PLS-SEM Midterm Exam Study Set Questions
and Answers Grade A+ 2023
What are the two types of analysis tools? - -Exploratory and confirmatory. Exploratory helps
develop a model. Confirmatory confirms a theory.
-What are exploratory analysis tools? - -1st generation tools include Cluster analysis, EFA, and
Multi dimensional scaling. 2nd generation tools include PLS-SEM, which is non-parametric and
OLS estimation.
-What are confirmatory analysis tools? - -1st generation tools include ANOVA, Logistic
Regression, and Multiple Regression. 2nd generation tools include CB-SEM with CFA, which is
normal distributions, parametric, and ML estimation.
-Define SEM - -Structural equation modeling.
It is Soft modeling and has Latent variable modeling.
It is multivariate.
Enables the examination of relationships among measured variables and latent variables.
-What is a Latent Variable? - -Latent variable: captures a phenomenon that is unobservable (e.g.
perception, intention). It cannot be directory measured.
-What are Latent Variable traits? - -Abstract, Complex, Not directly measurable. Ex: trust,
intention to use, intention to buy. There is no objective measurement such as $ or miles or
temperature.
-What is an independent variable (IV)? - -Variable related to the DV that:
Drives the DV
Predicts the DV
'Causes' the DV
Explains the DV
-What is a dependent variable (DV)? - -Variables that respond to changes in the IVs
-What is Simple Linear Regression? - -Example: We believe there is a relationship between the
number of sales calls made in a month and the number of copiers sold that month. The IV is
number of calls and the DV is copiers sold.
-How to use a scatter plot? - -Scatter plots show if there is a relationship between and IV and a
DV. It uses r, the correlation coefficient to show the strength of the relationship.
-What is the Correlation Coefficient r? - -r is a measure of the strength of the relationship
between two variables.
, It requires interval or ratio-scaled data.
It can range from -1.00 to 1.00.
Values of -1.00 or 1.00 indicate perfect and strong correlation.
Values close to 0.0 indicate weak correlation.
Negative r indicate an inverse relationship and positive r indicate a direct relationship.
-What is perfect correlation? - -r = 1 or -1. -1 has a negative slope (goes down from left to right)
and 1 has a positive slope (goes up from left to right)
-How do you interpret the Correlation Coefficient? - -0 is no correlation, 1 is perfect correlation.
.5 is moderate correlation
Above .5 is strong, below .5 is weak.
-What can you do with a strong correlation? - -Make predictions about the IV and the DV. For
example, if more sales calls are made more copiers will be sold.
-What is regression? - -The line of best fit among the data points. Expressed as For every 1 unit
change in X, estimate of Y is ? For example Make 10 sales calls, Should sell 30.8 copiers
-What is r squared? - -It is the Coefficient of Determination and it is the square of correlation. It
is the proportion of the total variation in the dependent variable (Y) that is explained or
accounted for by the variation in the independent variable (X).
-What does r squared tell us? - -It ranges from 0 to 1. It does not give any information on the
direction of the relationship between the variables because when you square it you lose any
negative signs.
-Give an example of r and r squared - -If the r = .76 the r sq is .58. This tells us that 58% of the
variance in the DV is explained by the IV.
-What are Measures of Dispersion of Data? - -Mean, Variance, Standard Deviation.
-What is Standard Deviation? - -How the all the data for a variable varies around the mean for
that variable. For example if the SD was 9.2, The sales calls data varies around the mean by 9.2
sales calls.
-What is the standard error of estimate? - -It measures the dispersion of the observed values
around the regression line. How far the values are from the regression line. If they are close to
the regression line there is a small SE, if they are far from the regression line there is a large SE.
-When to use PLS-SEM? - -Use to develop theories; exploratory research, SmartPLS 3, PLS
Graph. Maximizes the explained variance in the DV.
When your data is non-parametric (distributions are unknown or skewed). It has no requirement
for normality.
and Answers Grade A+ 2023
What are the two types of analysis tools? - -Exploratory and confirmatory. Exploratory helps
develop a model. Confirmatory confirms a theory.
-What are exploratory analysis tools? - -1st generation tools include Cluster analysis, EFA, and
Multi dimensional scaling. 2nd generation tools include PLS-SEM, which is non-parametric and
OLS estimation.
-What are confirmatory analysis tools? - -1st generation tools include ANOVA, Logistic
Regression, and Multiple Regression. 2nd generation tools include CB-SEM with CFA, which is
normal distributions, parametric, and ML estimation.
-Define SEM - -Structural equation modeling.
It is Soft modeling and has Latent variable modeling.
It is multivariate.
Enables the examination of relationships among measured variables and latent variables.
-What is a Latent Variable? - -Latent variable: captures a phenomenon that is unobservable (e.g.
perception, intention). It cannot be directory measured.
-What are Latent Variable traits? - -Abstract, Complex, Not directly measurable. Ex: trust,
intention to use, intention to buy. There is no objective measurement such as $ or miles or
temperature.
-What is an independent variable (IV)? - -Variable related to the DV that:
Drives the DV
Predicts the DV
'Causes' the DV
Explains the DV
-What is a dependent variable (DV)? - -Variables that respond to changes in the IVs
-What is Simple Linear Regression? - -Example: We believe there is a relationship between the
number of sales calls made in a month and the number of copiers sold that month. The IV is
number of calls and the DV is copiers sold.
-How to use a scatter plot? - -Scatter plots show if there is a relationship between and IV and a
DV. It uses r, the correlation coefficient to show the strength of the relationship.
-What is the Correlation Coefficient r? - -r is a measure of the strength of the relationship
between two variables.
, It requires interval or ratio-scaled data.
It can range from -1.00 to 1.00.
Values of -1.00 or 1.00 indicate perfect and strong correlation.
Values close to 0.0 indicate weak correlation.
Negative r indicate an inverse relationship and positive r indicate a direct relationship.
-What is perfect correlation? - -r = 1 or -1. -1 has a negative slope (goes down from left to right)
and 1 has a positive slope (goes up from left to right)
-How do you interpret the Correlation Coefficient? - -0 is no correlation, 1 is perfect correlation.
.5 is moderate correlation
Above .5 is strong, below .5 is weak.
-What can you do with a strong correlation? - -Make predictions about the IV and the DV. For
example, if more sales calls are made more copiers will be sold.
-What is regression? - -The line of best fit among the data points. Expressed as For every 1 unit
change in X, estimate of Y is ? For example Make 10 sales calls, Should sell 30.8 copiers
-What is r squared? - -It is the Coefficient of Determination and it is the square of correlation. It
is the proportion of the total variation in the dependent variable (Y) that is explained or
accounted for by the variation in the independent variable (X).
-What does r squared tell us? - -It ranges from 0 to 1. It does not give any information on the
direction of the relationship between the variables because when you square it you lose any
negative signs.
-Give an example of r and r squared - -If the r = .76 the r sq is .58. This tells us that 58% of the
variance in the DV is explained by the IV.
-What are Measures of Dispersion of Data? - -Mean, Variance, Standard Deviation.
-What is Standard Deviation? - -How the all the data for a variable varies around the mean for
that variable. For example if the SD was 9.2, The sales calls data varies around the mean by 9.2
sales calls.
-What is the standard error of estimate? - -It measures the dispersion of the observed values
around the regression line. How far the values are from the regression line. If they are close to
the regression line there is a small SE, if they are far from the regression line there is a large SE.
-When to use PLS-SEM? - -Use to develop theories; exploratory research, SmartPLS 3, PLS
Graph. Maximizes the explained variance in the DV.
When your data is non-parametric (distributions are unknown or skewed). It has no requirement
for normality.
