{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

lec36v1_1up

# lec36v1_1up - Stat 104 Quantitative Methods for Economists...

This preview shows pages 1–8. Sign up to view the full content.

Stat 104: Quantitative Methods for Economists Class 36: Logistic Regression 1

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
What is logistic regression? square4 There are many important research topics for which the dependent variable is "limited." square4 For example: voting, morbidity or mortality, and participation data is not continuous or distributed normally. square4 Binary logistic regression is a type of regression analysis where the dependent variable is a dummy variable: coded 0 (did not vote) or 1(did vote)
Overview of categorical regression models Binary: Two categories square4 vote in last election? square4 patient cured after treatment? square4 startup failed? Ordinal: More than two categories and assume ordered square4 not favorable, favorable, extremely favorable square4 not likely, likely, very likely square4 no coverage, partial coverage, maximum coverage in insurance Nominal: More than two categories but not ordered square4 mode of transportation – bus, car or train? square4 employment status – employed, unemployed, out of work force Count: Number of times something has happened square4 number of patents a company has attained square4 number of times a country goes to war 3

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Y x x k k = + + + + β β β ε 0 1 1 L In the usual regression model set-up, we assume that Y is a linear function of k X variables, plus some random noise: Another way of stating this is E Y x x k k ( ) = + + + β β β 0 1 1 L 4
Now regression works fine and well if Y is continuous (or nearly so), but things can go wrong if Y is discrete. A special case is when Y takes on only the values 0 or 1. For a 0,1 random variable Y, we have that E Y P Y P Y ( ) ( ) ( ) = = + = 0 0 1 1 Thus for a 0,1 random variable Y E Y P Y ( ) ( ) = = 1 5

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
P Y x x k k ( ) = = + + + 1 0 1 1 β β β L If we use regression as we know it to model a 0,1, variable, our model is modeling This is sometimes called a “linear probability model” Why may this be a bad idea ? What do we know about probabilities, i.e. what values can they take on ? 6
Example: Failing or Passing an Exam square6 Let us define a variable ‘Outcome’ boxshadowdwn Outcome = 0 if the individual fails the exam = 1 if the individual passes the exam square6 We can reasonably assume that Failing or Passing an exam depends on the quantity of hours we use to study

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}