Search
Browse
Create
Log in
Sign up
Log in
Sign up
Upgrade to remove ads
Only $2.99/month
ST 260 Final Exam
STUDY
Flashcards
Learn
Write
Spell
Test
PLAY
Match
Gravity
Key Concepts:
Terms in this set (43)
Square root of R squared
coefficient correlation (Rxy)
e= Yi-Yi(hat)
residual/error value
SST = SSR +SSE
total variability/ estimates error of variance
R squared
total variability explained by predictor variable(x)
t-ratio
the estimated coefficient is ______ standard deviations from zero
coefficient - 0/ s.e. coefficient
calculate the t-ratio
tails of the t-ratio added together
calculate the p-ratio
co-efficients
____________ do not help determine if on data set is better than another
small p-value
____________ of the constant does not make one model better than another
square root of MSE
how to calculate s (standard error of estimation)
MSR/MSE
how to calculate f-ratio
MSE
________ is an unbiased estimate of the error variance
response variable(x); explanatory variable(y)
_____________ can not be independent of _______________
changing units
__________ can make coefficients larger or smaller so coefficients are not useful in determining if a graph is better than another
the largest value of R squared
a model that includes all predictor variables will always have _________________
extrapolation
estimating or concluding something by assuming existing trends will continue
true
In a simple regression of Y and X, if the sample correlation between Y and X is -1, then SSE must be equal to zero. True or False
False
MSR is an unbiased estimate of the error variance. True or False?
False
In simple linear regression, one of the assumptions of the model is that the response variable is independent of the explanatory variable. True or False?
false
In simple regression, if the estimate b1 is large in absolute value , then the model will produce a correspondingly large value of R squared. True or False?
fasle
in multiple linear regression if SSR=SST then the value of R squared is zero. True or False?
false
in multiple regression application, the least important variable in the model is the one with the smallest estimated coefficient, b1. True or False?
true
in selecting a multiple regression model, the full model, which includes all of the predictor variables, will always have the largest value of R squared. True or False?
residuals
_____________ are the difference between the observed value of Y and the predicted value of X
regression line/ best fit line
________________ is the line that follows the residual formula that minimizes the squared residuals
zero
residuals always sum to _______
least squares; sum of squared residuals
the ______________ line produces a smaller _____________ than any other straight line can
correlation
___________ measures the strength of the linear relationship of two variables
positively correlated
relationship increases with X
negatively correlated
relationship decreases with Y
perfect correlation; line
___________ would indicate that all values in a scatterplot of two variables would form an exact _________
the value or r for this would either be 1 or -1
shotgun pattern
if there is no correlation, then a scatterplot would show a _______________ where there is no discerning effect for one variable towards another
correlation; causation
________________ does not imply ______________
two variables being correlated does not mean that one variable caused the other to occur
k
____ = number of explanatory variables
n
____= total observations
SSR
____= Sum of Squares of Regression
the variability that can be explained by the regression line
SSE
____= Sum of Squares Error
the variability that is around the regression line
SSR/dfR
MSR= ________
SSE/dfE
MSE= ________
R squared/ coefficient of determination
the percent of variability that can be explained by the effects of regression (explained by the line)
the square of the correlation coefficient (r)
f statistic
___________ test whether or not the regression as a whole is useful as a predictor of the response variable
doesnt indicate the number of variables that are significant just indicates that at lease one variable is significant
t statistic
__________ tests whether or not each individual coefficient is useful as a predictor of the response variable
.05
generally if the p value is less than _______ then the explanatory variable is a useful predictor of Y
YOU MIGHT ALSO LIKE...
stats final!!
36 terms
ST 260 Final Exam
53 terms
Stats Test 3
47 terms
chapter 4
15 terms
OTHER SETS BY THIS CREATOR
AC 310 Exam 1
60 terms
AC 371 Exam 1
59 terms
OM Exam 2
124 terms
Macro-Econ Chapter 22
6 terms