Direction of Bias in OLS when using Instrumental Variables

[Carys Wright]

Hi all,

Just a general question:

If when using an instrumental variable it increases the size of the coefficient and changes the direction of the relationship compared to OLS --> what direction of bias does it suggest in the OLS estimate?

For example in standard OLS the coefficient is -3.319 and when instrumenting a proxy for this variable, it changes the coefficient to --> 192.

What direction of bias do you call the standard OLS estimate?

Many thanks,
Carys

[Phil Bromiley]

It was a negative bias - the estimated parameter with OLS was below the consistently estimated parameter.