The slope of a line is a measure of its steepness. Mathematically, slope is calculated as “rise over run” (change in y divided by change in x).

Typically, dummy variables are used in the following applications: time series analysis with seasonality or regime switching; analysis of qualitative data, such as survey responses; categorical representation, and representation of value levels.

Slope Dummies. ➢ A dummy variable that changes the slope of the relationship between x. and y. 4. Dummy Dependent Variables.

A dummy variable (aka, an indicator variable) is a numeric variable that represents categorical data, such as gender, race, political affiliation, etc. Technically, dummy variables are dichotomous, quantitative variables. Their range of values is small; they can take on only two quantitative values.

For example, many people don’t like to standardize dummy variables, which only have values of 0 and 1, because a “one standard deviation increase” isn’t something that could actually happen with such a variable. Ergo, you might want to leave the dummy variables unstandardized while standardizing continuous X variables.

If you are using R and scaling the dummy variables or variables having 0 or 1 to a scale between 0 and 1 only, then there won’t be any change on the values of these variables, rest of the columns will be scaled. The point of mean centering in regression is to make the intercept more interpretable.

Linear Discriminant Analysis (LDA) finds it’s coefficients using the variation between the classes (check this), so the scaling doesn’t matter either.

For the second question, this really depends on the dataset and other features. If the 80% of the features are bounded (0-1) MinMax scaling should definitely work. And, if the features are not bounded so then scaling won’t have a bigger impact.