Multiple Linear Regression (Exercise) : Example No 1

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 5

Multiple Linear Regression (Exercise)

EXAMPLE NO 1
NULL HYPOTHESIS H0:
Importance is not a significant predictor of job satisfaction.

ALTERNATIVE HYPOTHESIS H1:


Importance is a significant predictor of job satisfaction

NULL HYPOTHESIS H0:


Advancement is not a significant predictor of job satisfaction.

ALTERNATIVE HYPOTHESIS H2:


Advancement is a significant predictor of job satisfaction

NULL HYPOTHESIS H0:


Express ideas is not a significant predictor of job satisfaction.

ALTERNATIVE HYPOTHESIS H3: Express ideas is not a significant predictor of


job satisfaction
H4: Importance, advancement and express of ideas are significant predictorof job
satisfaction.

Model Summary
Adjusted R Std. Error of the
Model R R Square Square Estimate
1 .755a .471 .521 7.46000
a. Predictors: (Constant), express, advance, importance

ANOVAa
Model Sum of Squares df Mean Square F Sig.
1 Regression 1922.024 3 640.675 11.512 .000b
Residual 1446.943 26 55.652
Total 3368.967 29
a. Dependent Variable: satisfaction
b. Predictors: (Constant), express, advance, importance
Coefficientsa
Standardized
Unstandardized Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) -5.756 9.083 -.634 .532
importance 1.051 .288 .522 3.650 .001
advance .205 .242 .113 .849 .403
express 1.069 .423 .372 2.529 .018
a. Dependent Variable: satisfaction

RESULT
A multiple regression was conducted predicting job satisfaction to the variable’s
connectedness, importance, advancement and express of ideas. We checked the assumption
of normality, linearity, homoscedasticity and multicollinearity. . All the assumptions were
met. Overall, the regression model was significant, F (3,26) =11.51, p<.05, R2=.47
(accounted of variance in dependent variable). Of all the predictors investigated both
importance (β=.552, t (26) =3.65, p<.05) and expression of ideas (β=.372 t (26) =.2.53,
p<.05) were significant. Advancement was not a significant predictor of job satisfaction.
(β=.113, t (26) =.849, p>.05). So that, Alternative hypothesis H1, H3 and H4 are accepted
while H2 was not supported by the data

EXAMPLE NO 2

NULL HYPOTHESIS H0:


Forgiveness is not a significant predictor of happiness.

ALTERNATIVE HYPOTHESIS H1:


Forgiveness is a significant predictor of happiness.

NULL HYPOTHESIS H0:


Social support is not a significant predictor of happiness.

ALTERNATIVE HYPOTHESIS H2:


Social support is a significant predictor of happiness.
NULL HYPOTHESIS H0:
Forgiveness and social support are not significant predictors of happiness.

ALTERNATIVE HYPOTHESIS H3:


Forgiveness and social support are significant predictors of happiness.

Model Summary
Adjusted R Std. Error of the
Model R R Square Square Estimate
a
1 .677 .559 .409 4.98011
a. Predictors: (Constant), support, forgiveness

ANOVAa
Model Sum of Squares df Mean Square F Sig.
1 Regression 462.367 2 231.184 9.321 .001b
Residual 545.633 22 24.801
Total 1008.000 24
a. Dependent Variable: happiness
b. Predictors: (Constant), support, forgiveness

Coefficientsa
Standardized
Unstandardized Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) 5.798 5.207 1.114 .277
forgiveness .399 .095 .664 4.223 .000
support .299 .251 .187 1.191 .246
a. Dependent Variable: happiness

RESULT
A multiple linear regression was conducted to predict happiness from the variable’s
forgiveness and social support. We checked the assumption of normality, linearity,
homoscedasticity and multicollinearity. All the assumptions were met. Overall, the regression
model was significant, F (2, 22) =9.32, p<.05, R2=.56 (accounted of variance in dependent
variable). Of all the predictors investigated Forgiveness (β=.664, t (22) =4.22, p<.05) was
significant. Social support was not a significant predictor of happiness. (β=.187, t (22) =1.19,
p>.05). Thus, H1 and H3 are accepted while H2 was not supported by the data.

EXAMPLE NO 3

NULL HYPOTHESIS H0:


Wellbeing is not a significant predictor of fear of death.

ALTERNATIVE HYPOTHESIS H1:


Wellbeing is not a significant predictor of fear of death.

NULL HYPOTHESIS H0:


Meaning in life is not a significant of death predictor fear of death
ALTERNATIVE HYPOTHESIS H2:
Meaning in life is a significant predictor of fear of death.

NULL HYPOTHESIS H0:


Wellbeing and meaning in life are not significant predictors of fear of death.

ALTERNATIVE HYPOTHESIS H3:


Wellbeing and meaning in life are not significant predictors of fear of death.

Model Summary
Adjusted R Std. Error of the
Model R R Square Square Estimate
a
1 .365 .133 .096 8.36053
a. Predictors: (Constant), meaning, wellbeing

ANOVAa
Model Sum of Squares df Mean Square F Sig.
1 Regression 503.655 2 251.827 3.603 .035b
Residual 3285.225 47 69.898
Total 3788.880 49
a. Dependent Variable: feardeath
b. Predictors: (Constant), meaning, wellbeing

Coefficientsa
Standardized
Unstandardized Coefficients Coefficients
Model B Std. Error Beta t Sig.
1 (Constant) 36.434 6.405 5.688 .000
wellbeing .290 .211 .209 1.375 .176
meaning -.349 .130 -.407 -2.677 .010
a. Dependent Variable: feardeath

RESULT
A multiple linear regression was conducted to predict fear of death from the variables well-
being and meaning in life. We checked the assumption of normality, linearity,
homoscedasticity and multicollinearity. All the assumptions were met. Overall, the regression
model was significant, F (2, 47) =3.60, p<.05, R2=.13 (accounted of variance in dependent
variable). Of all the predictors investigated meaning in life (β=-.407, t (47) =-2.68, p<.05)
was significant. Well-being was not a significant predictor of fear of death. (β=.209, t (47)
=1.38, p>.05). Thus, H2 and H3 are accepted while H1 was not supported by the data.

You might also like