QBA 3305 Final Exam
= - ANS-must be exactly
≤ - ANS-cannot exceed
≥ - ANS-at least
2 types of observational data - ANS-Retrospective data is from the past (say a year
ago.) Prospective data is in real-time.
Analysis of Variance (ANOVA) - ANS-Used to compare more than two means.
balanced design - ANS-Equal sample sizes in each group. This is preferred.
Binding - ANS-All of the resource or constraint was used.
Blinding - ANS-Withholding what type of treatment was given
blocking - ANS-group subjects together according to something that is uncontrollable
but may affect the response
characteristics of linear optimization models - ANS-1. objective function and constraints
are linear functions of the decision variables
2. all variables are continuous
Completely Randomized design - ANS-has just one factor
confounded variables - ANS-When two factors have been conjoined and cannot be
separated. E.g. Store & Product sales.
constraints - ANS-Limitations or specifications.
= LHS, Sign, RHS
Constraints in optimization models - ANS-algebraic inequalities with variables on left
and constraint terms on the right
Control group purpose - ANS-A baseline for the data
decision variables - ANS-The variables that will represent "how much" of a resource is
needed.
dimensions (Tableau) - ANS-hold the categorical variables
, Double blind - ANS-this term describes an experiment in which neither the subjects nor
the experimenter knows whether a subject is a member of the experimental group or the
control group
effective error rate - ANS-increases exponentially with the number of means compared
incorrectly
=1 - ( 1-α)^k (k=# of pairwise comparisons)
experiment - ANS-recording the outcomes from the manipulation of attributes in the
study
experimental data - ANS-information that describes the result of a careful manipulation
of the system under study
F-value of factorial - ANS-Use F -ratio of source with interaction
F= - ANS-variance between treatment means/variance
factorial design - ANS-can test for interaction between two variables
feasible solution (optimization problem) - ANS-any solution that satisfies all of the
constraints
filtering techniques - ANS-Filter by Top 10, Range (Min to Max)
full factorial design - ANS-contains treatments that represent all possible combinations
of all levels with all factors
Given a specific scenario, define what the experiment is, the design, factors, levels,
treatments, and response variable. - ANS-
How does ANOVA control the variables - ANS-It controls the variation within the groups
while measuring the variation between the groups.
How is LP used in today's businesses - ANS-Determine the Optimal Product mixes,
transportation routes, schedules, media mixes.
How many pairwise comparisons could be made if I had the groups North, South, East,
and West - ANS-6 -North &South, North & East, North & West, East and West, East and
South, West and South. You could also work out a Combination of 4 things taken two at
a time.
how much is left of constraint - ANS-constraints -- slack
Hypothesis for completely randomized and randomized block - ANS-Ho: μ1=μ2=μ3
Ha: At least two means differ
= - ANS-must be exactly
≤ - ANS-cannot exceed
≥ - ANS-at least
2 types of observational data - ANS-Retrospective data is from the past (say a year
ago.) Prospective data is in real-time.
Analysis of Variance (ANOVA) - ANS-Used to compare more than two means.
balanced design - ANS-Equal sample sizes in each group. This is preferred.
Binding - ANS-All of the resource or constraint was used.
Blinding - ANS-Withholding what type of treatment was given
blocking - ANS-group subjects together according to something that is uncontrollable
but may affect the response
characteristics of linear optimization models - ANS-1. objective function and constraints
are linear functions of the decision variables
2. all variables are continuous
Completely Randomized design - ANS-has just one factor
confounded variables - ANS-When two factors have been conjoined and cannot be
separated. E.g. Store & Product sales.
constraints - ANS-Limitations or specifications.
= LHS, Sign, RHS
Constraints in optimization models - ANS-algebraic inequalities with variables on left
and constraint terms on the right
Control group purpose - ANS-A baseline for the data
decision variables - ANS-The variables that will represent "how much" of a resource is
needed.
dimensions (Tableau) - ANS-hold the categorical variables
, Double blind - ANS-this term describes an experiment in which neither the subjects nor
the experimenter knows whether a subject is a member of the experimental group or the
control group
effective error rate - ANS-increases exponentially with the number of means compared
incorrectly
=1 - ( 1-α)^k (k=# of pairwise comparisons)
experiment - ANS-recording the outcomes from the manipulation of attributes in the
study
experimental data - ANS-information that describes the result of a careful manipulation
of the system under study
F-value of factorial - ANS-Use F -ratio of source with interaction
F= - ANS-variance between treatment means/variance
factorial design - ANS-can test for interaction between two variables
feasible solution (optimization problem) - ANS-any solution that satisfies all of the
constraints
filtering techniques - ANS-Filter by Top 10, Range (Min to Max)
full factorial design - ANS-contains treatments that represent all possible combinations
of all levels with all factors
Given a specific scenario, define what the experiment is, the design, factors, levels,
treatments, and response variable. - ANS-
How does ANOVA control the variables - ANS-It controls the variation within the groups
while measuring the variation between the groups.
How is LP used in today's businesses - ANS-Determine the Optimal Product mixes,
transportation routes, schedules, media mixes.
How many pairwise comparisons could be made if I had the groups North, South, East,
and West - ANS-6 -North &South, North & East, North & West, East and West, East and
South, West and South. You could also work out a Combination of 4 things taken two at
a time.
how much is left of constraint - ANS-constraints -- slack
Hypothesis for completely randomized and randomized block - ANS-Ho: μ1=μ2=μ3
Ha: At least two means differ
