Use the data from [Consumer.csv]. We have three fields: Data set available here : https://docs.google.com/spreadsheets/d/18o4OA0zLUo7Xtv-_rZ4_4AzIEM0LmgOm07K-ILvl4bw/edit?usp=sharing -Household income
Question:
Use the data from ["Consumer.csv"]. We have three fields:
Data set available here : https://docs.google.com/spreadsheets/d/18o4OA0zLUo7Xtv-_rZ4_4AzIEM0LmgOm07K-ILvl4bw/edit?usp=sharing
-Household income annually (in $1,000s)
-Household size (number of adults in the home)
-Amount charged to credit card annually(in $1,000s)
1.Make a scatterplot to predict credit card charges from household income. Describe the relationship.
2. Run a correlation analysis to get a rough sense of the strength of relationship. What is the r-value? Is it significant? Interpret it.
3. Run a regression analysis to predict credit card charges from household income. What is the regression equation?
4. What do the slope and intercept mean, in plain language, in the question above?
5.What is the R2 value? What does it mean, in plain language?
6. Someone you work with thinks you could get a better predictive model if you add household size to the regression. Add household size. What is the new regression equation?
7.What is the R2 value now? How much did it go up? What does it mean, in plain language? Do you appear to be predicting credit card spending well? Was it a good idea to add household size? Be sure to compare models using jamovi to see if the one with more predictors is actually 'better'?
8.How much credit card spending would you expect for a home making $100,000 annually with household size of 3?
9.On average, how accurate are your predictions?