Simple regression modeling and meta-analysis

  1. For each of your six OECD or WHR predictors, develop five single-year simple re- gression models on OECD or WHR data, selecting either the OECD variable "Life Satisfaction" or WHR variable "Life Ladder" as the dependent variable. That is, you could develop simple regressions on WHR data for each of the predictors of "Life Lad- der" for each year of data that you consider. We are using data from five separate years in order to obtain five models for each predictor for meta analysis.
  2. Document your regression results in a table showing the model coefficient (b1), R2, p-value, and confidence interval of the slope.
  3. Perform a meta analysis (using the "Single r" tab in the Excel-based ESCI Meta Analysis tool - available as a free download) of each predictor using the five year mod- els. Include the "synthesis forest plot, synthesized confidence interval, and associated p-value in your report for each predictor you study.
  4. Use your results to select six predictors that you think are the "best," and moti- vate your choices. Discuss the requirements for regression (linearity, normality, ho- moskedasticity, and independence) for each and include scatterplots for each of the six predictors you select.

Sample Solution