Logistic Regression & Probit Regression by SPSS
I. Logistic regression
A. Extension of multiple regression but the dv is categorical
B. Value being predicted represents a probability, and it varies between 0 and 1
C. Possible to use categorical ivs (dummy coded, but won’t here)
D. Key concept: logit
1. natural logarithm (ln) of the odds
2.
3. Therefore, prob success + ? + + + +
E. SPS
were checked. Finally, fitness of model was examined by deciding whether the price of the car can be explained by each variance.
1.4. Selection of potentially relevant variables [unit]
The Variables below are what we choose we think of as the factors determining the price of the cars.
a) Response variable(Y): the selling price of the car [ten thousand won]
b) Predict variables(X)
What is the problem?
Man’s growing energy demands
Supply of oil depends on
- Rates of extraction
- Endowment in Nature
- Economic and political factors
Propose of the project
Endowment in Nature
- Prediction of oil exhaustion
Rates of extraction
- Drilling cost and Depth
Why?
Increases with a resulting increase in
rig capacity
Changes in the rate of penetration.
Research Purpose
Nowadays, there are many different models of cars and their prices range.
We want to know what the factors are which affect the selling price of the car and how much each variable explains the selling price.
Research Process
To determine if there is a correlation between various factors and the selling price of the car, the multiple linear regression model was used
Determination of Won/USD Exchange Rate With Respect to Global Oil Price Change
To see the relationship between exchange rate and oil price, we use econometrical methodology, multiple regression. Our regression model is this:
s_t=β_1+β_2 (m_t-m_t^* )+β_3 (y_t-y_t^* )+β_4 〖lroil〗_t+u_t
*Explanation about explanatory variable
s_t : Nominal exchange rate (USD/Won)
m_t-m_t^*