L21 & L22 Social Science Statistics
By the end of lesson 21, you should be able to:
- Create a scatterplot of bivariate data.
- Interpret the overall pattern in a scatter plot to assess linearity and direction.
- Calculate the correlation coefficient.
- Interpret the correlation coefficient, , as a measure of strength and direction of a linear relationship between two variables.
REMEMBER:
> What we want to predict or estimate = (y) response variable (the dependent variable)
> What we use to make that prediction = (x) explanatory variable (the independent variable)
What to look for on a Scatterplot:
- Form (Linear vs. Nonlinear)
- Direction (Positive or Negative) When positive, x and y move together, both increasing or both decreasing. When negative, x and y move opposite
- Strength (Weak, Moderate, Strong)
> Values close to 1 indicate a strong positive association
> Values close to -1 indicate a strong negative association
> Values close to 0 indicate a weak or no linear association
- Correlation can only be computed for two quanitative variables
- Use rho (soft curve p) for population correlation and r = sample correlation
- Correlation is always between -1 and positive 1 ( for samples -1 < r < 1)
- The sign on correlation only indicates the direction, not the strength
- Strength is determined by how close the absolute value is to 1
- Changing the unit of measurment for x or y or both will not change the correlation
By the end of lesson 22, you should be able to:
- Identify the explanatory and response variable in a study.
- Calculate the slope and intercept of a regression model.
- Interpret the slope of the regression model.
- Make predictions using a regression model
REMEMBER:
>Correlation measures the strength and direction of the linear relationship between x and y
Comments
Post a Comment