This action might not be possible to undo. Are you sure you want to continue?
THE DETERMINANTS OF HAPPINESS
( Word Count: XXXX)
Declaration of Original Work In submitting this assignment 1. We declare that this written assignment is our own work and does not include (i) material from published sources used without proper acknowledgment or (ii) material copied from the work of other students. 2. We declare that this assignment has not been submitted for assessment in any other course at any university. 3. We have a photocopy or electronic version of this assignment in our possession.
Certain indicator factors assumed to be relevant in the determination of happiness will be identified and linked to our four established categories in order to model the behaviour of HAPPY. In the end. Data screening. we decided on the question “Taking all things together. and religion. in our opinion. job. Concerning the results of our research. we selected a range of indicator variables from the European Social Survey that we believed would model the influences above. which will all be underlined by a range of indicator variables describing them in greater detail. Factor analysis will be applied to produce latent variables from the range of indicator 1 http://www.html 2 The „pursuit of happiness“ is included as one of the undeniable rights of men in the United States Declaration of Independence 1 . and religion.The Determinants of Happiness I. SUMMARY It is the purpose of our research project to examine the determinants and influences of happiness. accounting for roughly 18 percent of variation only. II. we can state that age turned out to be insignificant in the determination of happiness while family and religion only showed little correlation with our dependent variable. how happy would you say you are?” (the variable HAPPY) of the European Social Survey. our factors were complemented by the remaining independent variables to gain a broader picture and more solid results. or even part of our political system2. and religion. The drive to achieve happiness characterises most humans’ life. health. In order to prove our hypothesis that the level of happiness is mainly affected by the four major factors of family.inspirednow. health. family. Grenville) The aim of this research paper is the investigation of the determinants of happiness. INTRODUCTION “In the pursuit of happiness. H. however. health. we have to state. That is why we decided to make the determinants of happiness the focus of our project. Summing up. the difficulty lies in knowing when you have caught up. In order to reach a conclusion we plan to set up a regression modelling the level of happiness. It is our hypothesis that we will end up with four latent variables along the line of our established categories. We identified four basic categories of variables that. Our detailed research question can be read as “Which aspects in life determine happiness?”. Nevertheless it can take totally different forms such as a general objective in life. we ended up with three latent factors indicating the determinants of family. As a result. we concluded that happiness mainly depends on the status of health and job satisfaction where the latter one actually evolved as our strongest determinant of happiness.”1 (R. led to the situation that a significant fraction of our indicator variables describing the influence of job & work did not prove appropriate for factor analysis. exert a major influence on the level of happiness. These three factors were then implemented in a regression analysis in order to determine their impact on the level of happiness. For the dependent variable. These are job. that our regression model is far from being reliable. however. This is surprising since we especially predicted family to be a major impact on the level of happiness. Finally. all of them having a significant influence on the level of happiness.com/goals--happiness. a fundamental concept of our religious belief.
This allows us to check whether our hypothesis that happiness is mainly affected by the categories of job. that the complexity of the concept of happiness does not allow us to come up with a fundamental and comprehensive answer but rather an indication of the major trends and impacts. however. we hope to have gained a range of meaningful results in order to draw a number of solid conclusions from our analysis and come up with a rough explanation of the determination of happiness. 2 . however. how happy would you say you are?”) as the dependent variable. Portugal. Norway. however. The study. proven by the fact that the Q-Q plot closely follows a straight line with a slope of one. It must be noted. Therefore we will deal with secondary data only. III. According to the ESS questionnaire. Finally. DATA DESCRIPTION The project will be based on the third round of the European Social Survey conducted in 2006 and 2007. As shown below the variable is approximately normally distributed. it is measured on a scale from zero to ten with zero being “extremely unhappy” and ten “extremely happy”. the apparent disadvantage is that it was designed for a purpose differing from our research question so validity problems may be faced. health. precision. On the contrary.The Determinants of Happiness variables. The fact that it is funded by government and EU agencies allows the achievement of a high degree of data quality. and Ukraine. we have chosen to use HAPPY (“Taking all things together.1 The Dependent Variable As mentioned in the introduction. our concerns for accuracy. is of crosssectional nature and can be considered a representative sample. Ireland. Nevertheless. that is. 3. We narrowed down the data set to five countries. Therefore. and reliability are negligible. Austria. it seems that the distribution is actually slightly left skewed. We will use this variable for our regression analysis in order to see how the range of chosen factors models the level of happiness. and religion is correct. founded by the European Commission in association with the European Science Foundation. the Central Limit Theorem (which will be more deeply explained below) allows us to disregard the slight skewness. family. This shape indicates that the majority of people interviewed are in general rather happy. According to our histogram.
calculated State of Health Services in your country nowadays RLGDGR RELIGION Have you ever considered yourself as belonging to any particular religion or denomination? How religious are you? PRAY How often do you pray apart from religious services? In terms of measurement scale and level of measurement. Since we plan to use factor analysis to extract latent variables we made sure that each category contains at least three indicator variables. NUMERICAL Interval STFJB STFECO STFJBOT STFHLTH RLGDGR Ratio NBTHCLD AGE Nominal EVMAR PARTNER RLGBLG CATEGORICAL Ordinal PDAPRP HEALTH HLTHHMP PRAY 3. considering your efforts & achievement? HEALTH How is your health in general? EVMAR PARTNER FAMILY Are or have you ever been married? Dou you live with your husband/wife/partner? Number of children ever given birth to/fathered Number of people living regularly as members o household STFJBOT NBTHCLD PDAPRP HHMMB HEALTH RLGBLG HLTHHMP AGE STFHLTH Are you hampered in daily activities by illness/disability/infirmary/mental problems? Age of respondent. As a result. the situation in which a model is uncovered that cannot be observed in the population. These are summarized in the table below.The Determinants of Happiness 3.2 The Independent Variables Considering our four categories of influence. we identified a total of 15 indicating variables from the ESS questionnaire that allow us to draw conclusions about the four basic factors described above. If our plan turns out to be correct. we tried to keep the number of variables in each category low in order to avoid overfitting. we came up with a number of indicator variables that we believed would add explanatory power for our independent factors. we would end up with four different latent variables from the extraction process that represent the four categories illustrated in detail below. On the other hand. our independent variables show a wide range of different categories.3 Data Screening of Independent Variables 3 . STFJB STFECO JOB How satisfied are you with your job? How satisfied are you with the present state of the economy in your country? Are you satisfied with the balance between time on your job & time on other aspects? Do you feel that you get paid appropriately.
484 Our sample size of 9.562 -.491 1.101 2.21 2. Furthermore. When analysing extreme values.025 . and PRAY show kurtosis levels above 1.220 -.050 . Therefore we can disregard the rule of thumb that non-normality exists if the absolute value of skewness and/or kurtosis is above 1.050 . In addition.066 .269 .844 .44 1.858 .36 4.025 .066 . and sabotage may lead to answers different from the truth.308 . RLGBLG.049 .706 . the Central Limit Theorem allows us to disregard these concerns. normality can be assumed.948 -1.972 -.025 . It states that if the sample size is sufficiently large.82 2.403 -.050 .980 -. Especially NBTHCLD does not seem to have a normal distribution according to skewness and kurtosis figures. Dev. a large sample size guarantees correlation reliability that will be required for the application of factor analysis.310 2.025 . random responses.43 6.41 2. Descriptive Statistics N Min Max Mean St.332 .049 .025 . Skewness Statistic St.025 .953 -1.2597 5. These thoughts have to be kept in mind throughout this project and especially highlight the need of preliminary data screening. a few points have to be kept in mind. simple calculations showed that three generations of a family living together in the same household can easily reach a two-digit number.050 .531 .066 .642 -1.137 . Hence.37 2.050 STFJB STFECO STFJBOT PDAPRP EVMAR PARTNER NBTHCLD HHMMB HEALTH HLTHHMP AGE STFHLTH RLGBLG RLGDGR PRAY Valid N 5571 9594 5561 5540 9828 9549 6477 9827 9820 9743 9671 9706 9760 9770 9671 3275 0 0 0 1 1 1 1 1 1 1 14.83 1. due to the large number of interviews conducted there is a high chance of data entry errors. Also HLTHHMP shows critical values for both skewness and kurtosis.025 .96510 2.030 . or thoughts.774 -.025 Kurtosis Statistic St. showing the highest values in both cases for all the variables.16 5.97 4. Error .846 interviewed people is large enough to allow reference to the Central Limit Theorem.033 .349 -. our first thoughts considered a maximum of 15 to be an improbable value as well.83 0 1 0 1 10 10 10 5 2 2 31 15 5 3 97.643 . We defined outliers as values outside the 4 .856 51.025 .025 .050 .423 -. feelings.033 . Nevertheless.354 -.33 1.257 -. The screening for outliers will give us a more accurate picture and understanding of the questioned values. accidental errors. we found a maximum value for NBTHCLD – the number of children ever given birth to/fathered – of 31 that can be clearly marked as impossible. social desirability bias may cause questioned individuals to state answers that differ from their true opinions.547 17.684 -.The Determinants of Happiness Since the underlying data originates from a survey.385 . First of all.335 2.173 1.41 2. Lastly. PARTNER.509 .423 1. AGE.050 .288 . Furthermore. However.061 . we figured that 15 is a possible value.72 46.025 .971 2.612 .502 -1.033 .963 .481 2.472 .050 .274 1.049 .610 -1. Error -. For HHMMB.11 2. including a small “buffer”.381 4.58 10 2 10 7 7.
4 . however. According to calculations based on this rule of thumb and as predicted above. among other requirements. variables NBTHCLD and HHMMB show outliers. the ESS states that potential candidates for interviews must be members of a private household.8 1.9 . Even with this restriction we keep several responses that are marked as outliers in the Box-and-Whisker Plot since the mean is slightly above 2 (or 2.4 2.7 .3. a maximum of 31 for NBTHCLD is considered to be impossible.5 standard deviations from the mean. 3.The Determinants of Happiness interval of +/.8 43.6 43. This is especially illustrated in the Box-and-Whisker Plots below. of Extremesa Low 0 0 High 349 0 5 . we believe that the maximum of 15 household members found in the data set is possible and therefore relevant in our investigation.2597 Std.8 No. Responses around the higher end of the interval cannot be serious or are due to errors and mistakes.4 Missing Value Analysis Univariate Statistics: Missing Value Anaylsis Missing N nbthcld age stfjb stfeco stfjbot pdaprp evmar partner health hlthhmp stfhlth rlgblg rlgdgr pray 6463 9671 5571 9594 5561 5540 9828 9549 9820 9743 9706 9760 9770 9671 Mean 2. As explained above.5 43. the situation of outliers can be explained by the focus of the ESS survey. As a result.0 .96510 Count 3383 175 4275 252 4285 4306 18 297 26 103 140 86 76 175 Percent 34. Deviation 1.38 46.4 1.0 1. As a result. As a result.3 1.41 to be exact). In the case of HHMMB. we agreed to exclude any values for NBTHCLD that are above 10. In contrast. large households become outliers.2 3.240 17. outliers for HHMMB will be included in further analysis. The vast majority of private households in Europe consist of nuclear families.
Furthermore. Pairwise deletion is possible for all of our variables and we think that using this method will provide us with the most accurate result.240 17. This means that we omit the case from just those parts of the analysis that use the variables for which values are missing. We believe that this is explained by the fact that only people who currently have work were able to answer this question. of Extremesa Low 0 0 High 349 0 The data estimations show evidence on high proportion of missing values in some variables.0 . To start off.7 percent of missing values. keeping in mind that the proper responses given are only valid for people that have a job. thereby being recorded as a missing value in the data set. IV. 6 . some people could have found this topic sensible so they are unwilling to provide an answer. We have decided to use pairwise deletion.4 percent. however. each of them representing one identified category of indicator variables.96510 Count 3383 175 4275 252 4285 4306 18 297 26 103 140 86 76 175 Percent 34. we will run tests to check data suitability and sufficient correlation for data analysis.5 43.0 1.4 2.9 .8 1. We therefore decide to accept the high amount of missing values for these variables. the same reasons also apply for STFJBOT and STFJB.4 .8 43. and the determinant of the correlation matrix will be used to obtain appropriate sets of indicator variables. Deviation 1.8 No. The Kayser-MayerOlkin Measure of Sampling Adequacy (KMO MSA). there are a number of ways to deal with missing values.7 .2597 Std. This could be explained by the fact that people who have never given birth to/fathered a child may have answered “not applicable”. In the variable PDAPRP (Do you get paid appropriately considering effort and achievement?) there is a proportion of 43. “no answer” or simply left the question blank instead of stating “0”.3 1. Bartlett’s Test of Sphericity. FACTOR ANALYSIS As discussed above.6 43.4 1. In our opinion. For the variable NBTHCLD (Number of children ever given birth/fathered to?) the percentage of missing values was 34.38 46.2 3. As a consequence.The Determinants of Happiness Univariate Statistics: Missing Value Anaylsis Missing N nbthcld age stfjb stfeco stfjbot pdaprp evmar partner health hlthhmp stfhlth rlgblg rlgdgr pray 6463 9671 5571 9594 5561 5540 9828 9549 9820 9743 9706 9760 9770 9671 Mean 2. it is our plan to end up with four different latent variables.
5. In a good factor model. Extraction Communalities Initial STFJB .402 Variable HEALTH HLTHHMP AGE STFHLTH RLGBLG RLGDGR PRAY Anti-Image Correlation 0. In order to check that our data shows a sufficient level of common variance we apply the measures of sampling adequacy for each variable (MSA) and the particular communalities.679 PDAPRP 0. we can reject the null hypothesis and conclude that there is correlation between at least two variables.502. both at 0. Our obtained result of 0. Summary: Anti-Image Matrix Variable Anti-Image Correlation STFJB 0.651 0.638 can be defined as the ratio of Bartlett's Test of Sphericity Approx. Also PARTNER and NBTHCLD. no correlation among the variables. is considered inadequate according to the rule of thumb.268 Extraction . Furthermore. Since the level of significance is 0 (and thus below 0. For the multicollinearity test.638 is of medium quality.611 0. HHMMB. The relevant values are obtained from the anti-image matrix that is not fully included in the report but summarized below for the benefit of simplicity and clarity.with 0. we can proof absence of multicollinearity since its value is greater than zero.713 0. however.5 and can therefore be included in further analysis.402. almost all of them being above the critical level of acceptance at 0.502 HHMMB 0.730 STFJBOT 0. THE MSA results are strong. we have to check for the absence of multicollinearity and for a sufficient common variance. . KMO and Bartlett's Test Moving on. our point of interest is the determinant. it checks the null hypothesis that the matrix R is significantly different from the identity matrix – that is.The Determinants of Happiness The KMO MSA applies to the data set as a whole and Kaiser-Meyer-Olkin Measure of Sampling Adequacy.719 As it can be seen. on the other hand. show low values.661 0.617 PARTNER 0.570 0. .05).876 the sum of all squared df 105 correlations in the sample to the sum or all squared Sig. Even though it shows a low value with 0.723 STFECO 0. Here.000 correlations plus the sum of all squared partial correlations. the Bartlett’s Test of Sphericity is a test statistic used to examine the hypothesis that the variables are uncorrelated in the population. A determinant equal to 0 would indicate a problem of multicollinearity in the correlation matrix. In essence. Therefore we decided to exclude it from further multivariate analysis. both of them are above 0. The concept of MSA is the preliminary measure of common variance relative to other sources of shared variance. The majority of variables are satisfactory.428 7 . The only exception is HHMMB – the number of household members . There would definitely be room for improvement but it is a value we can work with.025. we produced a correlation matrix.778 EVMAR 0. Chi-Square 13074.801 0.502 NBTHCLD 0. the proportion of common variance should be higher than the sum of the squared partial correlations.
PDAPRP. it will be added again to the regression during the final phase of our multivariate analysis. This Extraction Method: Principal Axis Factoring.173 .4 are excluded.713 which the extracted factors explain an . we also agreed to exclude the variable AGE from factor extraction. “Health” and “Religion”.408 . Therefore we decided to treat STFJB as an independent variable and remove it from the factor analysis as well. we are left with the three categories “Family”.675 STFJBOT. Finally. Hence. All other variables are measured on an anchored scale.101 Here.513 .087 that show extraction communality lower than STFHLTH . We will use only those variables for HEALTH .508 . hopefully leading to three extracted factors of significance. We believed that the job factors as well as the number of children would play an essential role in our model. and STFHLTH do not meet these criteria.502 to 0. Bartlett’s Test of Sphericity. we run KMO MSA.164. NBTHCLD.4 indicates RLGBLG that 40% of common variance is modelled.198 .327 . are still met in our adjusted set of indicator variables. STFECO.386 . PRAY .605 .103 . The “Final Extraction Communalities” Table shows the new communalities for the adjusted range of indicators after the inappropriate variables have been excluded.478 8 . Hence. the results are not as strong as we HHMMB . we can check whether the extracted factors explain an adequate amount of common variance STFECO STFJBOT PDAPRP EVMAR PARTNER NBTHCLD . at this point of multivariate analysis. there are too little indicators available now to guarantee a satisfactory modelling. in theoretical terms.566 . we obtained satisfactory results from our final MSA values so that we can conclude a sufficient level of common variance. As a result.150 . the absence of multicollinearity and a sufficient level of correlation or common variance. Hence. Thereby problems of multicollinarity can be ruled out. Negligible changes in communalities confirmed that finding. only one variable from the job category is identified as appropriate. The value of 0. Communality is the proportion of common variance given the extracted factor model.638 to 0. However. individual MSA and communality analyses again to make sure that the requirements of suitable data.443 HLTHHMP adequate amount of variance given the . Hence.634 while the Bartlett’s Test of Sphericity still shows a significance level of 0 but at a much lower number of degrees of freedom.The Determinants of Happiness In order to gain further insight the estimates of communalities are evaluated.792. Summary: Final Anti-Image Matrix Variable Anti-Image Correlation EVMAR 0. We observed that KMO MSA has decreased slightly from 0. In addition.648 . it is the only variable from the range of job indicators for which the extracted factors explain an adequate amount of common variance.229 .663 According to the table above.374 . we can conclude that we deal with sufficient correlation in the data set in order to extract factors.473 0.397 . The determinant of the correlation matrix has increased significantly to 0. contradicts our hypothesis.381 . ranging from 0. For the “Job Factor”.236 . any variables AGE . RLGDGR .224 . This decision is based on the fact that this variable shows a different scale set-up in comparison to the rest. we have to adjust the rest of the procedure as well as our hypothesis.515 . Hence. Now. MSA for each of the remaining variables from the anti-image show negligible variations compared to previous values.957 extracted factor model.453 hoped.562 PARTNER 0.
According to the Kaiser’s rule (or latent root criterion).689 0.The Determinants of Happiness Initial HEALTH HLTHHMP RLGBLG RLGDGR PRAY 0. The Scree Test.507 . In order to define the number of factors to extract from an initial solution.935 1.606 HLTHHMP . it seems like our modified hypothesis has become true.060 13. explaining a satisfactory amount of 56.543 89.555 PARTNER . After the third factor.273 19. we implemented two restrictions: 1.000 Total 1.330 As can be seen from the graph above. three factors satisfy our two requirements.509 82.349 0.644 43.384 . Rotation is a geometric transformation of the factor matrix so that the 9 .715 2.653 When it comes to factor extraction.492 .474 RLGDGR . A minimum of 50 percent of the variance explained across all the observed variables.458 .092 95.644 16.540 75.267 22. we applied a rotation factor matrix. Extraction Sums of Squared Loadings Cumulative % 33. Hence.559 1. we have decided on the common factor model since our research project is of social nature.496 HEALTH .698 Final Extraction Communalities Extraction EVMAR .704 56. This is explained by the fact that a developed factor makes sense only as long as it gives more information than single variables.549 6.193 4.434 . 2.398 . To aid interpretation.927 percent of variance.223 Cumulative % 27. the minimum value of the eigenvalues is set to 1.267 55. Total Variance Explained Factor Initial Eigenvalues Total d1 i2 m 3 e 4 n 5 s 6 i o7 n 0 Extraction Method: Principal Axis Factoring. which is clearly out of our predetermined range.500 .285 100.5.688 PRAY . the graph indicates a deep fall in the level of eigenvalue to a point below 0. a plot displaying the eigenvalues in decreasing order over the number of factors.927 % of Variance 33. The common factor model assumes that each variable has some unique variance and some variance that is common with the other variables.926 % of Variance 27.525 0. confirms this result: Three extracted factors show an eigenvalue greater than 1.531 0.783 0.507 0.970 7. The used method is principal axis factoring.325 .033 6.329 1.514 RLGBLG .351 .124 .
051 religion or denomination how religious are you at religious services Extraction Method: Principal Axis Factoring.036 .043 how often pray apart from . and “How often do you pray apart from religious services”.027 hampered in daily activities . a. we used Kaiser’s Varimax Rotation that minimises the complexity of factors by maximising the variance of the loadings on each factor. Rotation converged in 4 iterations.086 -. These are “Belonging to a particular religion or denomination”.683 -.710 . “Are or ever married” and “Living with a partner” both show high correlation with factor 2.699 -.004 -.The Determinants of Happiness relationship between the variables is still the same but orientation of the factors is different.804 Factor 1 is closely correlated to the indicator factors related to religion.081 -. we can identify the factor of health from “Subjective general health” and “hampered in daily activities by illness” in form of the third factor.011 -.776 .005 . 2 . we can summarize this group under the factor of religion.715 3 .827 -.162 -.158 with -. Rotated Factor Matrixa Factor 1 are or ever been married lives husband/wife/partner at f4 subjective general health by illness/disability/infirmary/ mental problem belonging to particular . renamed as the factor of family. Finally. Rotation Method: Varimax with Kaiser Normalization.062 . In particular.053 . Therefore. 10 . We will refer to it as the factor of wellbeing in order to avoid confusion with the indicator variable HEALTH. “How religious are you”. Secondly.060 -.
1 The Basic Model Model Summary: Basic Model Model R 1 . 5.023 Standardized Coefficients Beta t Sig. V. REGR factor score 2 for analysis 1. We planned to model the level of happiness by multiple independent variables.002 11 .094 Ad.345 29.000a a. weighted by their correlation with the factor. Predictors: (Constant). Dependent Variable: how happy are you Coefficients: Complete Model Unstandardized Coefficients B St.078 -6.167 F 316.The Determinants of Happiness Now we can move on to factor creation.114 3. Hence.130 . REGR factor score 1 for analysis 1 b.221 31842.998 .272 -. The factor score for each factor extracted is a linear combination of all the variables used in factor analysis.000 ... n the coefficents.002 1.224 7. we try to build a multiple linear regression of the variable HAPPY over our three latent variables created by factor analysis and the independent variables of STFJB and AGE.000 . Here fore we used factor scores through the regression method.019 Religion Family Wellbeing -.335 -7. REGR factor score 4 for analysis 1.094 Std. . we would obtain the following regression equation: “HAPPY” = 0 + 1 “Religion Factor” + 2 “Family Factor” + 3 “Wellbeing Factor” + 4 “Age&Household Factor” + 5 “STFJB” + 6 “AGE” + Ei where 0 is the constant. REGR factor score 3 for analysis 1. Summarising this algebraically.892 -.345 -.342 28836. let us quickly go back to our research question.170 .5) To start off.606 -. Error (Constant) 7.293 -.650 -..000 .308 .563 3 9106 9109 Mean Square 1002.022 .020 . we will build a regression based solely on the latent factors extracted from factor analysis and then add the indicating variables STFJB and AGE at a later point in order to avoid complexity of the model in the present stage of the analysis.179 .998 1.307 a R Square .000 .693 -.063 . and Ei the error term (for n = 1. REGRESSION ANALYSIS As an introduction to the regression analysis.451 Sig. R Square .845 . 95% Confidence Interval for Lower Upper Bound Bound 7.999 .780 DurbinWatson 1. Error of the Estimate 1.817 ANOVAb Model 1 Regression Residual Total Sum of Squares df 3006.2.001 1.090 .135 Collinarity Statistics Tolerance FIV 391.
802 .309 . all of our extracted factors are nevertheless significant since t-test significance is 0 in all cases and none of the 95% confidence levels includes 0.515 .096 -.284 .011 .000 . adding STFJB and AGE will complete our model. our basic model is significant.106 Religion Family Wellbeing STJFB AGE -. 95% Confidence Interval for Lower Upper Bound Bound 5.294 -.The Determinants of Happiness We gain the regression for HAPPY as the dependent variable over our three extracted factors: “HAPPY” = 7. In conclusion.293 “Family Factor” – 0.137 -.307 -.053 1.950 . REGR factor score 2 for analysis 1.676 1.000 .0.0. This indicates a poor goodness-of-fit of the model and means that our three factors extracted account for only 9 percent (rounded to next percentage) of the total level of happiness. R Square . .000 .000 .177 a. REGR factor score 4 for analysis 1 b. of 0.078 “Wellbeing Factor” R squared.140 5 5226 5231 Mean Square 646.026 .053 1. REGR factor score 1 for analysis 1.170 22. we can also state that.420 a Ad. the percentage of HAPPY modelled by our regression.295 .595 . REGR factor score 3 for analysis 1.590 17. except for the very poor fit.239 -.473 .031 .000a . Error of the Estimate 1.880 F 224.515 . Using a significance level of 0.193 1.206 .063 .480 Summarized.016 “AGE” 12 .877 .033 -.2 The Complete Model Model Summary: Complete Model Model R R Square 1 ANOVAb Model 1 Regression Residual Total Sum of Squares df 3233.241 “Wellbeing Factor” + 0. 5.085 -.294 “STFJB” – 0.241 .722 -. our model seems to be all right.041 ”Religion Factor” – 0.005 5.002 . Error (Constant) 5.041 -.219 -4.063 “Family Factor” + 0.002 Standardized Coefficients Beta t Sig.638 2.806 -1. Now. Predictors: (Constant).094 is very low.016 -3.496 Sig.047 .05. our regression line can now be expressed as: “HAPPY” = 5.248 1.534 .176 Std.144 .189 15052. Dependent Variable: how happy are you Coefficients: Complete Model Unstandardized Coefficients B St.950 18286.001 Collinarity Statistics Tolerance FIV 52.950 .697 DurbinWatson 1. Referring to the F-Test for overall significance from the ANOVA table. in general.031 .083 .063 ”Religion Factor” + 0.838 .001 . how satisfied with job.261 -.
is negatively correlated. low Variance Inflator Factor Indices and high tolerance levels allow us to rule out the concern of multicollinarity. indicating only a small impact on the level of happiness. it roughly explains 18 percent of the variance in the level of happiness. Examining the single variables more closely. This variable actually shows the highest level of influence out of all our dependent variables. The significance test for AGE. we realise that two of the variables indicate a positive influence on the level of happiness while the other three exert a negative one. The expected value of Y. is a linear function of our independent variables 3. Also STJB is of positive influence as it can be easily explained: the more satisfaction a person receives from his job. The error terms are normally distributed If these assumptions hold true then our Ordinary Least Square estimators are. The factor of wellbeing. Therefore the negative correlation makes sense since religion is an essential factor in the life of many people that provides them with strength and hope. the value is still too low to speak of a reliable model. Our factors and the error terms Ei are not correlated 2.063. Hence the higher the belief in religion. however. Therefore we can conclude that it is not significant in our regression. on the other hand. have an anchored scale attached that relates a high degree of religious belief to low numbers and vice-versa. the unhappier he becomes. The first factor. Its coefficient.177 in comparison to our poorly fitting basic model. The error terms are random variables with mean 0 4. Even though this is a substantial increase. Religion. 13 .The Determinants of Happiness Adding the independent variables STFJB and AGE to our regression increases the reliability to 0. the higher the level of happiness. Hence. best linear unbiased estimators. Also this factor shows a rather limited influence on happiness due to its coefficient of 0. in contrast. This would indicate that the older a person gets. In case of overall significance of the model. Finally. that is. In addition. the lower the negative influence on the level of happiness.041). here the influence is of positive nature so the higher the factor. PRAY and RLGBLG. The random error terms are not correlated with one another 6. Referring to the coefficients table of the complete model. have an expected value that equals the coefficients. Finally. indicates a value of 0. Finally. which is below our reference value of 0. These assumptions are: 1. shows a much greater correlation with the level of happiness. the lower the factor of family. The majority of its indicator factors. they are a linear function of our dependent variable. Hence. Here the indicator variables EVMAR and PARTNER answer the questions for marriage and living status with partner first with “Yes” and then with “No”. and show the smallest variance in the class of linear unbiased estimators. so that they are considered the most efficient. it can be concluded that STFJB and our extracted factors are significant. is rather small (0. and the greater the level of happiness. the closer and more intimate the relationship. the fact that we use Ordinary Least Squares method to obtain our coefficient estimates requires us to check the assumptions for standard multiple regression in order to make sure that our model is actually valid. according to the Gauss-Markov Theorem. the level of happiness. it is also confirmed this time by a F-test significance level of 0. the error terms have a constant variance to insure homoschedasticity 5. Another factor of negative influence on happiness is the one of family.05. AGE has a negative influence of low relevance. the happier he is.295 > 0.05.
We also need to assert that we have homoschedasticity in order to satisfy assumption number four. However we observe that the distribution is slightly left skewed. CONCLUSION Returning to our final regression model. This is not a problem since the number of observation is high (N=9846). the age has been proven to be insignificant in the determination of happiness.The Determinants of Happiness We can conclude from the distribution of the standardized residuals and from the Normal Probability plot that the error term is approximately normal. This applies to the case shown in our scatter plot below. According to our investigation. Surprisingly. We do this by checking the scatter plot. marriage. such as children. the histogram indicates that error terms show a mean close to 0. This is evident from the fact that the observed residuals in our P-P plot approximately follow the straight line that would represents a normal distribution. higher income 14 . V. Our variable should look like a random array of dots evenly dispersed around zero in order to meet the assumption of homoschedasticity. job satisfaction and the status of health are the two essential determinants of the level of happiness in life. and therefore our analysis is statistically reliable due to the Central Limit Theorem. we can draw certain conclusions from our research project. even though a significantly weaker one. In addition. A reason for that may be that the benefits and costs of a higher age. Religious belief and family relationships also play a role.
are already represented in other categories of variables. on a few indicator variables only. an extended range of independent variables would significantly enhance our model and.The Determinants of Happiness and/or responsibility in job but weaker health.com/goals--happiness. NJ. In so far. we were forced to exclude a high number of indicator variables during multivariate analysis. London. Pearson Education. Third Round. we have to recall the limitations on our sample. and then. Newbold.3 Webpages http://www. The list of possibly significant variables in endless and varies for every individual human being. show relatively common cultural. XXX. NJ. increase our reliability. especially. Thorne. family. 2010) 15 . A broader range of indicator variables would provide us with more accurate and precise factors. or originally four. UK 6. this has been proven correct since we were able to extract exactly these three factors. LIST OF REFERENCES 6. and moral standards and values. However. Marija. Prentice Hall. Statistcal Procedures Companion. social. USA Norusis. we modified our hypothesis in such a way that we now expected three major factors representing the areas of health. areas of focus.0.2 Text Books Carlson. First of all. since they are all European. Second. Statistics for Business and Economics. A broader picture would provide us with more reliable and comprehensive results. Upper Saddle River. We rather expected roughly equally influence from all three. Our study only focuses on five countries that. it is needless to say the model and our results are far from being perfect.inspirednow. SPSS Statistics 17. Therefore we want to indicate a few additional points that we believe would lead to a substantial result. we only focused on four major areas. Summing up. our hypothesis is contradicted by the finding that health and job satisfaction represent such a major share of the determinants of happiness in life. Upper Saddle River. and religion. 2008. Due to the limited scope of this project. 2006/2007. 7th Edition.html (last assessed 31st May. such as in the factors of family or health. Therefore we ended up with two factors that were based on only two indicator variables and thus on a number that is below three which is generally considered as sufficient and satisfactory. USA 6.1 Data Source European Social Survey. VI. During factor analysis. Third.