Description
Please see attached document.
- Were all assumptions tested for?
- Are there some violations that the model might be robust against? Why or why not?
- Explain and provide any additional resources (i.e., web links,
articles, etc.) to provide your colleague with addressing diagnostic
issues.
1. What is your research question?
Our research question is: “Is it any difference between men and women regarding job
satisfaction and do men worry more than women regarding finding a job?
We will estimate a regression model with:
•
•
•
Y= dependent variable = low income – dummy variable – variable 19
X1 = independent variable = job is just a way to earn $ – variable 947
X2 = independent variable = job satisfaction = variable 947
The regression equation is: y= β0+β1X1+β2 X2 +ε (Wagner, 2016).
2. Interpret the coefficients for the model, specifically commenting on the dummy variable.
We will run a multiple regression analysis in SPSS and get the estimated model:
Hence, the estimated multiple regression equation is:
Y = 1.317+ 0.002 (X1)+0.26 (X2)
Interpreting the coefficients:
Interpreting the coefficients:
•
•
For any unit increase in the number of hours/week, the income is increasing by
0.002;
For any additional brother and sister, the income is increasing by 0.026 (Wagner,
2016).
3.Run diagnostics for the regression model. Does the model meet all of the assumptions? Be
sure and comment on what assumptions were not met and the possible implications. Is there any
possible remedy for one the assumption violations?
The regression model assumptions are:
•
•
Linear relationship: This assumption is true since our model is valid (Sig. = 0.01 – in
ANOVA table)
Multivariate normality
Allison (1999) outline that the components of a study are guaranteed to be independent and
uncorrelated only when the multivariate normality of the variables is assumed. However, if
the normality assumption does not hold, components are guaranteed to be uncorrelated, but not
independent. Besides, if the independence assumption is violated, each component cannot be
uniquely interpreted because of contamination by other components. Now, we will look at the
diagram below and see that the dummy variable has two histograms which are normally
distributed.
No or little multicollinearity- This will be tested with VIF (Variance Inflection factor)
Since the values of VIF are close to 1, we conclude that there is no multicollinearity of the data.
No auto-Correlation
Homoscedasticity
For this assignment we will perform the Durbin-Watson test in SPSS- Huitema and McKean
(2007) agree that many tests have been developed to identify errors but suggested that the
Durbin-Watson (D-W) test is the best statistic approach although the test was not designed to
identify autocorrelated errors.
Since the value of DW is close to 2, we could conclude that there is no homoscedasticity. Hence,
it was concluded that all the assumptions are true, and the model is valid.
Purchase answer to see full
attachment
Our research question is: “Is it any difference between men and women regarding job
satisfaction and do men worry more than women regarding finding a job?
We will estimate a regression model with:
•
•
•
Y= dependent variable = low income – dummy variable – variable 19
X1 = independent variable = job is just a way to earn $ – variable 947
X2 = independent variable = job satisfaction = variable 947
The regression equation is: y= β0+β1X1+β2 X2 +ε (Wagner, 2016).
2. Interpret the coefficients for the model, specifically commenting on the dummy variable.
We will run a multiple regression analysis in SPSS and get the estimated model:
Hence, the estimated multiple regression equation is:
Y = 1.317+ 0.002 (X1)+0.26 (X2)
Interpreting the coefficients:
Interpreting the coefficients:
•
•
For any unit increase in the number of hours/week, the income is increasing by
0.002;
For any additional brother and sister, the income is increasing by 0.026 (Wagner,
2016).
3.Run diagnostics for the regression model. Does the model meet all of the assumptions? Be
sure and comment on what assumptions were not met and the possible implications. Is there any
possible remedy for one the assumption violations?
The regression model assumptions are:
•
•
Linear relationship: This assumption is true since our model is valid (Sig. = 0.01 – in
ANOVA table)
Multivariate normality
Allison (1999) outline that the components of a study are guaranteed to be independent and
uncorrelated only when the multivariate normality of the variables is assumed. However, if
the normality assumption does not hold, components are guaranteed to be uncorrelated, but not
independent. Besides, if the independence assumption is violated, each component cannot be
uniquely interpreted because of contamination by other components. Now, we will look at the
diagram below and see that the dummy variable has two histograms which are normally
distributed.
No or little multicollinearity- This will be tested with VIF (Variance Inflection factor)
Since the values of VIF are close to 1, we conclude that there is no multicollinearity of the data.
No auto-Correlation
Homoscedasticity
For this assignment we will perform the Durbin-Watson test in SPSS- Huitema and McKean
(2007) agree that many tests have been developed to identify errors but suggested that the
Durbin-Watson (D-W) test is the best statistic approach although the test was not designed to
identify autocorrelated errors.
Since the value of DW is close to 2, we could conclude that there is no homoscedasticity. Hence,
it was concluded that all the assumptions are true, and the model is valid.
Purchase answer to see full
attachment
Categories: