ISYE 6501 Midterm Exam Study Guide Questions And
Answers Verified 100% Correct
What measure is used to determine the quality of a linear regression line to data? -
ANSWER Square of the difference between the line and the data points. (Sum squared
error.)
What is the formula for point error in linear regression? - ANSWER y(i)-Yhat(i)=y(i)-
(a(0) + a(i)*x(i)
Taking partial derivates and setting them equal to zero and then solving that system
equation helps us do what? - ANSWER Minimize the error and optimize the coefficients
for linear regression.
What does AIC stand for? - ANSWER Akaike Information Criterion
What is "Likelihood"? - ANSWER A measure for the probability density for any
parameter set.
What is Maximum likelihood? - ANSWER Parameters that give the highest probability.
What is MLE? - ANSWER Maximum Likelihood Estimate... The set of parameters that
minimizes the sum of square errors.
What is the formula for AIC? - ANSWER AIC=2k - 2*ln(L*) where L* is the maximum
likelihood value and K is the number of parameters estimated.
What is the penality term in AIC and what does it do? - ANSWER 2K - It helps prevent
overfitting.
A models that is fit to random effects and not real ones is said to be? - ANSWER
Overfit
What does corrected AIC account for? - ANSWER The fact that we cannot have
infinitely many data points.
If AIC for model 1 is 75 and AIC for model 2 is 80 how do you compute which is better. -
ANSWER It is the relative likelyhood: e^((AIC1-AIC2)/2) = 8.2%
,What does BIC stand for? - ANSWER Bayesian Information Criterion
If you have a lot more data than parameters should you use AIC or BIC? - ANSWER
BIC
If you have "fewer" parameters - ANSWER should you use AIC or BIC?, BIC
The "Rule of Thumb" deals with? - ANSWER When comparing two models on the
same data set by their BIC scores.
In exponential smoothing what does alpha do? - ANSWER Adjust the trade off between
current (x_t) and previous values.
In exponential how should you adjust for randomness? - ANSWER Make alpha close to
0.
In exponential trending, what does Beta do? - ANSWER Adjusts for trending.
In exponential smoothing, what is C_t? - ANSWER A multiplicative seasonality factor at
time t.
In exponential smoothing, what is L? - ANSWER The length of a cycle.
In exponential smoothing, what does gamma do? - ANSWER Adjusts how much cycles
contribute to the model.
In multiplicative seasonality, the first L values of C are set to what? - ANSWER 1.
1-norm - ANSWER Similar to rectilinear distance; measures the sum of the lengths of
each dimension
2-norm - ANSWER Similar to Euclidian distance; measures the straight-line length of a
vector from the origin.
Additive seasonality - ANSWER Seasonal effect that is added to a baseline value.
Adjusted R-squared/Adjusted R2 - ANSWER Variant of R2 that encourages simpler
models by penalizing the use oftoo many variables.
AIC - ANSWER Akaike information criterion
, Akaike information criterion - ANSWER Model selection technique that trades off
between model fit and model complexity. Model with lower AIC is preferred. Generally
penalizes complexity less than BIC.
Algorithm - ANSWER Step-by-step procedure designed to carry out a task.
Analysis of Variance/ANOVA - ANSWER Statistical method for dividing the variation in
observations among different sources.
Area under curve/AUC - ANSWER Area under the ROC curve; an estimate of the
classification model's accuracy. Also called concordance index.
ARIMA - ANSWER Autoregressive integrated moving average.
Attribute - ANSWER A characteristic or measurement - for example, a person's height
or the color of a car. Aka "feature", "covariate" or "predictor"
Autoregression - ANSWER Regression technique using past values of time series data
as predictors of future values.
Autoregressive integrated moving average (ARIMA) - ANSWER Time series model that
uses differences between observations when data is nonstationary. Also called Box-
Jenkins.
Bayes' theorem/Bayes' rule - ANSWER Fundamental rule of conditional probability:
𝑃(𝐴|𝐵) = 𝑃(𝐵|𝐴)𝑃(𝐴) / 𝑃(𝐵) .
Bayesian Information criterion - ANSWER (BIC) Model selection technique that trades
off model fit and model complexity. Generally penalizes complexity more than AIC.
Lower is better.
Bayesian regression - ANSWER Regression model that incorporates estimates of how
coefficients and error are distributed.
BIC - ANSWER Bayesian information criterion
Binary data - ANSWER Data that can take only two different values (true/false, 0/1,
black/white, on/off, etc.).
Binary variable - ANSWER Variable that can take just two values: 0 and 1.
Box and whisker plot - ANSWER Graphical representation data showing the middle
Answers Verified 100% Correct
What measure is used to determine the quality of a linear regression line to data? -
ANSWER Square of the difference between the line and the data points. (Sum squared
error.)
What is the formula for point error in linear regression? - ANSWER y(i)-Yhat(i)=y(i)-
(a(0) + a(i)*x(i)
Taking partial derivates and setting them equal to zero and then solving that system
equation helps us do what? - ANSWER Minimize the error and optimize the coefficients
for linear regression.
What does AIC stand for? - ANSWER Akaike Information Criterion
What is "Likelihood"? - ANSWER A measure for the probability density for any
parameter set.
What is Maximum likelihood? - ANSWER Parameters that give the highest probability.
What is MLE? - ANSWER Maximum Likelihood Estimate... The set of parameters that
minimizes the sum of square errors.
What is the formula for AIC? - ANSWER AIC=2k - 2*ln(L*) where L* is the maximum
likelihood value and K is the number of parameters estimated.
What is the penality term in AIC and what does it do? - ANSWER 2K - It helps prevent
overfitting.
A models that is fit to random effects and not real ones is said to be? - ANSWER
Overfit
What does corrected AIC account for? - ANSWER The fact that we cannot have
infinitely many data points.
If AIC for model 1 is 75 and AIC for model 2 is 80 how do you compute which is better. -
ANSWER It is the relative likelyhood: e^((AIC1-AIC2)/2) = 8.2%
,What does BIC stand for? - ANSWER Bayesian Information Criterion
If you have a lot more data than parameters should you use AIC or BIC? - ANSWER
BIC
If you have "fewer" parameters - ANSWER should you use AIC or BIC?, BIC
The "Rule of Thumb" deals with? - ANSWER When comparing two models on the
same data set by their BIC scores.
In exponential smoothing what does alpha do? - ANSWER Adjust the trade off between
current (x_t) and previous values.
In exponential how should you adjust for randomness? - ANSWER Make alpha close to
0.
In exponential trending, what does Beta do? - ANSWER Adjusts for trending.
In exponential smoothing, what is C_t? - ANSWER A multiplicative seasonality factor at
time t.
In exponential smoothing, what is L? - ANSWER The length of a cycle.
In exponential smoothing, what does gamma do? - ANSWER Adjusts how much cycles
contribute to the model.
In multiplicative seasonality, the first L values of C are set to what? - ANSWER 1.
1-norm - ANSWER Similar to rectilinear distance; measures the sum of the lengths of
each dimension
2-norm - ANSWER Similar to Euclidian distance; measures the straight-line length of a
vector from the origin.
Additive seasonality - ANSWER Seasonal effect that is added to a baseline value.
Adjusted R-squared/Adjusted R2 - ANSWER Variant of R2 that encourages simpler
models by penalizing the use oftoo many variables.
AIC - ANSWER Akaike information criterion
, Akaike information criterion - ANSWER Model selection technique that trades off
between model fit and model complexity. Model with lower AIC is preferred. Generally
penalizes complexity less than BIC.
Algorithm - ANSWER Step-by-step procedure designed to carry out a task.
Analysis of Variance/ANOVA - ANSWER Statistical method for dividing the variation in
observations among different sources.
Area under curve/AUC - ANSWER Area under the ROC curve; an estimate of the
classification model's accuracy. Also called concordance index.
ARIMA - ANSWER Autoregressive integrated moving average.
Attribute - ANSWER A characteristic or measurement - for example, a person's height
or the color of a car. Aka "feature", "covariate" or "predictor"
Autoregression - ANSWER Regression technique using past values of time series data
as predictors of future values.
Autoregressive integrated moving average (ARIMA) - ANSWER Time series model that
uses differences between observations when data is nonstationary. Also called Box-
Jenkins.
Bayes' theorem/Bayes' rule - ANSWER Fundamental rule of conditional probability:
𝑃(𝐴|𝐵) = 𝑃(𝐵|𝐴)𝑃(𝐴) / 𝑃(𝐵) .
Bayesian Information criterion - ANSWER (BIC) Model selection technique that trades
off model fit and model complexity. Generally penalizes complexity more than AIC.
Lower is better.
Bayesian regression - ANSWER Regression model that incorporates estimates of how
coefficients and error are distributed.
BIC - ANSWER Bayesian information criterion
Binary data - ANSWER Data that can take only two different values (true/false, 0/1,
black/white, on/off, etc.).
Binary variable - ANSWER Variable that can take just two values: 0 and 1.
Box and whisker plot - ANSWER Graphical representation data showing the middle
