Saba: As long as the underlying assumptions implicit to regression analysis are met either directly or following an appropriate transformation, linear regression, linear multiple regression, and different types of non-linear regression can be performed for a wide range of data types. The key is to not conclude that a tight association (high R^2 or low residual sum squared deviation) is necessarily analogous to causation. For example, height expressed in units of cms regressed against height expressed in units of inches will produce a regression with R^2 = 1.0, aside from rounding errors, but this particularly regression does not improve knowledge as to the underlying bases for height comparing individuals.
In simple linear regression a single independent variable is used to predict the value of a dependent variable. In multiple linear regression two or more independent variables are used to predict the value of a dependent variable. The difference between the two is the number of independent variables.
Saba: As long as the underlying assumptions implicit to regression analysis are met either directly or following an appropriate transformation, linear regression, linear multiple regression, and different types of non-linear regression can be performed for a wide range of data types. The key is to not conclude that a tight association (high R^2 or low residual sum squared deviation) is necessarily analogous to causation. For example, height expressed in units of cms regressed against height expressed in units of inches will produce a regression with R^2 = 1.0, aside from rounding errors, but this particularly regression does not improve knowledge as to the underlying bases for height comparing individuals.
In simple linear regression a single independent variable is used to predict the value of a dependent variable. In multiple linear regression two or more independent variables are used to predict the value of a dependent variable. It depends on hypothesis which method can be used.
Regression can be used in medical statistics as it determine the dependency of 1 factor(Variable) on other factor.. In linear regression, it tell us about how smoothly they depend on each other, For example, unit increase in sugar intake leads to unit increase in insulin secretion in normal human being and it will shows a linear trend.... But in case of a diabetic patient ,there will not be a linear trend...as sometimes patient pancreas doesn't make any insulin or doesn't make enough or the insulin it makes doesn't work properly. thus it makes curve then u use multiple regression like Gaussian etc....
Hope it clarifies..
- Badges
- Science topic
- Similar topics
- Medicine