In a simple regression to estimate a linear trend, the dependent variable is the value of the time series and the independent variable is

Question 2 options:

	The natural log of time.
	A binary (dummy) variable equal to 1 for observations in January, and 0 for other months.
	The time series lagged by 1 period.
	Time or some time index.

Question 3 (1 point)

True or False: When using regression to estimate a trend model one should rely solely on the statistical significance of the estimated coefficient on the trend variable in deciding whether a trend exists.

Question 3 options:

	True
	False

Question 4 (1 point)

When applying a non-linear trend, it is important not to choose an overly complex shape because

Question 4 options:

	It will likely only fit the training period well and be overfitting the data
	The loss of degrees of freedom reduces the statistical significance of the model
	Multicollinearity will be a problem with such a model
	Seasonality will dominate the resulting forecasts