) matlines(x[order(x)],predict(lm(y[order(x)]~x[order(x)]),int=c),col=black) matlines(x[order(x)],predict(lm(y[order(x)]~x[order(x)]),int=p),col=red) 置信区间小于预测区间 非线性模型 6月12日 多项式回归 library(ISwR) attach(cystfibr) summary(lm(pemax~height+I(height^2))) summary(lm(pemax~height+I(height^2))) Call: lm(formula = pemax ~ height + I(height^2)) Residuals: Min 1Q Median 3Q Max -51.411 -14.932 -2.288 12.787 44.933 Coefficients: Estimate Std. Error t value Pr(|t|) (Intercept) 615.36248 240.95580 2.554 0.0181 * height -8.08324 3.32052 -2.434 0.0235 * I(height^2) 0.03064 0.01126 2.721 0.0125 * --- Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1 Residual standard error: 24.18 on 22 degrees of freedom Multiple R-squared: 0.5205, Adjusted R-squared: 0.4769 F-statistic: 11.94 on 2 and 22 DF, p-value: 0.0003081 pemax.s=pemax[order(height)] height.s=height[order(height)] plot(height,pemax) matlines(height.s, predict(lm(pemax.s~height.s+I(height.s^2)),int=c)) matlines(height.s, predict(lm(pemax.s~height.s+I(height.s^2)),int=p)) 简单变量代换 指数关系： 例8.4 weight=c(0.029, 0.052, 0.079, 0.125, 0.181, 0.261, 0.425, 0.738, 1.130, 1.88