OPER1135 Lecture Notes - Lecture 18: Scatter Plot, Statistical Hypothesis Testing, Descriptive Statistics

• School: Boston College
• Department: Operations Management
• Course: OPER1135
• Professor: Stephanie Jernigan

Document Summary

Steps when doing a regression: gather descriptive statistics on each variable, make a scatter plot of the variables, run regression in excel. Independence (if we don"t have this there may be some explanatory factor our model is not considering) Evaluate the quality/strength of the model with r2: interpret model: especially the slope. How significant is the relationship between x and y: we want to know if our model is valid and useful. So far we have r2 as our measure: we can check for significance at the coefficient level and at the model level. In simple linear regression they are the same thing since there is only one variable. How significant is the coefficient: for the slope, the t-test is effectively a hypothesis test: To get an estimate of the true slope based on our sample: we can use the same techniques that we used for forming confidence intervals and doing hypothesis tests.