List Of Statistically Significant Independent Variables. Case Study Examples

1 SEAT ALL ELECTRIC MODEL

Size of home town

Gender
Marital
Age category
Level of education
Income category
Gasoline emissions contribute to global warming
4 SEAT GASOLINE HYBRID
Size of home town
Gender
Age category
Level of education
Income category

Dwelling type

I am worried about global warming
Gasoline emissions contribute to global warming

Directional relationship of statistically independent variables

1 SEAT ALL ELECTRIC MODEL
Size of home town- The coefficient for size of home town is 4.257E-7. So for every unit increase in size of home town, a 4.257E-7 is predicted, holding all other variables constant.
Gender- The coefficient for gender is -1.304. So for every unit increase in gender, a -1.304 is predicted, holding all other variables constant.
Marital status- The coefficient for marital status is -0.320. So for every unit increase in marital status, a -0.320 is predicted, holding all other variables constant.
Age category- The coefficient for age category is -0.026. So for every unit increase in age category, a -0.026 is predicted, holding all other variables constant.
Level of education- The coefficient for level of education is -0.188. So for every unit increase in level of education, a -0.188 is predicted, holding all other variables constant.
Gasoline emissions contribute to global warming- The coefficient for gasoline emissions contribute to global warming is 0.155. So for every unit increase in gasoline emissions contribute to global warming, a 0.155 is predicted, holding all other variables constant.
4 SEAT GASOLINE HYBRID
Size of home town- The coefficient for size of home town is -7.158E-7. So for every unit increase in size of home town, a -7.158E-7 is predicted, holding all other variables constant.
Gender- The coefficient for gender is -1.503. So for every unit increase in gender, a -1.503 is predicted, holding all other variables constant.
Age category- The coefficient for age category is -0.099. So for every unit increase in age category, a -0.099 is predicted, holding all other variables constant.
Level of education- The coefficient for level of education is 0.463. So for every unit increase in level of education, a 0.463 is predicted, holding all other variables constant.
Income category- The coefficient for income category is -1.034E-5. So for every unit increase in income category, a -1.034E-5 is predicted, holding all other variables constant.
Dwelling type- The coefficient for dwelling type is 0.132. So for every unit increase in dwelling type, a 0.132 is predicted, holding all other variables constant.
I am worried about global warming- The coefficient for I am worried about global warming is -0.433. So for every unit increase in I am worried about global warming, a -0.433 is predicted, holding all other variables constant.
Gasoline emissions contribute to global warming- The coefficient for gasoline emissions contribute to global warming is 0.652. So for every unit increase in gasoline emissions contribute to global warming, a 0.652 is predicted, holding all other variables constant.

The relative importance of each statistically independent variables

1 SEAT ALL ELECTRIC MODEL
Size of home town has a coefficient of 4.257E-7 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Gender has a coefficient of -1.304 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Marital status has a coefficient of -0.320 which is significantly different from zero (0) because its p value is 0.019 which is smaller than 0.05.
Age category has a coefficient of -0.026 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Level of education has a coefficient of -1.188 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Gasoline emissions contribute to global warming has a coefficient of 0.155 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
4 SEAT GASOLINE HYBRID
Size of home town has a coefficient of -7.158E-7 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Gender has a coefficient of -1.503 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Age category has a coefficient of -0.099 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Level of education has a coefficient of 0.463 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Income category has a coefficient of -1.034E-5which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Dwelling type has a coefficient of 0.132 which is significantly different from zero (0) because its p value is 0.005 which is smaller than 0.05.
I am worried about global warming has a coefficient of -0.433 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.
Gasoline emissions contribute to global warming has a coefficient of 0.652 which is significantly different from zero (0) because its p value is 0.000 which is smaller than 0.05.

The strength of statistically independent variables

1 SEAT ALL ELECTRIC MODEL
R- R is the square root of R-squared and it shows the correlation between the observed and predicted values of the dependent variables.
There is a 0.527 correlation between the observed and predicted values of the dependent variables (hybrid model). There is a 0.527 correlation between the observed and predicted values of the independent variables (hybrid model). A 0.527 correlation is an indication of relatively strong correlation between observed and predicted variables.
R-Square- This is an overall measure of the strength of association and does not reflect the extent to which any particular independent variable is associated with the dependent variable. There is a 0.278 strength of association between dependent variables (hybrid model) which can be explained by independent variables (size of home town, gender, marital status, age category, level of education, gasoline emissions contribute to global warming).
0.278 strength is an indication of a low correlation between dependent and independent variables.
4 SEAT GASOLINE HYBRID
R- R is the square root of R-squared and it shows the correlation between the observed and predicted values of the dependent variables.
There is a 0.718 correlation between the observed and predicted values of the dependent variables (hybrid model). A 0.718 correlation is an indication of a strong correlation between the observed and predicted variables.
R-Square- This is an overall measure of the strength of association and does not reflect the extent to which any particular independent variable is associated with the dependent variable. There is a 0.516 strength of association between dependent variables (hybrid model) which can be explained by independent variables (size of home town, gender, number of people in household, age category, level of education, income category, dwelling type, I am worried about global warming, gasoline emissions contribute to global warming).
0.516 strength is an indication that there is a relatively high correlation between the dependent and independent variables.