In R, when we use the ggplot2 layer geom_point(), it automatically

• puts the dependent variable along the horizontal axis.
• puts the independent variable along the vertical axis.
• displays the relationship between two variables.
• displays probabilities for each variable.

A typical use of the linear model function lm() is to have a dependent variable

• that is along the horizontal axis.
• that is being predicted or estimated.
• that provides the basis for estimation.
• that is the explanatory variable.
• None of these are correct.

Binary variables such as placebo or not placebo can be included as a dependent variable in a linear model by calling:

• lm( formula = y ~ placebo + x, data = somedataset )
• geom_smooth( placebo )
• lm( formula = placebo ~ y + x, data = somedataset )
• geom_smooth( aes( y = y, x = placebo ) )

The coefficients from the linear model function lm() could

• represent the average change in y for each change of one unit in the independent variable, x.
• represent the average change in x for each change of one unit in the dependent variable, y.
• represent the average variance in x for each unit change in any variable, y.
• None of these answers are correct.

A binary or dummy variable

• is not a qualitative variable.
• can only assume one of two values.
• is always used as the dependent variable.
• All of these answers are correct.

The function to fit a linear model is lm(), and that function

• will generate much data that should be assigned to a R object.
• will display a blue line in a cloud of data.
• only works for two explanatory variables.
• All of these answers are correct.

The difference between the value a model predicts and what is actually observed is called

• a residual
• the error
• sometimes denoted as e
• All of these answers are correct.

A regression is

• a quantity used to summarize the data.
• a model that can be used for prediction.
• a way to return the data to its raw less developed state.
• All of these answers are correct.

You are inspecting the output of the geom_point() layer. What you get is

• a scatter plot displaying the relationship between two variable.
• is a cloud of point that are randomly positioned.
• not a good tool for visual inspection of data.
• All of these answers are correct.

The default blue line drawn with geom_smooth( model = 'lm' ) is

• the line of best fit.
• used to make predictions.
• a graphical representation of the linear model, lm.
• All of the above answers are correct.
• None of these answers are correct.