Heteroscedasticity in SPSS – Uji Asumsi Klasik Heteroskedastisitas di SPSS

Heteroscedasticity in SPSS

Hi! One of the test for CLRM assumption is Heteroscedasticity. Testing it in E-views or Stata for Time-Series or Panel data is easy because the software provides the command. You just need to click this and that, then the heteroscedasticity will be out. However, testing it under SPSS software (perhaps cross-sectional data) it needs a work.

Below is the process to run it. Note that you need to copy paste the macro syntax below to run it. We use Breusch-Pagan and Koenker Test for it. The procedure is as follow: Continue reading

Running Panel Logistic Regression (STATA)

In accounting and finance (and indeed in other research areas too), there is a possibility for having a categorical dependent variable. For instance, research in auditor opinion or efficiency or board size determinants makes our dependent variable to be binary. However, we are afraid that there is no variance in our categorical dependent variables due to our panel data set. Then the question is “Can we run panel logistic regression?”

By far, my answer is still yes. Indeed, there is possibility of estimation bias due to the variance and standard errors post-estimation. So, how can we run panel logistic regression? Continue reading

How to transpose your rich data into panel (Data Stacking / Transpose)

If you are in finance research area, and you are using panel data, the most annoying part is stacking/transpose your time series into panel data. Hereby, I give you the macros in excel (even though I know many software such Tableau can do it faster) to do in a click.

Yet, when you want to run it, adjust it with the number of your column. Mine is 6, and the data that has to be stacked/transposed is from column 2. Therefore, the i = 2 to 6.

Happy trying

Copy paste this to your macros (open your excel –> view –> macros –>view macros –> create –> copy paste –> run)

Continue reading

Why You should attend Statistical / Econometrics Class before Mastering a Software

I just read comments from 2 reviewers of a journal. The first reviewer gives a minor correction because of English editing, copy editing, and elaboration in the discussion section. The first reviewer gives good comments too, for instance, we have to have another robustness test, which is a very good idea to make our paper better. The second reviewer gives a rejection because two issues. First, he/she suspect we just wrote down the R-Square (R2) before running the factor analysis. I just stunned, and read it again and again. R2 from factor analysis? Second issue is about the data collection. He/she addresses our manuscript is too weak as it does not mention the philosophical data collection. I was confused that time thinking what the reviewer means by philosophical data collection. After reading it again, reviewer mentions that I have to write down, not only whether we adopt or adapt the items of questionnaire, but also the grounded theory of the data collection and the phenomenological of items construction. I was very surprised because actually grounded theory data collection and phenomenological are qualitative approach which is totally different view from our approach which is quantitative method. I just smile facing this type of reviewing process. But it makes me think what the root of this “evil” is. Why nowadays people are good in click-click the software interface but fail in understanding comprehensively the statistic. Continue reading