Correlation and Regression with SPSS - Coursework Example

Introduction The concept that income distribution within a population could be a vital determinant of health has prompted a huge and increasing research literature. In recent times, the relationship that exists between health status and total income of a family has been called into question. Previous studies have suggested and revealed a negative relationship between low income and life expectancy and appositive relationship between low family income and mortality across most developed countries. Other revised studies have indicated a positive relationship between high income and high health standards within the family settings. According to The National Poverty Center at the University report, there were 14.1 million children that lived in poverty in the USA by the year 2008. 19% of these children were below 18 years old. The official level of poverty changes and in relation to household size; however, in 2008 the definition of poor family changed if a single parent with two children had an income below $17,346. The Connecticut Commission on children indicates that most children living in poverty are more vulnerable to diseases than children from more a well off homes. According to this commission, most babies that are born to low-income parents experience lower birth weights hence are more vulnerable to infant mortality. Child Trends organization reports that children from poor families experience mental health such as impulsiveness, disobedience and difficulties in association with other people. Their self-esteem is low and this may affect them throughout their lives. It is clear that income is a determinant on the health conditions of a person. Therefore this study wants to determine the effect of total family income on the health condition of an individual. The research question guiding this study is: does total income a family positively impact the health conditions of an individual. Objective of the study The objective of the study is to determine the effects of total family income in the health condition/status of an individual. Statistical assumptions Researchers, who study the effect of income on health conditions, generally seek to generalize their results from the available data to some larger context by generalizing a sample to a population. Assumptions are important aspect of empirical studies. This study, just like any other study, applies some statistical assumptions in order to achieve at the desired results. The statistical assumptions are: The mean difference is zero The data is normally distributed The variance of the two variables are equal (homoscedasticity) Methodologies The independent variable of the study is income while the dependent variable is health. The study will mainly duel on correlation and regression for data analysis. Correlation coefficient is important in showing whether and how strongly income and health conditions are related. Because the study is linear in nature, Pearson product-moment correlation coefficient will be used to measure the direction and strength of the linear relationship between income and health conditions. The value of Pearson’s correlation coefficient is influenced by the distribution of the independent (income) variable in the sample. Regression analysis defines the relationship between income and health status. The following regression model will be used during the study: Y=Bo + BX + e (where; Y= heath conditions, X=income, Bo=constant, e=error term). T-test will be used to determine the significance of the regression model before using it to predict the value of health status given values for income. Apart from; t-tests, regression and correlation coefficient, tables and graphs will also be used to determine the effect of income on health conditions of an individual. Hypothesis The hypothesis of the study is derived from the research question above. Null hypothesis Ha: total income of a family positively impacts the health conditions of a person. Alternative hypothesis Ho: total income of a family does not positively impacts the health conditions of a person. RESULTS The mean for total family income is 17.66 while the mean of health condition is 2.06. The standard deviations for total family income and health condition are 6.067 and 0.820 respectively. Correlation results The correlation matrix is shown below Total family income Condition of health Total family income (Pearson correlation) Sig. (2-Tailed) 1 __ -0.191 0.00 Condition of health Sig. (2-Tailed) -0.191 0.00 1 __ The Pearson correlation coefficient is -0.191. This means that there is a weak negative relationship between total family income and health condition. The negative sign shows that if one variable increase, the other variable decreases. For example, increases in total family income will results to a decline in health conditions. Generally, total family income and health conditions exhibit negative correlation. The Sig. (2-Tailed) value from correlation output is 0.00. This value is less than 0.05. Hence there is a statistically significant correlation between total family income and health conditions. Regression  The regression equation as per the spss output is Y= 2.505 -0.25X + e (0.67) (0.004) The regression coefficients: 2.505: this is the constant -0.25 this shows that; holding other factors constant, an increase in income by one unit will reduce health condition by 0.25 units. The values (0.67) and (0.004) are the standard errors for constant and income respectively. The coefficient for income is statistically significant because the p-value is 0.00 which is less than 0.05. The intercept is significantly different from 0 at the 0.05 alpha levels. Hypothesis testing Ha: total income of a family positively impacts the health conditions of a person. Ho: total income of a family does not positively impacts the health conditions of a person. The one way Anova gives a p-value of 0.00. The study uses 95% confidence interval that means the significance level is 0.05. Therefore, the P-value (0.00)< significance level (0.05). Therefore we reject the null hypothesis and accept the alternative hypothesis. We conclude therefore that income does not positively impact the health of a person. Scatterplot Conclusion The objective of the study was to determine the impact of total family income in health conditions. The regression analysis shows that income does not positively impact health conditions of an individual. The hypothesis testing also indicates similar results while Pearson correlation coefficient also a negative correlation between income and health conditions. The scatterplot diagram also reveals a similar situation. Therefore, from the study it is necessary to conclude that income does not positively impact health conditions. This is in line with other studies but at the same time contradicts other earlier studies. But the conclusion of this study is solely based on the results attained from analysis of the available data. References Cronk, B. C. (2008). How to use SPSS: A step-by-step guide to analysis and interpretation. Glendale, CA: Pyrczak Pub. Read More