Stata Software - Science topic

Good morning Sir Florian Schütze

Thank you very much for your reply/comment.

I have visited there. I found video for PLFS and NSS but did not get for ASI.

From MoSPI microdata catalog, I have downloaded data but unable to get specific variables' quantity. Variables Like, no. of firms and operated firms, I have get. But I am unable to get fixed capital, input, output and other variables. I merged two blocks and applied formula but perhaps there is some mistake. So I am not getting values.

->!

Hello ,

Thank you for the suggestion. I will definitely reach out to Ben Jann and the Statalist community for further assistance. I appreciate the advice on checking the FAQ for tips on how to craft my question.

Because the software are different.

You can simply start the graph editor and change the textbox properties by double-clicking on the corresponding study. As an alternative, you can also add superscript by changing the label of the corresponding study identifier using "replace" and update the meta settings ("meta update"). The study identifier of the Forest plot ("meta forestplot") should then also adopt the changed label.

The graph you uploaded, and the code to produce it can be found on this page:

sysuse auto, clear

quietly regress price mpg trunk length turn if foreign==0

estimates store D

quietly regress price mpg trunk length turn if foreign==1

estimates store F

quietly regress weight mpg trunk length turn if foreign==0

estimates store D_weight

quietly regress weight mpg trunk length turn if foreign==1

estimates store F_weight

coefplot (D, label(Domestic)) (F, label(Foreign)), bylabel(Price) ///

|| (D_weight) (F_weight), bylabel(Weight) ///

||, drop(_cons) xline(0) byopts(xrescale) // scheme(s2color)

To get the same graphics scheme shown on the web page, remove the // before scheme(s2color). If you use the default graphics scheme for Stata 18 (the current version), the graph will look like the one I attached.

I addressed this by setting my data as Panel Mixed Logit Data

Hello Giuseppe Dario Testa. What version of Stata do you have? I ask, because if it is recent enough (v16 or later, IIRC), it will have a suite of new (official) meta-analysis commands, including this one:

PS- I recommend posting questions about how to do X using Stata to Statalist. If you do decide to post there in future, see the very helpful FAQ first.

I received a ling from @Tim Huegerich in Stata blog

https://blog.stata.com/2020/11/05/stata-python-integration-part-8-using-the-stata-function-interface-to-copy-data-from-stata-to-python/

One of the widely used and highly regarded software for conducting meta-analysis is Comprehensive Meta-Analysis (CMA). CMA provides a user-friendly interface, extensive statistical tools, and a comprehensive set of features for conducting meta-analyses across various research domains. Other popular options include RevMan (Review Manager) and Metafor in R, depending on user preferences and familiarity with specific programming languages. Ultimately, the "best" software may depend on the specific needs of the user, the nature of the meta-analysis, and individual preferences regarding interface and functionality.

Chuck A Arize May you kindly share the name of the package/ command ? Thank you so much

You may use this example: label define likertnew 0 “Strongly Agree” 1 “Agree” 2 “Disagree” 3 “Strongly Disagree”

Uzair Essa Kori, I repeat my earlier question, which you have not yet addressed: Why in the world did you not say clearly at the top of your post that it was generated using AI? Do you not think that would be the honest and ethical thing to do?

You need to download the community-contributed command "factortest".

You do this by issuing the command

. ssc install factortest

Then read the help file.

It's all there in the manual.

R in Power BI ?

It should not contain complex R syntaxes though.

https://learn.microsoft.com/en-us/power-bi/create-reports/desktop-r-visuals

@Dr.Arize. Thanks for sharing the paper. But, I couldn't find any codes on it. Thanks

SPSS, as my results necessitate analysis using SPSS

Dear Jan,

OK ! I see ! you need to create the spatial weight matrix indeed !

There are many possibilities in R:

I strongly advise to work with sf because it so easier now !

but spdp may still be clearly adaptated to you context :

This is one of the definitive books on the subject in R:

with the book :

there are other references but they are more geospatial (point process) oriented.

Here you should use one of those packages and that nb2mat from package spdp might do the trick !

All the best.

Franck.

Panel data regression, also known as fixed-effects regression, is a statistical method used to analyze data that vary over both time and cross-sectional units. This method is appropriate for data where we have repeated observations of the same individuals, firms, or countries over time.

In fixed-effects regression, we control for time-invariant differences across cross-sectional units by including individual-specific effects as fixed effects in the regression model. This helps to remove any confounding factors that might affect the dependent variable but do not vary over time.

To format panel data for STATA, you need to use the "reshape" command to convert the data from a wide format to a long format. The long format has one row per observation and includes variables for the individual or entity ID, the time period, and the dependent and independent variables.

send your article to : editor@ijmhc.com

Just to be clear : as Ma'Mon Abu Hammad states plainly, Stata is commercial software, made with care and professionalism by people who do this for a living. Downloading bootleg copies is stealing.

Just saying.

Chuck better than what? David Booth

Any new suggestion?

Would you please tell us, how did you calculate nri and idi in stata?

This should help

Maybe the attached is what you mean. David Booth

Jane C. Holland – mea culpa! I should have read my own code. Bruce Weaver was correct : foreach var of varlist is what I should have written. Somehow I glitched and wrote foreach var of var of varlist…

sir, i am doing research on labour market discrimination. help me to perform decomposition in unite level cross-section data.

encode (Var), gen (countryID)

من الممكن استخدام معادلة الارتباط اذا اردنا معرفة العلاقة الارتباطية بين النموذجين من جهة ومن جهة اخرى اذا اردنا معرفة الفروق بين النموذجين نستخدم معادلة ف-فثشسف

As far system Gmm is concerned, Hansen J is superior to sargan test and it will even give a better result if robust option specified.

Hello Moses Festo Towongo. IMO, one is usually much better off posting questions about how to do X with some stats package to a discussion forum for users of that stats package. In this case, I recommend that you post your question to Statalist (first link below). Before posting, please take a look at the excellent advice on how to post to Statalist in the FAQ (second link).

HTH.

There are three main approaches for doing latent interactions.

Approaches 1 and 3 can be readily implemented using Stata's SEM. Approach 2 is not supported by Stata. Mplus supports LMS as Mehmet says, which falls into this category. But note that distributional analytic approaches are sensitive to normality assumption of the latent variable. This assumption is untestable and therefore I personally always prefer to go for product indicators.

I cover all these approaches on my doctoral level course. You can find explanations here: https://www.youtube.com/watch?v=Ibv10E_WRYM&list=PL6tc6IBlZmOU_R1Ezb1WShAmLAuCVwF4S

(Note that at the time of writing I have not uploaded the interaction videos but will do that in the near future.)

You are so much welcome Dr. Addisu Tesfaw Zinabu.

Hello Amy,

If the Labor Survey is conducted with a "fresh" sample each year, rather than as a longitudinal study, then each year's data set may (and should) be treated as independent. If longitudinal, most long-term surveys with which I've worked do assign unique iD tags to each case and carry these forward, so that one may match responses across time.

Given the sample sizes, there's no apparent loss to treating each year's results as a stand-alone batch for purposes of investigating your model. If there are temporal events that could account for differences in variable values (e.g., pre-pandemic, post-pandemic; pre-recession of 2008, post-recession of 2008), this would argue against merging data sets across years.

You may certainly test whether model parameters are constant across years (for example, as a multi-group model in path/sem).

Good luck with your work.

One more time you don't need to linearize anything it's the regression coefficients that matter. Please read the Kutner book it's a free download from the z-library. David Booth

Hello, I reccomend to follow the guidelines provided by Tripton and Shuster, (2017), to perform a meta-analysis of bland-altman studies.

Hello Seyyed,

I guess you mean with beta the factor loading? Traditionally, these are denoted with lambda but probably, Stata treats these differently.

The fixation of the "marker variable" is needed a) to assign a metric to the latent variable--those of the marker, and to b) identify the equation system.

As far as I know it does not matter which variable you choose unless it is no valid indicator of the latent.

HTH

Holger

Stata

Yes

Hi,

I find a pdf.

Testing for unit roots is also of high importance when we have to deal with panel data. In the panel unit root test framework, two generations of tests have been developed. The first generation contains the Levin, Lin and Chu test (2002), Im, Pesaran and Shin test (2003) and Fisher -type tests, whose main limit is the assumption of cross-sectional independence across units. A second generation of tests that rejects the cross-sectional independence hypothesis also exist. Within this second generation of tests, two main approaches can be distinguished: the covariance restrictions approach, adopted by Chang (2002, 2004), and the factor structure approach, including contributions by Phillips and Sul (2003), Moon and Perron (2004), Choi (2002) and Pesaran (2003).

Most econometric packages incl. Stata contain the first generation tests. However, some of them (eg. the Levin-Lin-Chiu test) require strongly balanced data (namely not to have missing values). So, you proceed with the rest tests without any problem.

Cheers!

Dimitris

Good Luck.

Ronán Michael Conroy sir,

Thank you for sharing the article. Will go through it.

with stata you can click on time series -----ARCH/GARCH-------Nelson Egarch model

you fill in the dependent and independent variables

if you want to add variables in the equation of the mean you have to go to model 2

If you want to add variables in the variance equation you have to go to model 3

You may want to deepen you understanding of multilevel random coefficient models by using the resources given here:

and

it includes instructions for Stata

Modules

Kindly see also the following useful RG link:

Before we talk about your model what did you choose to setup like that as opposed to:

Responsiveness of Child with 3 levels (High (3), Mid (2), Low (0))

This way you can look at the effect of Responsiveness and then break it down by individual level and compare.

Dear Ngoni Chipere,

I would rather recommend you the employment of a rank-orderen logstic regression.

For technical implementation in STATA you can use the following Stata-Manual

With best wishes,

Richard

Hi,

Which statistical methodology do you plan to fit? For this, is it possible to fit the model in SPSS or STATA? If possible in both, you can use the software you prefer more, your preference may be the way output is displayed or the software you know more about. If impossible in both, use the one that can fit your model. For example, if you need to fit the parametric survival models, you can't fit through SPSS. So, you must go to use STATA.

Hi,

Some links:

Volume 4 Number 3  >>  st0071

The Stata Journal Volume 4 Number 3: pp. 282-289

Maximum likelihood estimation of endogenous switching regression models

This article may be of use to you

Use a program spss to access the appropriate analysis

use the SPSS program to analyze your data

Furkan Oral

These articles might be an asset, have a look:

1. https://www.adb.org/sites/default/files/publication/609476/small-area-estimation-guide-nsos.pdf

2. https://ec.europa.eu/eurostat/cros/system/files/Lesson1_SAE%20EMOSschool_last.pdf

3. https://unstats.un.org/sdgs/files/meetings/sdg-inter-workshop-jan-2019/Session%207.c.1_Country%20Presentation%20Thailand.pdf

4.

5. http://doc.ukdataservice.ac.uk/doc/6792/mrdoc/pdf/6792_small_area_estimation_using_esds_government_surveys.pdf

Alem Redda that’s why they are called independent

If your interest is in linear trend, then plot x-axis as year and Y-axis as % of patients then calculate the trend and identify slope values.

Rearrange the data monthly and you may repeat the same monthly-wise.

Then you will have 10 slopes values for both sets ..then attempt t-test based on slope. if you have subject details maybe you can calculate subject-wise slope as well.

best!!

Can you use a different software? Is that an option?

this is an excellent resource with code and videos for panel models and many others:

Dear All,

I have worked on this and written codes below for estimating marginal effect after MVPROBIT. I hope this will be useful. *Example data use http://www.stata-press.com/data/r7/school.dta, clear *Step 1: Running the MV probit model mvprobit (private = years logptax loginc) (vote = years logptax loginc)

*Step 2: Post estimation command to estimate Predictions from multivariate probit models estimated by SML mvppred pred_xb, xb *Step 3" Generate coeefiencts for each binay category gen Coef_years_private = -.0089447 gen Coef_logptax_private =-.1018381 gen Coef_loginc_private =.3787381 gen Coef_years_vote = -.0160871 gen Coef_logptax_vote =-1.260877 gen Coef_loginc_vote =.9744685 *Step 4: Calculating Marginal effect using (Coefficients and linear Predictions) gen ME_years_private =normalden(pred_xb1)*Coef_years_private gen ME_logpatx_private =normalden(pred_xb1)*Coef_logptax_private gen ME_loginc_private =normalden(pred_xb1)*Coef_loginc_private gen ME_years_vote =normalden(pred_xb1)*Coef_years_vote gen ME_logpatx_vote =normalden(pred_xb1)*Coef_logptax_vote gen ME_loginc_vote =normalden(pred_xb1)*Coef_loginc_vote *Step 5 After estimating the ME for each observation we can get the mean using the summarize or mean command.

The final say is your theory. If you got the fitting model it would be fine despite having some issues in construct validity primarily if you're developing a new theory or measure (see Netemeyer et al., 2003 or other relevant sources)

It can also be helpful to use the Stata command

.set trace on

which will echo the progress of the program on your screen. You can see what it was doing immediately before it issued the error message.

Path models like this are most effectively and efficiently estimated within specialized software such as R (lavaan), which is free, or commercial SEM packages such as Mplus. SEM software allows you to estimate the model as a whole (using path analysis), examine global and local model fit statistics, and test the effects of interest for statistical significance using the most appropriate techniques such as e.g. bootstrapped confidence intervals for mediated effects.

The resolution to your argument is an empirical issue. If there is relatively little variation in then loadings, then adding them will be adequate because it assigns equal weights to each variable.

FYI equal weights is the assumption with coefficient alpha, so a high alpha (say .80 and above) would suggest that simply add the variables would be adequate. Also, averaging simply divides by a constant, so it just makes the results more interpretable.

STATA or RStata

Hi Louie! You can find what you need on Kenneth Train's website, in my opinion, he is the main reference on this topic. I leave you this link to his book, I recommend especially chapter six.

All the best in your work!

I am working in R with the package DCchoice, I am using the double bounded dichotomous choice method. However, I don't know how to analyse the result from the logit model.

For example, the coefficient of income is 0.002, then if income increase 1, the log(odd) will increase 0.002? or the probability of saying yes is increasing 0.002?

Also in double bounded , it 's more difficult because it's YES YES, NO No, No Yes, Yes No...

ANyone help me?