Regression Analysis Concepts Quiz

A statistical test used to check if the variance of the error terms in a regression model is constant across different levels of the independent variables. It tests whether the spread of the data points around the regression line is the same across all values of the independent variable.

A statistical test used to detect heteroscedasticity in a regression model. It involves splitting the sample data into two groups and comparing the variances of the residuals calculated from each group.

A statistical test used to detect heteroscedasticity in a regression model. This test is more adaptable to different forms of heteroscedasticity and doesn't rely on specific assumptions about the pattern of heteroscedasticity.

The difference between the actual observed values of the dependent variable and the values predicted by the regression model.

The variance of the residuals in a regression model is not constant but changes across different values of the independent variables. This means the spread of data points around the regression line varies for different values of the independent variables.

A regression model where the error terms have constant variance across all values of the independent variables.

The variance of the error term in a regression model. It indicates the spread of the data points around the regression line.

It is a statistical test to check for rth order autocorrelation, testing if residuals are correlated with themselves at different lags.

A situation where explanatory variables in a regression model are highly correlated with each other, leading to problems in estimating individual coefficients.

A situation where explanatory variables are perfectly linearly related. It makes it impossible to estimate all model coefficients.

When explanatory variables are highly correlated but not perfectly, causing issues in estimating individual coefficients, leading to high standard errors.

The presence of autocorrelation, where residuals are correlated with each other at different lags, can lead to various issues in regression analysis.

A statistical approach that estimates model coefficients while taking into account autocorrelated residuals.

A method used to correct for autocorrelation in time series data, based on the assumption of a specific autocorrelation model, such as an AR(1).

In regression, if autocorrelation is ignored, even though OLS estimates remain unbiased, they are inefficient, causing problems in inferences and potentially inflated R2 values.

It refers to a situation when residuals in a time series model are correlated with their past values, and this correlation is not random.

A dummy variable is a binary variable that takes a value of 1 if a certain condition is met, and 0 otherwise. They are used to account for qualitative factors in regression analysis, which cannot be measured directly. For example, a dummy variable could be created to represent a gender (1 for female, 0 for male).

This type of bias occurs when an important explanatory variable is omitted from the regression model. This can lead to incorrect or misleading results, as the estimates for the included variables will be influenced by the missing variable.

If an irrelevant variable is included in the regression model, it will not impact the consistency and unbiasedness of the estimates for other variables. However, the efficiency of the model will be reduced, leading to less precise results.

The Chow test is a statistical test used to determine if the parameters of a regression model are stable over different time periods. It helps analyze whether the relationship between variables remains consistent for the entire dataset or if it shifts across different intervals.

It aims to check if the predictions from a model trained on one part of the data are accurate for the other part. It helps assess the model's ability to generalize to new data and identify possible parameter instability.

A statistical test that checks if the distribution of residuals in a regression model is normal.

A measure of the asymmetry of a distribution. A positive skewness indicates a long right tail, while a negative skewness indicates a long left tail.

A measure of the peakedness of a distribution. A high kurtosis indicates a sharp peak with heavy tails, while a low kurtosis indicates a flatter peak with lighter tails.

The third standardized moment of a distribution, measuring its skewness.

The fourth standardized moment of a distribution, measuring its kurtosis, but adjusted so that the normal distribution has a kurtosis of 3.

A statistical test used to determine whether the distribution of residuals from a regression model is significantly different from a normal distribution.

A test statistic used in the Bera Jarque test for normality. It is calculated using the coefficients of skewness and kurtosis from the residuals.

The use of dummy variables to account for outliers in a regression model.

A statistical method that does not assume normality in the data.

A simple way to detect multicollinearity by looking at the correlation coefficients between independent variables. High correlations (above 0.8) suggest possible multicollinearity.

A measure of how much the variance of a regression coefficient is inflated due to multicollinearity. A VIF greater than 10 suggests strong multicollinearity.

Removing one of the highly correlated variables from the regression model.

Combining two or more highly correlated variables into a single ratio, reducing the collinearity.

A statistical test that checks whether the chosen functional form (e.g., linear) is correct. It adds higher-order terms of the fitted values to an auxiliary regression.

It's possible that the true relationship between variables is not linear. This test helps you discover if the assumed linear model is appropriate.

The residuals of a regression model are the differences between the actual observed values of the dependent variable and the values predicted by the model. These residuals are used in various statistical tests to assess the model's performance.

A general test for mis-specification, it adds higher order terms of fitted values to a regression.

Collecting more data points can sometimes help reduce the problem of multicollinearity, especially if you have a longer time frame or collect data at a higher frequency.