BUAL 2650 - Gramling- Exam 3 || Questions with
Complete Solutions.
multiple regression model correct answers used to predict a dependent (quantitative) variable
using two or more independent variables
^y=b0+b1x1+b2x2+⋯+bkxk correct answers multiple regression formula
r-squared correct answers measures the proportion of the variance in the dependent variable
explained by the model
a better fit correct answers Higher R-squared means_________
adjusted R-squared correct answers adjusts for the number of predictors, penalizing models that
add unnecessary complexity.
increases R-squared correct answers adding new predictor variables to a model always______
SSR/SST
(sum of squares regression/ sum of squares total) correct answers R^2=
penalty correct answers Adjusted R^2 imposes a ______ on the correlation strength of larger
models
adjusted r-squared correct answers allows for a more equitable comparison between models with
different number of independent variables, k
n-k-1 correct answers residual df=
1 correct answers beta coefficient tells you the change in the dependent variable for a _____ unit
increase in the predictor variable
when you are predicting something based on more than one independent variable correct answers
when is multiple regression used?
one predictor variable correct answers For simple regression, the predicted value "depends" only
on_______
the number of independent (or explanatory) variables to make a prediction correct answers What
does K equal?
the prediction correct answers what does y^ equal?
the y-intercept correct answers what does b0 equal?
, square root of MSE correct answers How do you find s or SE
SSR/DF (K) correct answers How do you find MSR?
SSE/DF (n-k-1) correct answers How do you find MSE
K (the number of independent variables) correct answers How do you find regression DF
n-k-1 (sample size- predictor variables-1) correct answers How do you find residual DF
MSR/MSE correct answers How do you find F-ratio
bj/sbj (coefficient/SE Coefficient) correct answers How do you find T ratio
R^2 correct answers shows how well the independent variables collectively explain the variance
in the dependent variable
Adjusted R-squared correct answers accounts for the number of predictors and penalizes
unnecessary complexity
R-squared correct answers _______ can be artificially high if you add more predictors, even if
the predictors don't actually improve the model significantly
SE- standard error correct answers measures the average distance that the observed values fall
from the regression line
lower SE correct answers A ______ indicates that the predictions are closer to the actual values-
showing a more accurate model
precise predictions correct answers A lower SE is generally preferred because it suggests more
______
goodness of fit correct answers checking a model with r^2 and SE
multiple regression correct answers uses two or more independent quantitative variables to
describe a quantitative dependent variable
dependent variable correct answers Multiple regression has only one quantitative
Null hypothesis correct answers This is the "default" assumption, where we assume that there's
no effect or no difference.
Alternative hypothesis correct answers This is what we suspect might be true- the outcome is
affected
Complete Solutions.
multiple regression model correct answers used to predict a dependent (quantitative) variable
using two or more independent variables
^y=b0+b1x1+b2x2+⋯+bkxk correct answers multiple regression formula
r-squared correct answers measures the proportion of the variance in the dependent variable
explained by the model
a better fit correct answers Higher R-squared means_________
adjusted R-squared correct answers adjusts for the number of predictors, penalizing models that
add unnecessary complexity.
increases R-squared correct answers adding new predictor variables to a model always______
SSR/SST
(sum of squares regression/ sum of squares total) correct answers R^2=
penalty correct answers Adjusted R^2 imposes a ______ on the correlation strength of larger
models
adjusted r-squared correct answers allows for a more equitable comparison between models with
different number of independent variables, k
n-k-1 correct answers residual df=
1 correct answers beta coefficient tells you the change in the dependent variable for a _____ unit
increase in the predictor variable
when you are predicting something based on more than one independent variable correct answers
when is multiple regression used?
one predictor variable correct answers For simple regression, the predicted value "depends" only
on_______
the number of independent (or explanatory) variables to make a prediction correct answers What
does K equal?
the prediction correct answers what does y^ equal?
the y-intercept correct answers what does b0 equal?
, square root of MSE correct answers How do you find s or SE
SSR/DF (K) correct answers How do you find MSR?
SSE/DF (n-k-1) correct answers How do you find MSE
K (the number of independent variables) correct answers How do you find regression DF
n-k-1 (sample size- predictor variables-1) correct answers How do you find residual DF
MSR/MSE correct answers How do you find F-ratio
bj/sbj (coefficient/SE Coefficient) correct answers How do you find T ratio
R^2 correct answers shows how well the independent variables collectively explain the variance
in the dependent variable
Adjusted R-squared correct answers accounts for the number of predictors and penalizes
unnecessary complexity
R-squared correct answers _______ can be artificially high if you add more predictors, even if
the predictors don't actually improve the model significantly
SE- standard error correct answers measures the average distance that the observed values fall
from the regression line
lower SE correct answers A ______ indicates that the predictions are closer to the actual values-
showing a more accurate model
precise predictions correct answers A lower SE is generally preferred because it suggests more
______
goodness of fit correct answers checking a model with r^2 and SE
multiple regression correct answers uses two or more independent quantitative variables to
describe a quantitative dependent variable
dependent variable correct answers Multiple regression has only one quantitative
Null hypothesis correct answers This is the "default" assumption, where we assume that there's
no effect or no difference.
Alternative hypothesis correct answers This is what we suspect might be true- the outcome is
affected
