Sociology Research - Statistics Assessment Answer

• Subject Name : Statistics

Research Paper Writing Assessment Answer

The paper mainly talks about whether respondent and spouse age differences will cause the marriage to end in divorce. Divorce is an important of  aspect how our culture and family are reshaped.

It affedcts the society the most, therefore many socialists have researched about the rationale behind it. The three main sociological perspectives are Conflict theory, Functionalism, and Internationalism. The research question  mainly deals with the Functionalist perspective.

The Functionalist identifies several key functions of the family – socialization, reproduction, protection, emotional support, care, assignment of status, and regulating sexual behavior through social norms.

Sociologists consider social- demographic changes (provision of care, delayed fertility, and population aging) as the reason for divorce.

The null hypothesis states that respondent and spouse age have no significant impact on divorce.

Our alternative hypothesis states that the age difference between respondent and spouse age, is positively correlated with divorce. It means if age differences increases, it is more likely that it will result in divorce. Age difference includes both the cases – where spouse is younger than the respondent and where respondent is younger than the spouse. In the paper, we have included only the results of the first marriage, not the second marriage or third marriage.

Data and Variables

We have used SPSS software to conduct our analysis. Both , dependent and independent variable are collected from General Society Survey data.

The variables included in the analysis are-

Agedifr_ma1 - Age difference between respondent and spouse - first marriage.
Ma1_q170 -  Did your first marriage end in:
The dependent variable is a categorical variable.

Description of the dependent and independent variable

The dependent variable is the outcome variable because it shows what kind of situation the respondents’ first marriage ended in with their spouse. In the survey for this variable, respondents were asked whether their first marriage ended in separation and then divorce or annulment, separation and then the death of spouse, divorce or annulment without separation, or other.  We want to check whether the respondents are divorced, or their spouse died before even before it got to the stage of divorce.

The independent variable is the age difference between respondent and spouse in their first marriage, The variable name in SPSS is AGEDIFGR_MA1. The label for the independent variable is the age difference between respondent and spouse in their first marriage. The dependent variable is the divorce rate and the variable name in SPSS is MA1_Q170. The label for the dependent whether the first marriage ended in divorce. Since there is one independent variable, age differences between respondent and spouse; and one dependent variable, how many respondents ended up in divorce, this is going to be a bivariate regression model. The outcome variable, did the respondent’s first marriage ended up in divorce, is not an interval ratio variable. Therefore, the technique of logistic regression can be used to prove the hypothesis.

The independent variable is the causing variable that states the age differences between respondent and spouse in their first marriage, the factor generates spouses’ chance to end in divorce. In the survey for this independent variable, respondents were asked in their first marriage, how the age gap between the respondents and their spouses. The answers for this survey have separated the age differences into how many years older and younger as different options. In my model, we have recoded the independent variable such that it does not matter who is younger or older. It has been recoded in such a way that year difference are recoding in the same category. For example- recode the category ‘spouse  is 10 years older’ as the same category with ‘spouse  is 10 years  younger’.

The first histogram below is created by the independent variable, agedifgr_ma1, in SPSS. There are 15 bins because the survey separates the age differences into different categories differentiating older and younger. After the recoding (second histogram), there are only 8 bins, which make the result more centralized. Patterns can be seen easily after recoding the variable.

Analytical Strategy(modeling)

We have used logistic regression because our dependent variable is the dummy variable we created from MA1_170, which has just two outcomes: 1 for having divorce and 0 for all other options. In our model, we have nominal variable for both dependent and independent variable.

By logistic regression, we want to empirically check whether age difference between respondent and spouse are more likely to increase the chances of divorce. Logistic regression is the appropriate regression analysis to conduct when the dependent variable is dichotomous (binary).  Like all regression analyses, the logistic regression is a predictive analysis.  Logistic regression is used to describe data and to explain the relationship between one dependent binary variable and one or more nominal, ordinal, interval or ratio-level independent variables.

References

Carmichael, S. (2011). Marriage and power Age at first marriage and spousal age gap in lesser developed countries.The History of the Family,16(4), 416-436. doi10.1016/j.hisfam.2011.08.002
Daz-Gimnez, J., amp Giolito, E. (2013). accounting for the timing of first marriage.International Economic Review,54(1), 135-158. doi10.1111/j.1468-2354.2012.00728.x.
Goldscheider, F., Bernhardt, E., amp Lappegrd, T. (2015). The gender revolution A framework for understanding changing family and demographic behavior.Population and Development Review,41(2), 207-239.
Kalmijn, M. (2007). Explaining cross-national differences in marriage, cohabitation, and divorce in europe, 1990-2000.Population Studies,61(3), 243-263. doi10.1080/00324720701571806
Kolk, M., Stockholms universitet, Samhllsvetenskapliga fakulteten, amp Sociologiska institutionen. (2015). Age differences in unions Continuity and divergence among swedish couples between 1932 and 2007.European Journal of Population / Revue Europenne De Dmographie,31(4), 365-382. doi10.1007/s10680-015-9339-z
Lehrer, E. L., amp Son, Y. J. (2017). Womens age at first marriage and marital instability in the united states Differences by race and ethnicity.Demographic Research,37, 229-250. doi10.4054/DemRes.2017.37.9
Liu, H., amp Waite, L. (2014). Bad marriage, broken heart age and gender differences in the link between marital quality and cardiovascular risks among older adults.Journal of Health and Social Behavior,55(4), 403-423. doi10.1177/0022146514556893
Schaefer, R. T. (2008).Sociology A brief introduction. New York City McGraw-Hill.