{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

Lecture+4+Assess+regression+studies

# Lecture+4+Assess+regression+studies - Internalvalidity...

This preview shows pages 1–2. Sign up to view the full content.

1 Lecture 4 Assessing regression studies Two criteria in evaluating regression studies: Internal validity Whether the estimated causal relationship is valid for the sample being studied. External validity Whether the estimated relationship can be generalized from the population and setting studied to other populations (samples) and settings, where the “setting” refers to the legal, policy, and physical environment and related salient features. It depends on whether the sample of data used in estimation is representative of other samples. Five threats to internal validity: Omitted variable bias (already discussed ) Wrong functional form (already discussed) Measurement Error (Errors‐in‐variables) bias Sample selection bias Simultaneous causality bias Measurement Error Sometimes we have the variable we want, but we think it is measured with error. Examples : A survey asks your income last year, how much alcohol you drunk for the last month, or whether you use marijuana last month. Sometimes we don’t have the variable we want, but we have a variable that’s closely related to it—a proxy variable Example: use standard test score such as Armed Forces Qualification Test (AFQT)or IQ test score to as a proxy for unobserved ability. The consequence of measurement error in Y is different from that in X’ s.

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 ]}

### Page1 / 4

Lecture+4+Assess+regression+studies - Internalvalidity...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online