pdAllBalanced¶

Purpose¶

Checks if a panel dataset is strongly balanced and returns 1 if balanced, 0 otherwise.

Format¶

isBalanced = pdAllBalanced(df[, groupvar, datevar])¶

Parameters:

df (Dataframe) – Contains long-form panel data with \(N_i \times T_i\) rows and K columns.
groupvar (String) – Optional, specifies the name of the variable used to identify group membership for panel observations. Defaults to the first categorical or string variable in the dataframe.
datevar (String) – Optional, specifies the name of the variable used to identify dates for panel observations. Defaults to the first date variable in the dataframe.

Returns:

isBalanced (Scalar) – Indicates if the panel dataset is balanced. Returns 1 if balanced, 0 otherwise.

Examples¶

If your group variable is the first categorical variable in your dataframe and the date variable is a GAUSS date variable and not just a numeric column, you can just pass in the panel dataframe and GAUSS will locate the group and date variables for you.

// Import data
fname = getGAUSSHome("examples/pd_ab.gdat");
pd_ab = loadd(fname);

// Take a small sample for the example
pd_smpl = pd_ab[1:4 8:11,.];

// Print our sample
print pd_smpl;

id        year        emp       wage
1977-01-01     5.0410    13.1516
1978-01-01     5.6000    12.3018
1979-01-01     5.0150    12.8395
1980-01-01     4.7150    13.8039
1977-01-01    71.3190    14.7909
1978-01-01    70.6430    14.1036
1979-01-01    70.9180    14.9534
1980-01-01    72.0310    15.4910

// Check to see if the panel is balanced
is_balanced = pdallbalanced(pd_smpl);

print is_balanced;

The above code will return:

1.000

Remarks¶

This function takes long-form panel data. To transform wide data to long-form data see dfLonger().

This function assumes panel is sorted by group and date. Note that panel data can be sorted using pdSort().

A strongly balanced panel dataset contains the same time points for each group. pdAllBalanced() examines the provided dataset to determine if it meets this condition.

If groupvar is not provided, the function defaults to the first categorical or string variable in the dataframe.
If datevar is not provided, the function defaults to the first date variable in the dataframe.

For datasets that are not strongly balanced, pdAllBalanced() returns 0.