Freight Investor Services Interview Questions and Answers

Preventive measures for regression assumptions not met

• Check for multicollinearity among independent variables

• Transform variables if they are not normally distributed

• Consider using non-parametric regression methods

• Use robust regression techniques to handle outliers

• Collect more data to improve model performance

Multicollinearity is a phenomenon in which two or more predictor variables in a regression model are highly correlated.

• Multicollinearity can lead to unstable estimates of the coefficients and make it difficult to determine the effect of each predictor variable on the outcome.

• One way to tackle multicollinearity is to identify the highly correlated variables and consider removing one of them from the model.

• Another approach is to use techniques like principal component analysis ...read more

Time series analysis components include trend, seasonality, cyclicality, and irregularity.

• Trend: Long-term movement or direction of the data.

• Seasonality: Regular patterns that occur at specific intervals.

• Cyclicality: Repeating patterns that are not necessarily at fixed intervals.

• Irregularity: Random fluctuations or noise in the data.

• Examples: Trend in stock prices, seasonality in retail sales, cyclicality in economic cycles.

Tuple is immutable and fixed in size, while list is mutable and can change in size.

• Tuple is created using parentheses, while list is created using square brackets.

• Tuple elements can be of different data types, while list elements are usually of the same data type.

• Tuple is faster than list for iteration and accessing elements.

• Example: tuple = (1, 'a', True), list = [1, 2, 3]

Handling missing values is crucial in data analysis. Various techniques like imputation, deletion, or prediction can be used.

• Use imputation techniques like mean, median, mode to fill in missing values.

• Consider using predictive modeling to estimate missing values based on other variables.

• Delete rows or columns with a high percentage of missing values if they cannot be accurately imputed.

• Use advanced techniques like K-nearest neighbors or decision trees for missing value imputa...read more

Outliers can be detected using statistical methods like Z-score, IQR, or visualization techniques like box plots.

• Calculate Z-score for each data point and identify points with Z-score greater than a certain threshold (usually 3 or -3).

• Use Interquartile Range (IQR) to identify outliers by determining data points that fall below Q1 - 1.5 * IQR or above Q3 + 1.5 * IQR.

• Visualize the data using box plots and identify points that fall outside the whiskers as potential outliers.