Why is the assumption of independently and identically distributed (IID) residuals important in linear regression?
- It ensures that the model is not overfitting
- It ensures that the model is not underfitting
- It ensures that the parameter estimates are unbiased
- It ensures the correctness of standard errors and hypothesis tests
The assumption of IID residuals is important because it ensures that standard errors, confidence intervals, and hypothesis tests are valid. If this assumption is violated, these statistics may be incorrect, leading to misleading results.
What is the purpose of the 'whiskers' in a box plot?
- To represent the outliers
- To represent the range of the data
- To show the interquartile range
- To show the mean and median
The 'whiskers' in a box plot represent the range of the data. The upper whisker extends to the maximum data value or up to 1.5 times the interquartile range (IQR), while the lower whisker extends to the minimum data value or up to 1.5 times the IQR. Any data points beyond the whiskers can be considered outliers.
How does the Breusch-Pagan test check for heteroscedasticity in residuals?
- By comparing the variance of residuals
- By examining the correlation of residuals
- By plotting residuals against fitted values
- By regressing the squared residuals on the predictors
The Breusch-Pagan test checks for heteroscedasticity by regressing the squared residuals on the predictors. If the predictors explain a significant amount of variance in the squared residuals, the test concludes that heteroscedasticity is present.
___________ occurs when changes in one variable are associated with changes in another variable, but one does not necessarily cause the other.
- Causation
- Correlation
- Covariation
- Regression
Correlation occurs when changes in one variable are associated with changes in another variable. It's important to remember that correlation does not imply causation. Just because two variables move together, it does not mean that one variable's movement is causing the other's.
How does the variability of the population affect the width of a confidence interval?
- Higher variability decreases the width of the confidence interval
- Higher variability increases the width of the confidence interval
- The relationship between variability and the width of the confidence interval is unpredictable
- Variability has no effect on the width of the confidence interval
Higher variability in the population increases the width of the confidence interval. When data points are spread out more (higher variability), there is more uncertainty about where the true population parameter lies, leading to a larger standard error and thus a wider confidence interval.
What is the Central Limit Theorem and how does it relate to the normal distribution?
- It states that all distributions are ultimately normal distributions
- It states that the mean of a large sample is always equal to the population mean
- It states that the sum of a large number of independent and identically distributed random variables tends to be normally distributed
- It states that the sum of a small number of random variables has an exponential distribution
The Central Limit Theorem states that, given certain conditions, the arithmetic mean of a sufficiently large number of iterates of independent random variables, each with a well-defined (finite) expected value and finite variance, will be approximately normally distributed, regardless of the shape of the original distribution.
How does polynomial regression differ from linear regression?
- Linear regression models relationships as curves
- Linear regression models relationships as straight lines
- Polynomial regression models relationships as curves
- Polynomial regression models relationships as straight lines
Polynomial regression models relationships as curves, not straight lines. This allows polynomial regression to capture non-linear relationships, where the relationship changes direction at different levels of the independent variables. On the other hand, linear regression models relationships as straight lines, assuming a constant rate of change.
Pearson's Correlation Coefficient assumes that the variables are ________ distributed.
- negatively
- normally
- positively
- randomly
Pearson's Correlation Coefficient assumes that the variables are normally distributed. It's one of the key assumptions made when calculating the coefficient, and it refers to the shape of the distribution of the values.
What is the role of eigenvalues in factor analysis?
- They are used to categorize the data
- They are used to transform the data
- They help in normalizing the data
- They represent the variance explained by each factor
In factor analysis, eigenvalues represent the total variance explained by each factor. A larger eigenvalue indicates that more of the total variance is accounted for by that factor.
What assumptions must be met for Pearson's Correlation Coefficient to be valid?
- Both variables are independent
- Both variables are measured on a nominal scale
- Both variables are normally distributed, and there is a linear relationship between them
- Both variables have no outliers
For Pearson's Correlation Coefficient to be valid and reliable, the following assumptions should be met: both variables should be continuous, they should be linearly related, and both variables should be approximately normally distributed. Independence of observations is also required.