+1 (315) 557-6473 

Statistics research assignment using hypothesis testing and multivariate model: Quantitative methodology in SPSS

If you struggle with using SPSS for hypothesis tests and multivariate modeling, you will find this helpful article. Statistical Packages for the Social Sciences, officially known as IBM SPSS, is an environment for analyzing and editing data. It doesn't matter where these data come from. The source can be scientific research, Google analytics, the server log files of some websites, databases, etc. The best thing about SPSS is that it can open almost all structured data file formats. In this sample SPSS assignment, we will investigate Euroskepticism and its determinants in Italy. The data we have used is from the Italian database. For this research, we have formulated our research questions and provided a comprehensive answer based on our study. Also, we have outlined the hypothesis involved and included a multivariate causal model with at least two independent variables. Feel free to contact us if you need assistance with your statistics research assignment.

Introduction

With the exit of United Kingdom in 2016 famously known as Brexit, there has been seen a rise in Euroscepticism whereby some nations are opposing some of the European Union institutions and policies, and are seeking for reformation. In most cases, those member states who are seeking these reforms and oppose the European Union membership see the union as irreformable on the matters they raise. According to Brack & Startin (2015), Euroscepticism has become increasingly mainstream and this can be observed from public opinion, civil society groups and among political parties, and the challenging media discourses. It continues to be a significant ideological current, and the European Union continues to face increasingly pressing challenges, particularly as the rapidly shifting global socioeconomic landscape continues to affect the Union from both within and beyond its borders.

Various researchers and institutions have tried to find out what really drives Euroscepticism. The findings suggest that some of the factors that drive this ideology are beliefs that integration weakens national sovereignty and the nation state, that the EU is too bureaucratic and highly inefficient, stimulates high rates of immigration, chauvinistic and lacks democratic legitimacy and accountability, and that it is a libertarian organization that caters to the big business elite at the expense of the working class, driving austerity and marketization (Sulima, 2018). In a research done by Stanojević, Vujić & Vujović (2022) in Serbia on the causes of the rise in Euroscepticism, their findings suggest that in Serbia, Euroscepticism was on the rise due to a weakening expectation of economic benefits of EU membership and a strengthening of national attachment, including concerns over the loss of national sovereignty, under increased EU pressure on Serbia to give up disputed Kosovo territories.

This paper aims to look at the driving factors to Euroscepticism in Italy. In using the 4th wave of the European Values survey (2008) data, this study identifies various factors that may be the causing factors to Euroscepticism in Italy and seeks to validate these factors by applying quantitative analysis to the data set.

Research Questions and Hypotheses

To meet the main objective of this paper, we seek to answer the following research questions and validate the following hypotheses.

  1. What are the main driving factors of Euroscepticism in Italy?
  2. What is the relationship between the identified factors to Euroscepticism in Italy?

The research hypotheses;

H0: The identified factors do not have an effect on Euroscepticism in Italy

H1: The identified factors do have adverse effect on Euroscepticism in Italy

Data set and Variable Definition

The data set contains 1519 respondent’s response on various issues (EVS, 2008). The main variables of interest are; how much confident one is in the European Union which will be treated as the dependent variable of study, fears that people from less developed countries would take away existing jobs, and the general concern with immigrants. All these are identified are potential factors that can drive Euroscepticism in Italy.

Data Analysis

Descriptive Statistics

Descriptive analysis provides the insights and the basic information of variables within a data set and provide simple summaries about the sample and measures therein.

Table 1: Descriptive statistics of study variables

Variable
FrequencyPercentageMissing
How much confidence in: European Uniona great deal
quite a lot
not very much
none at all
anyone comes who wants to
175
723
387
96
162
11.5%
47.6%
25.5%
6.3%
10.7%
138
(9.1%)
work: people from less developed countries
(V266)
come when jobs available
strict limits on the number of foreigners
prohibit people coming here from other countries
601
602
85
39.6%
39.6%
5.6%
69
(4.5%)
are you concerned with: immigrants?
(V292) 
very much
much
to a certain extent
not so much
not at all
64
322
574
369
150
4.2%
21.2%
37.8%
24.3%
9.9
40
(2.6%)

From the table 1 above, we can see the distribution of the responses for both the dependent variable of study and the consecutive independent variables. The missing values consists reposes that were not relevant to the respective questions. In Italy, 25.5% of the respondents agreed that they do not have very much confidence in European Union, 39.6% of the respondents agreed that there should be restriction by the European union on the number of foreigners from less developed countries to Italy, and that they should only come to Italy when jobs are available. To a great extent, 37.8% of the respondents are concerned with immigrants into Italy.

Fitting of the Model

To fit a model to explain this data set, we fit a multinomial logistic regression with the 4 categories as potential response and this is validated with the two independent variables of study. Multinomial logistic regression is essential in explaining the probability of a category of membership on the dependent variable based on various independent variables (Yin et al., 2018). This model will also help us quantify the relationship between the variables of study and is ideal in answering the research questions of this study.

We check for the goodness of fit test of the fitted model. The Chi-square test for the -2 loglikelihood for model fitting criteria of the final model against the intercept only model is 68.163, with 21 degrees of freedom, the significance value is 0.000. This tests the null hypothesis that the model was not of a good fit for the data, i.e. the fitted model was not better than a model without the covariates. At 5% significance level, 0.000 < 0.05 thus the null hypothesis is rejected and we conclude that the model if of a good fit.

From table 2 above, we test for the causal effects of the selected factors of study in the model to the likelihood of Euroscepticism in Italy. At 5% significance level, 0.000 < 0.05 thus, we can conclude that v292 (Italians being concerned by immigrants) being a significant factor to have an effect on Euroscepticism in Italy.

The coefficient estimates to explain the causal relationship between the independent variable and the dependent variable of study is as shown in the table below.

The reference category is the response that to a great deal an individual has confidence in the European Union. The standard interpretation of the estimates in this model is that for a unit change in the independent variables, the logit of outcome of how much confidence one has on European Union with reference to a great deal is expected to change by its respective parameter estimate which is in log odds given the variables in the model are held constant. For example, the logit for not very much having confidence and not at all having confidence on EU is 1.44 and 0.936 respectively. While the logit for having quite a lot confidence in EU for Italians with reference to having to a great deal confidence is 1.32. We can also identify from the model that as the concern of immigrants in Italy increases there is a reduction in the logit for having confidence in EU thus increasing Euroscepticism.

Conclusion

The main aim of this study was look at the driving factors to Euroscepticism in Italy. In using the 4th wave of the European Values survey (2008) data, this study identified fears that people from less developed countries would take away existing jobs, and the general concern with immigrants can be the leading causes of Euroscepticism in Italy. To meet this objective, the study validated the null hypothesis that the chosen factors do not have an effect on Euroscepticism in Italy. The results show that the identified factors do have adverse effect on Euroscepticism in Italy, and that Italians being concerned by immigrants is a significant factor to help in explaining the effect of Euroscepticism in Italy.

Limitations of the study

The major limitation of the analysis is that this study only fitted a multinomial logistic model and considered all the four categories which assumed that there was a linear relationship between the dependent variable and the independent variables of study.

References

Brack, N., & Startin, N. (2015). Introduction: Euroscepticism, from the margins to the mainstream. International Political Science Review, 36(3), 239-249. https://doi.org/10.1177/0192512115577231.

EVS 2008 Integrated Dataset, ZA4800, v.5.0.0 (2022-06-08), doi:10.4232/1.13841.

Stanojević, N., Vujić, N., & Vujović, S. (2022). The causes of the rise of Euroscepticism: a survey of Serbian citizens in 2020. Journal of Contemporary European Studies, 1-17.

Sulima, E. M. (2018). Brexit, Secession, and Euroscepticism. Mapping Politics, 9.

Yin, M., Zeng, D., Gao, J., Wu, Z., & Xie, S. (2018). Robust multinomial logistic regression based on RPCA. IEEE Journal of Selected Topics in Signal Processing, 12(6), 1144-1154.



Comments
No comments yet be the first one to post a comment!
Post a comment