In: Statistics and Probability
Suppose you are interested in understanding the causal impact of having an MBA (versus just an undergraduate degree in business) on earnings. To this end, you estimate a regression of the following form:
EARNINGS = 55679 + 27809(MBA)
The estimated coefficient above suggests that individuals with an MBA earn $27,809 more than those with just a business undergraduate, on average. Give an example of how omitted variable bias might impact this estimate
Let us take an example to understand this problem.
Let us assume that a person wants to buy a house and hence he decided to find out the factors tht determine the price of the houses in his area. He looked into each factor that could result in the difference of price between two houses. He included factors like number of rooms in the house, the number of bathrooms, whether the house is furnished or not, and how old the house is. But he forgot to include a very important variable – the size of the house in square feet. If he performs regression, then he would definitely get biased results. Two houses with exactly similar values of the variables he had taken can have drastically different prices if the size of the house (or say the size of the room) is different. In missing this important variable, his regression suffers from Omitted Variable Bias.
In the same way if any of the factors affecting the earnings of an MBA is omitted, then the results would be biased.