## (EViews10) Panel Data Descriptive Analysis (Bar Charts) : CrunchEconometrix

Why do you want to perform panel data analysis?

Some of the reasons could be to explore the behaviour of a variable across a sample of groups (e.g. firms, schools, countries, agro produce, individuals, cars, production style, political parties etc.); to explore the behaviour of the groups in the sample with respect to a variable; the groups have some semblance of commonness; the groups have varying heterogeneities (i.e. differences) with respect to a variable; perhaps due to inadequate data over a long period for your sample or maybe you just don’t know why! (lol).

I give 5 tips required for building an engaging panel data structure. They are (1) generate identifiers (watch my video on “Reshape Wide to Longitudinal Data”); (2) reshape the data (watch my video on “Reshape Wide to Longitudinal Data”); (3) group classification (to explore the heterogeneities in the data); (4) categorise the outcome variable (to explore the heterogeneities in the data) and (5) create dummy variables (regional and time dummies).

erogeneities within and among the groups with the summary statistics of the outcome variable (Gini coefficient) and the different categorical variables such as countries, regions, income groups and inequality categories. Remember, graphics convey lots of information than words. So, load your data and let’s get started.

[Watch video tutorial]

## (EViews10) Estimate and Interpret VECM (2) : CrunchEconometrix

So, what do you understand by vector error correction model (VECM)?

You may say any of the following: that it is a system having a vector of two or more variables;

that all the variables in a VECM are endogenous; there are no exogenous variables;

VECM is constructed only if the variables are cointegrated; cointegration implies evidence of a long-run relationship among the variables;

it is a restricted VAR model with cointegrating restrictions built into the specification;

constructed to examine long- and short-run dynamics of the cointegrated series;

restricts the long-run behaviour of endogenous variables to converge to their cointegrating relationships;

that the cointegrating term is known as the error correction term;

it is a representation of cointegrated VAR (courtesy of Granger’s representation theorem) and that the resulting VAR from VECM representation has more efficient coefficient estimates.

Also, note that VAR specified in differences is a mis-specification while VECM is obtained by differencing a VAR, hence losing a lag. So, you construct a VECM with a (p-1) lag lengths for all the variables in the system.

These are the basic steps required to estimating a VECM. (1) series must be stationary (integrated of same order); (2) determine optimal lag length for the model; (3) perform Johansen cointegration test; (4) if there is no cointegration, estimate the unrestricted VAR model; (5) but if there is cointegration, then specify the restricted VAR model (i.e. VECM).

[Here is the video clip for the tutorial]

## (EViews10) Estimate and Interpret VECM (1) : CrunchEconometrix

So, what do you understand by vector error correction model (VECM)?

You may say any of the following: that it is a system having a vector of two or more variables;

that all the variables in a VECM are endogenous; there are no exogenous variables;

VECM is constructed only if the variables are cointegrated; cointegration implies evidence of a long-run relationship among the variables;

it is a restricted VAR model with cointegrating restrictions built into the specification;

constructed to examine long- and short-run dynamics of the cointegrated series;

restricts the long-run behaviour of endogenous variables to converge to their cointegrating relationships;

that the cointegrating term is known as the error correction term;

it is a representation of cointegrated VAR (courtesy of Granger’s representation theorem) and that the resulting VAR from VECM representation has more efficient coefficient estimates.

Also, note that VAR specified in differences is a mis-specification while VECM is obtained by differencing a VAR, hence losing a lag. So, you construct a VECM with a (p-1) lag lengths for all the variables in the system.

These are the basic steps required to estimating a VECM. (1) series must be stationary (integrated of same order); (2) determine optimal lag length for the model; (3) perform Johansen cointegration test; (4) if there is no cointegration, estimate the unrestricted VAR model; (5) but if there is cointegration, then specify the restricted VAR model (i.e. VECM).

[Here is the video clip for the tutorial]