Cross-Sectional data

[Flipster]

Hello!
I am running a regression for a paper and I am dealing with cross-sectional data. I have one year and am only interested in the changes that year and I am using Eviews 9. My question is if anyone has a list of tests one should run for cross-sectional data, or problems that may arise. I'm asking because I realize that there should not be any issues regarding change over time. I'm very new to Eviews, please be patient with me. Best, Flipster

[EViews Mirza]

Testing for changes can take on several forms, but the most popular are break-point changes. The simplest among them is the Chow test if you know (suspect) and can specify where in the data the breakpoint happens. Alternatively, the more complicated ones are the Quandt-Andrews test and the Multiple Breakpoint Tests where you don't know the exact location of the start of the instability and the algorithm produces a list of potential breakpoints with an indication of those most likely to have happened.

Either way, you can get to these by estimating your regression, going to View then Stability Diagnostics.

[startz]

Testing for changes can take on several forms, but the most popular are break-point changes. The simplest among them is the Chow test if you know (suspect) and can specify where in the data the breakpoint happens. Alternatively, the more complicated ones are the Quandt-Andrews test and the Multiple Breakpoint Tests where you don't know the exact location of the start of the instability and the algorithm produces a list of potential breakpoints with an indication of those most likely to have happened.

Either way, you can get to these by estimating your regression, going to View then Stability Diagnostics.

These tests are generally only used for time series data, and probably don't apply here.

[EViews Mirza]

These tests are generally only used for time series data, and probably don't apply here.

Not entirely true. Suppose I have cross sectional data with dummies on males and females. A Chow test could be used to test whether a parameter of interest is different between these two groups.

[EViews Gareth]

In EViews a non-time based Chow test is called a Factor Breakpoint test.