a-) its seem to be moderate linear positive but no very strong.
b-) y-axis is the response variable and the x-axis is the explanatory variable
c-) to see the correlection between the variable
d-) we can see a square line but we see an issue with the variability.
#a-)
beta <- (9.41/10.37) * 0.67
beta## [1] 0.6079749b <- 171.14 - beta * 107.2
paste("y =" ,beta ,"+", b ,"x") ## [1] "y = 0.607974927675989 + 105.965087753134 x"b-) the slope predict the positive increase and the intercept shows the height.
c-) 0.67 ^ 2 = 0.4489 -The variation height
d-) 105.96 + 0.60797 ∗ 100 = 166.76
e-)160 - 166.76 = -6.76 we have a negative residue which we can see that overestimated the height model.
a-) y = - 0.357 + 4.034X
b-) is - 0.357, the heart weight
c-)the slope is 4.034 its predict the increase by 4.034 of the heart weight
d-)its explain the variability which is 64.66%
e-) the correlection coeficient is the root square of 64.66% which is 0.8041144
a-) (3.9983 - 4.010) / - 0.0883 = - 0.1325
b-) Yes, we can see this observing the p value which is nearly 0 and the graph.
c-)
Linearity: we can observe some pattern in the scatter plot. Nearly normal residuals: residuals seem nearly normal. Constant variability: in the graph, we can see constant variability residuals plot. Independence: these variables can be assumed to be independent.