Page 31 - FINAL CFA II SLIDES JUNE 2019 DAY 3

LOS 8.m: Describe how model misspecification affects READING 8: MULTIPLE REGRESSION AND ISSUES IN REGRESSION ANALYSIS
the results of a regression analysis and describe how to
avoid common forms of misspecification – 3 Types! MODULE 8.9: MODEL MISSPECIFICATION, & QUALITATIVE DEPENDENT VARIABLES

1.The functional form can be mis-specified:
1. Important variables are omitted.
2. Variables should be transformed.
3. Data is improperly pooled.

2. Explanatory variables are correlated with the error term in time series models.
1. A lagged dependent variable is used as an independent variable.
2. A function of the dependent variable is used as an independent variable (“forecasting the past”).
3. Independent variables are measured with error.

3. Other time-series misspecifications that result in non-stationarity.

The effects of the model misspecification are basically the same for all misspecifications.

Recall from CFA I:

• Unbiased estimator: EV of estimator = parameter you are trying to estimate.

• Consistent estimator: Accuracy of the parameter increases as n increases.