- Data spans from 1950 - 2015. Data for 2015 is for partial year thru June.
- Examines the relationship between unemployment rate and individual income and savings in the US. The data is annual since 1950 and Disposable Income and Personal Savings are in billions of US Dollars.The null hypothesis being that Disposable Personal Income is a good predictor of Personal Savings.
- The interactive app is hosted at https://tinausa.shinyapps.io/Project.
- The linear regression model fit examines the goodness-of-fit statistics, as seen in Figure - 1.
- Even though disposable income has increased over the years with the exception of the last few years, personal savings have declined consistently since 1965 as displayed in Figure - 2.
- As shown in Figure - 1 and on slide 5, the adjusted r-squared is 0.8347999 explains the goodness-of-fit of this model - variability of the data around the mean. And the correlation between the two variables is 0.9136738.
- As shown on slide 5, the p-value is almost zero and hence it can be deduced that Disposable Personal Income is a good predictor for Personal Savings.
- Given the data in 6 and 7 above, the null hypothesis would be accepted.
Coursera DSS Developing Data Product Project
US Unemployment & Personal Savings - 1950-2015
Smita Desai
Data Science Student
US Unemployment & Personal Savings
US Unemployment & Personal Savings - Figure 1
Historic Relationship between Individual Disposable Income and Individual Savings.
US Unemployment & Personal Savings - Figure 2
US Unemployment & Personal Savings - Model
##
## Call:
## lm(formula = PersSavings ~ DisposPersIncome, data = dt)
##
## Residuals:
## Min 1Q Median 3Q Max
## -256.354 -42.587 0.794 51.667 307.800
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 62.909166 14.766538 4.26 6.83e-05 ***
## DisposPersIncome 0.046437 0.002582 17.98 < 2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 84.06 on 64 degrees of freedom
## Multiple R-squared: 0.8348, Adjusted R-squared: 0.8322
## F-statistic: 323.4 on 1 and 64 DF, p-value: < 2.2e-16