Question

For the following scenario, please identify the most appropriate statistical method to use. Additionally, describe why it is the most appropriate.

Family caregiving of older adults is more common in Korea than in the United States.  A recent study assessed 100 caregivers of older adults with dementia in Seoul, South Korea.  The dependent variable was caregiver burden as measured by the Korean Burden Inventory (KBI).  The KBI is a score which ranged from 28 to 140, with higher scores indicating higher burden.  Additional explanatory variables were indexes that measured a) total activities of daily living (a low score indicates that the elderly perform activities independent), b) memory and behavioral problems (higher scores indicate more problems), and c) cognitive impairment (lower scores indicate a greater degree of cognitive impairment.  The goal of the statistical analysis was to predict the KBI based on the explanatory variables.

Answer 1

The appropriate statistical method to use in this scenario would be linear regression. We can take KBI score as our dependent variable, that is the variable which will depend on explanatory variables. We can use these explanatory variables to regress over KBI score and the function thus can be used to predict values based on explanatory variables. This is most appropriate because our score does not depend on time, so we don't need time series analysis and this method helps in prediction. Also since the relation of explanatory variables with KBI score is linear (as explained in question for each variable, the higher value for one gives higher or lower value for KBI score), linear regression would be appropriate.