The IQR (Interquartile Range) method is less sensitive to extreme values as compared to the z-score method or the standard deviation method. This is because IQR is a measure of statistical dispersion, being equal to the difference between upper and lower quartiles.

Z-score standardization scales data by subtracting the mean and dividing by the standard deviation. If the standard deviation is very small, the result of this division could be very large, leading to scaled values that are quite large.

The first step in the EDA process is questioning, i.e., defining the questions that the analysis aims to answer based on the problem's context and data available.

VIF provides a measure of multicollinearity by quantifying how much the variance of an estimated regression coefficient increases if predictors are correlated. If the predictors are uncorrelated, the VIF of each variable will be 1. The higher the value of VIF, the more severe the multicollinearity.

To calculate a Z-score for a particular data point, you need to know the mean and standard deviation of the dataset. The Z-score is calculated by subtracting the mean from the data point and then dividing by the standard deviation.

Choosing between a scatter plot, pairplot, correlation matrix, and heatmap depends on several factors including: the number of variables you want to visualize, the type of data you're working with, and the level of familiarity your audience has with these types of plots.

Linear models are more susceptible to the issue of feature redundancy as they assume independence among features. Redundant features violate this assumption and can cause problems.

The temperature outside and the amount of sunlight in a day are likely to be highly correlated, as more sunlight generally corresponds to higher temperatures. This is an example of multicollinearity.

In a normal distribution, the "Mean", "Median", and "Mode" are all the "Same", falling at the center of the distribution.

Principal Component Analysis (PCA) is a dimensionality reduction technique that can be used when dealing with high-dimensional datasets with many redundant features. PCA transforms the original features into a new set of uncorrelated features, capturing the most variance in the data, thus helping to maintain the essential information while reducing the dimensionality.

The process of converting an actual range of values in a numeric feature column into a standard range of values is known as Data Scaling. This is a fundamental step in data preprocessing, particularly important when dealing with machine learning algorithms.

The Min-Max scaling technique, which scales the data to a fixed range (usually 0 to 1), is highly sensitive to the presence of outliers. It shrinks the range of the feature values, so the outliers can drastically change the ranges of the attributes.