ISYE 6402 CERTIFICATION SCRIPT 2026
QUESTIONS WITH SOLUTIONS GRADED A+
◍ Global.
Answer: Lasso, ElasticNet and Ridge are examples of what kind of approach
◍ How many terms to estimate in a VAR model?.
Answer: In a n‐variate system, the number of coefficients in each equation is
1+np and the total number is n(1+np)=n+ ^2p
◍ Stepwise regression.
Answer: A combination of forward and backward feature selection
◍ Bellman's Equation.
Answer: Used to determine optimal state
◍ if Wt is a white noise process, then the first order difference of Wt is
stationary.
Answer: TRUE
◍ What has to do w/ invertible - Xt or Zt?.
Answer: causal and Xt - think c and chi.invertible and Zt
◍ Constraints.
Answer: Restrictions on variables in an optimization scenario or called
◍ Comparison and Control.
Answer: Red and blue cars must be similar in all other aspects (age, car
type) is an example of what
◍ if-then constraint.
Answer: A constraint requiring same/opposite decisions is called what
◍ in VAR modeling, residual analysis.
Answer: needs to be performed to diagnose goodness of fit. correct
,◍ Slow.
Answer: Are interger optimizations fast or slow?
◍ Greedy.
Answer: Stepwise, Backward and Forward feature selection are what kind of
approach
◍ Prescriptive Analytics.
Answer: Optimization is a key part of what?
◍ which assumptions of stationary are violated?.
Answer: 2. Consider the following assumptions for stationary time series: (i)
Constant mean; (ii) Finite variance; and (iii) Covariance between any two
observations depends only on the time lag between them.Which
assumptions of stationarity seem to be violated (figure 1)?i) and iii)
◍ T/F - A linear process is a special case of the moving average model..
Answer: FALSE - the moving average is a special case of a linear process.
◍ Exponential.
Answer: Weibull measure time between failures. What measure trials
between discrete failures?
◍ T/F Your boss hands you the
U. S. inflation rate and exchange rate time series. The two sequileries are
not stationary, and are known to have a long-run equilibrium relationship.
Building a VAR model on the differenced data is a preferable way to go
about analyzing the two series..
Answer: FALSE - if long run equilibrium, you've got co-integration and
can't just difference it
◍ ElasticNet.
Answer: Lasso and Ridge Regression are special cases of what?
◍ No.
Answer: Is the Weibull distribution memoryless?
◍ Sequential game theory.
, Answer: rock-paper-scisors (decisions made at the same time).
◍ what in an ACF plot would show non-stationarity?.
Answer: slowly decreasing lags
◍ can confidence intervals be used for significance?.
Answer: you bet - should all be same sign for significance
◍ Running models.
Answer: What is optimization software particularly good at?
◍ The sum of the squares of the coefficients.
Answer: Ridge regression puts a constraint on what?
◍ If ADF ~ 0.
Answer: The null hypothesis is that the time series is stationary. If p value is
small, we reject the null hypothesis of stationarity.
◍ All factors.
Answer: Backwards feature selection starts with
◍ Suppose we fit a VAR model to the 6 time series simultaneously. At the
0.05 significance level, a 0.24 p-value corresponding to the multivariate
Ljung-Box Q(m) statistic test for uncorrelated model residuals means that.
Answer: There is no lead-lag relationship among the six series correct
◍ T/F For Structural VAR models, restrictions are needed for parameters to be
identifiable. Having a B model means the B matrix must be an Identity
matrix..
Answer: FALSE - restrictions are necessary, but B model means A = I. A
model means B = I
◍ T/F A white noise process has zero autocovariances except at lag zero..
Answer: TRUE
◍ A/B Testing.
Answer: Fast data collection is needed
◍ Randomness.
QUESTIONS WITH SOLUTIONS GRADED A+
◍ Global.
Answer: Lasso, ElasticNet and Ridge are examples of what kind of approach
◍ How many terms to estimate in a VAR model?.
Answer: In a n‐variate system, the number of coefficients in each equation is
1+np and the total number is n(1+np)=n+ ^2p
◍ Stepwise regression.
Answer: A combination of forward and backward feature selection
◍ Bellman's Equation.
Answer: Used to determine optimal state
◍ if Wt is a white noise process, then the first order difference of Wt is
stationary.
Answer: TRUE
◍ What has to do w/ invertible - Xt or Zt?.
Answer: causal and Xt - think c and chi.invertible and Zt
◍ Constraints.
Answer: Restrictions on variables in an optimization scenario or called
◍ Comparison and Control.
Answer: Red and blue cars must be similar in all other aspects (age, car
type) is an example of what
◍ if-then constraint.
Answer: A constraint requiring same/opposite decisions is called what
◍ in VAR modeling, residual analysis.
Answer: needs to be performed to diagnose goodness of fit. correct
,◍ Slow.
Answer: Are interger optimizations fast or slow?
◍ Greedy.
Answer: Stepwise, Backward and Forward feature selection are what kind of
approach
◍ Prescriptive Analytics.
Answer: Optimization is a key part of what?
◍ which assumptions of stationary are violated?.
Answer: 2. Consider the following assumptions for stationary time series: (i)
Constant mean; (ii) Finite variance; and (iii) Covariance between any two
observations depends only on the time lag between them.Which
assumptions of stationarity seem to be violated (figure 1)?i) and iii)
◍ T/F - A linear process is a special case of the moving average model..
Answer: FALSE - the moving average is a special case of a linear process.
◍ Exponential.
Answer: Weibull measure time between failures. What measure trials
between discrete failures?
◍ T/F Your boss hands you the
U. S. inflation rate and exchange rate time series. The two sequileries are
not stationary, and are known to have a long-run equilibrium relationship.
Building a VAR model on the differenced data is a preferable way to go
about analyzing the two series..
Answer: FALSE - if long run equilibrium, you've got co-integration and
can't just difference it
◍ ElasticNet.
Answer: Lasso and Ridge Regression are special cases of what?
◍ No.
Answer: Is the Weibull distribution memoryless?
◍ Sequential game theory.
, Answer: rock-paper-scisors (decisions made at the same time).
◍ what in an ACF plot would show non-stationarity?.
Answer: slowly decreasing lags
◍ can confidence intervals be used for significance?.
Answer: you bet - should all be same sign for significance
◍ Running models.
Answer: What is optimization software particularly good at?
◍ The sum of the squares of the coefficients.
Answer: Ridge regression puts a constraint on what?
◍ If ADF ~ 0.
Answer: The null hypothesis is that the time series is stationary. If p value is
small, we reject the null hypothesis of stationarity.
◍ All factors.
Answer: Backwards feature selection starts with
◍ Suppose we fit a VAR model to the 6 time series simultaneously. At the
0.05 significance level, a 0.24 p-value corresponding to the multivariate
Ljung-Box Q(m) statistic test for uncorrelated model residuals means that.
Answer: There is no lead-lag relationship among the six series correct
◍ T/F For Structural VAR models, restrictions are needed for parameters to be
identifiable. Having a B model means the B matrix must be an Identity
matrix..
Answer: FALSE - restrictions are necessary, but B model means A = I. A
model means B = I
◍ T/F A white noise process has zero autocovariances except at lag zero..
Answer: TRUE
◍ A/B Testing.
Answer: Fast data collection is needed
◍ Randomness.
