X site pop sex age head_l skull_w total_l tail_l
1 1 1 Vic m 8 94.1 60.4 89.0 36.0
2 2 1 Vic f 6 92.5 57.6 91.5 36.5
3 3 1 Vic f 6 94.0 60.0 95.5 39.0
4 4 1 Vic f 6 93.2 57.1 92.0 38.0
5 5 1 Vic f 2 91.5 56.3 85.5 36.0
6 6 1 Vic f 1 93.1 54.8 90.5 35.5
Create the linear regression and histogram. I failed to create separate histograms (not sure if this is an issue), and did not have a line of best fit. I also incorrectly analyzed the histograms. I guess I don’t really understand how to analyze marginal histograms, because to me the histograms seem to indicate constance, with some right skew in skull width. I thought this would imply a linear model would work.
b) Although the residual plot does show “some” quadratic behavior, a linear model still looks appropriate. I shouldn’t have used the term “quadratic”. Either way, I should have still created a polynomial model. However, I didn’t really understand creating polynomial models at this time. Homework 3 was helpful in this regard.
ggplot(midtermdata, aes(skull_w, log(head_l))) +geom_point() +stat_smooth(method='lm', formula = y ~poly(x,3))
I honestly ran out of time to do this part
lm1 <-lm(log(head_l) ~poly(skull_w,3, raw=TRUE), data = midtermdata)plot(predict(lm1), resid(lm1))abline(h=0, col='red')
summary(lm1)
Call:
lm(formula = log(head_l) ~ poly(skull_w, 3, raw = TRUE), data = midtermdata)
Residuals:
Min 1Q Median 3Q Max
-0.05700 -0.01468 -0.00197 0.01480 0.06848
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.121e+01 5.163e+00 2.171 0.0323 *
poly(skull_w, 3, raw = TRUE)1 -4.045e-01 2.641e-01 -1.531 0.1288
poly(skull_w, 3, raw = TRUE)2 7.808e-03 4.489e-03 1.739 0.0851 .
poly(skull_w, 3, raw = TRUE)3 -4.852e-05 2.535e-05 -1.914 0.0584 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.02344 on 100 degrees of freedom
Multiple R-squared: 0.6442, Adjusted R-squared: 0.6336
F-statistic: 60.36 on 3 and 100 DF, p-value: < 2.2e-16
It’s clear from the p-values that the third-order model and taking the log helps with the non-linearity d) The final model is predicted head length=46.19537+.81583(skull width). c) this is where I was supposed to insert the QQ plot*
#Using R to create a 97% confidence interval for a 55mm skull width: I did not understand how to find or analuze high leverage points and/or outliers
plot(hatvalues(lm1), rstandard(lm1),xlab ="Leverage", ylab ="Standardized Residuals")n <-nrow(midtermdata)abline(v=4/n, lty=2) # threshold for high leverageabline(h=c(-2,2), lty=2) # threshold for outliers
I forgot the rule for outliers. I can see now there are 7 outliers, 3 of which are leverage points. There also 3 high leverage points which will need to be investigated
Problem 2
a)
summary(lm1)
Call:
lm(formula = log(head_l) ~ poly(skull_w, 3, raw = TRUE), data = midtermdata)
Residuals:
Min 1Q Median 3Q Max
-0.05700 -0.01468 -0.00197 0.01480 0.06848
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 1.121e+01 5.163e+00 2.171 0.0323 *
poly(skull_w, 3, raw = TRUE)1 -4.045e-01 2.641e-01 -1.531 0.1288
poly(skull_w, 3, raw = TRUE)2 7.808e-03 4.489e-03 1.739 0.0851 .
poly(skull_w, 3, raw = TRUE)3 -4.852e-05 2.535e-05 -1.914 0.0584 .
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.02344 on 100 degrees of freedom
Multiple R-squared: 0.6442, Adjusted R-squared: 0.6336
F-statistic: 60.36 on 3 and 100 DF, p-value: < 2.2e-16
The adjusted R-squared value is 0.5004. This means that 50.04% of the head length can be explained by changes in the skull width.
The regression equation is head length=46.19537+.81583(skull width). That means that for every 1 mm increase in skull width, we expect to see a about a .81 increase in head length.
For a skull width of 55mm, the predicted value of head length would be 46.19537+.81583(55)=93.401867mm
The B_hat_0 value of my equation is 46.19537mm. This is not a meaningful value, as it would be very weird to encounter a possum with a head length of roughly 46 mm and a skull width of 0 mm. For some reason, this output is for the linear regression, even though the lm1 formula is clearly ##lm(log(head_l) ~ poly(skull_w,3, raw=TRUE), data = midtermdata). Therefore I will use the output of that summary to report and analyze R^2. The adjusted R-squared value is 0.6442 This means that about 64% of the head length can be explained by changes in skull width. The p-values are, respectively, \[\beta_0=0.1288, \beta_1=0.0851, and \beta_2=0.0584\], indicating that the higher order terms are marginally significant. Therefore, all three terms will be kept in the model. In my original answer, I did not analyze the value of \[\beta_0, \beta_1, and \beta_2,\] most likely because I was using a linear model.
b)The regression model is \[ln(\widehat(head_l))=-0.00004852(skull_w{^3})+0.007808(skull_w{^2})-.4045(skull_w))\]. Again, I was using a linear model.
c) The B_hat_0 value of my equation is 46.19537mm. This is not a meaningful value, as it would be very weird to encounter a possum with a head length of roughly 46 mm and a skull width of 0 mm. There is nothing wrong with this answer, although again, it uses the linear model. The updated answer would be \[e{^{11.121}}\], which still makes no sense in the context of the problem.
d) *Using the model, \[ln(\widehat{head_l}=-0.00004852(55{^3})+0.007808(55{^2})-.4045(55))\], \[ \widehat{head_l}= e^{(-0.00004852(55{^3})+0.007808(55{^2})-.4045(55))}\]=88.825mm. Using R to create a 97% confidence interval for a 55mm skull width:
e) *For this portion, I did not know how to insert a level into my predict function, and I also forgot to use the exp() function on my variable so I wouldn’t get the ln of skull_w.