Bio 180 M 11-15 questions with 100%
complete solutions A+ rated
This graph shows that the assumption of homogeneity of variance has been
violated. - correct answer ✔✔False
This graph shows that the assumption of normality of error (variance) has been
violated. - correct answer ✔✔True
Which of the following graphs are testing the assumption of linearity? - correct
answer ✔✔Graph "a."
Graph "d."
The model choice principle of "Economy of Variables" means: - correct answer
✔✔Models should have the simplest parameters possible while still retaining
good statistics
Which of the following is NOT one of the three principles of model choice: -
correct answer ✔✔Orthogonality
What constitutes the "best" statistical model you can build? - correct answer
✔✔It depends on your goal in building the statistical model.
Which of the principles of model choice is the following XKCD cartoon referring
to? - correct answer ✔✔Multiplicity of p-values
, Which of the following strategies is not a legitimate approach to dealing with the
multiplicity of p-values in complex models? - correct answer ✔✔Eliminate data
points until just a few models have low p-values
Which one of the following models violates the principle of consideration of
marginality? - correct answer ✔✔Y~A+B+A:B+B:C+A:C+A:B:C
Which of the following is a risk of including higher polynomial powers of the
continuous explanatory variables in your models? - correct answer ✔✔You may
over fit your data which can lead to a perfect, but meaningless fit.
First, let's look at the adjusted R2 for the model with all three explanatory
variables included to second order, which you can do as follows:
summary(lm(blooms~(bed+shade+water)^2,data=m12s2data))
Enter the value for the adjusted R2 below. - correct answer ✔✔0.8981
Because of the lost data points, the data set is not orthogonal, so to determine
which variables and interactions should be included in the final model, we need to
consider all 6 orderings of the 3 explanatory variables, which means running the
following 6 commands. These tables show that the p-values for the individual
variables (bed, shade and water) are always < 0.05, so we just need to look at the
3 interaction terms: (bed:shade, bed:water, shade:water). [Note that the
interaction terms can be written in either order, so bed:shade is the same as
shade:bed] Therefore you should look at the 6 resulting anova tables and record
whether each interaction term is significant (p<0.05) or not. Then you will use this
information to answer this and the next 2 questions. - correct answer ✔✔In all
but one case, the results show that 2 of the interaction terms are not significant.
complete solutions A+ rated
This graph shows that the assumption of homogeneity of variance has been
violated. - correct answer ✔✔False
This graph shows that the assumption of normality of error (variance) has been
violated. - correct answer ✔✔True
Which of the following graphs are testing the assumption of linearity? - correct
answer ✔✔Graph "a."
Graph "d."
The model choice principle of "Economy of Variables" means: - correct answer
✔✔Models should have the simplest parameters possible while still retaining
good statistics
Which of the following is NOT one of the three principles of model choice: -
correct answer ✔✔Orthogonality
What constitutes the "best" statistical model you can build? - correct answer
✔✔It depends on your goal in building the statistical model.
Which of the principles of model choice is the following XKCD cartoon referring
to? - correct answer ✔✔Multiplicity of p-values
, Which of the following strategies is not a legitimate approach to dealing with the
multiplicity of p-values in complex models? - correct answer ✔✔Eliminate data
points until just a few models have low p-values
Which one of the following models violates the principle of consideration of
marginality? - correct answer ✔✔Y~A+B+A:B+B:C+A:C+A:B:C
Which of the following is a risk of including higher polynomial powers of the
continuous explanatory variables in your models? - correct answer ✔✔You may
over fit your data which can lead to a perfect, but meaningless fit.
First, let's look at the adjusted R2 for the model with all three explanatory
variables included to second order, which you can do as follows:
summary(lm(blooms~(bed+shade+water)^2,data=m12s2data))
Enter the value for the adjusted R2 below. - correct answer ✔✔0.8981
Because of the lost data points, the data set is not orthogonal, so to determine
which variables and interactions should be included in the final model, we need to
consider all 6 orderings of the 3 explanatory variables, which means running the
following 6 commands. These tables show that the p-values for the individual
variables (bed, shade and water) are always < 0.05, so we just need to look at the
3 interaction terms: (bed:shade, bed:water, shade:water). [Note that the
interaction terms can be written in either order, so bed:shade is the same as
shade:bed] Therefore you should look at the 6 resulting anova tables and record
whether each interaction term is significant (p<0.05) or not. Then you will use this
information to answer this and the next 2 questions. - correct answer ✔✔In all
but one case, the results show that 2 of the interaction terms are not significant.
