วีดีโอ

@@manishakumari-tw7sp th-cam.com/video/Ug7vzUXGIQk/w-d-xo.htmlsi=xogJRfKAVfHP02fp Try this video, it should help coding. The analysis is explained in the other video on "fast analysis". Just scroll through my DCE playlist.

@@manishakumari-tw7sp for the analysis after restructuring th-cam.com/video/HBaFicxTiqI/w-d-xo.htmlsi=62bcJdErVcTWlkr6

@@eugenleo thank you sir

@@sameer2835 welcome!

Yes and no. I can make a video on Stata, but it will not help - the WTP is calculated in Excel. It is just a 'conversion' of one B value in anther one. So, you just need to copy the final table from Stata into Excel, and apply the formula. I am sure, I had a video on this in my DCE playlist. Good luck!

I have just amde a video on this. Enjoy: th-cam.com/video/LxbVIXNHZqY/w-d-xo.html

And here a small mistake correction: th-cam.com/video/QKBpbvA1TQU/w-d-xo.html

The difference is minimal - you will have to calculate the final_decision differently as you have the values 0, 1, 2 and not only 0 and 1. And restructuring second part- you will have 3 options seen, so put three variables in one category. Otherwise, all the same!

Sorry, both parts of restructuring need to be adapted. But the logic is the same.

@@eugenleo Thank you so much for your quick answer! This is really helpful. :) Am I right that we would need to do a multinomial logistic regression instead of a binary logistic regression in this case, because we have three possible values for final_decision?

No, the variable final_decision will be binary (1 - the want the option, 0 - they don't want it). So, it will be a binary logistic regression, I think.

I recorded a new video, explaining the process. Enjoy: th-cam.com/video/Ug7vzUXGIQk/w-d-xo.html

I encountered this issue newly - Qualtrics wanted to have SSL protocol activated (). It added an 's' to http and the link stopped working. So, I've bought an SSL from my hosting provider. Otherwise, it can be the issue of a typo in the address or similar. To check - try uploading a file to a different hosting. Alternatively, I had an issue with the free hosting - it add an advertisement to the link and only then forwards it to your php (zzz.com.ua made it last year). Qualtrics sees the wrong file then. Try a different hosting to check (you browser may block this pop-up, while Qualtrics cannot).

@@eugenleo Thanks. I'll see if there's another hosting option I can find besides the free one. I honestly don't get most of this stuff. New at Qualitrics and never done any coding. But I found a tab on my InfinityFree server for installing free Google Trust SSL certificate so I have a working https URL in browser. Qualtrics still returned no values but the raw data tab changed to "Web Service Error #60: SSL certificate problem: unable to get local issuer certificate". I'm guessing that's what I get for going with a free one.

@@gpupchurch17 no worries, you don't need any coding for this. In the worse case, send me your php file - I can try tomorrow if it works from my hosting.

Welcome! Watch 1-2 videos more - I sometimes make mistakes and refer to them in next videos. Enjoy!

I surely will. I am going to get addicted to this channel. @@eugenleo

Please watch the next video, as I made a mistake in this one. In the next, I explain why variables did not appear in the SPSS file ;)

And the option with php-file is actually easier to handle. Bit confusing because of the server, but later in the next stages.

Well... This is now a lot of manual work. Practically, you need to create a set of variables for each level within each attribute. It is what I show in the second part of the video. Then, you manually code them for each participant - has s/he seen the level - 1, if not - 0. These dummies will be your independent variables, and the decision - dependent. In the same way you code your dependent variable - if decision option selected - 1, if not - 0. I did it in this way once. It took a while but it is possible. For insurance, if all participants saw the same card - you can code dummies for all participants for this card. Good luck and be patient;)

You are very welcome! 😉

Welcome! Good luck with your study!

I hope I understand your question correctly: you want two compare two groups of responses, e.g. male vs female participants in their preferences (or whatever other "external" variable you can use). In this event, you just split the file based on your grouping variable. When splitting, you can select what should be done with the groups. Click "compare groups". However, your question can be also understood differently - that you want to create groups from DCE attributes and levels. In this event, I assume that you want to investigate moderation effects of one attribute for another one. If so, don't split the file. Add as you independent variables, e.g., attribute1, attribute2, and their interaction attribute1*attribute2. Pay attention that in order to investigate interaction of two attributes you will need to look at all possible interactions of all levels. It sounds complex but it is simple - just add all possible combinations of levels to analysis: attr1lvl1*attr2lvl1, attr1lvl1*attr2lvl2, ... attrNlvlN*attrKlvlK. If I did not understand your question, you can contact me with an explanation.

Thank you so much for your reply. Sorry for the confusing question. My idea is that I give out several choice sets for the respondents to make a choice. For example, Car 1: black, auto gear, $15k; Car 2: white, auto gear, $20k; Car 3: red, normal gear, $13k and so on. Finally, which set (car) or sets (cars) that I should suggest to my boss to produce or sell? The analysis show which attribute level is preferred. However, the combination of all good may be not good (for the customer or producer). Is it right that I can make the interaction of 3 attributes: (attri1 * attr2 * attri 3) by looking at all possible interactions of all levels of these 3 levels. Thank you for your help and your time.

@@user-dv5me2vf3l There are several things that you can show: 1. Look at the most preferred levels for each attribute and pull them to one object, e.g. red car, automatic gear, 15k. This would be the optimal way to show what are most desired aspects. 2. You can have interactions (if this was your theory). E.g. if the engine is not sufficiently powerful, an air conditionair might be useless. So, there might be interaction between two attributes. In this event, you show two objects: red car, automatic gear change, 45 kWh motor AND red car, mechanical gear change, 35kWh motor. Because of the interaction between attributes, these two objects will be "best" object to present to your boss. 3. You can also show, what is the value for each attribute (look for ma video on the willingness-to-trade calculation). Here you can show what should the final price be dependent on the object properties, e.g. red car, automatic gear change, 45kWh for 12,000EUR OR red car, automatic gear change, 35 kWh for 10,000, and so on. As soon as you have price/value, the number of optimal objects to suggest will grow. If something it less optimal - just sell it with a lower price tag. I hope it helps you present your results better. :)

Actually, SPSS is not good for this. We applied STATA. But you might be interested in this video which explains how to convert odds ratio to probability (th-cam.com/video/UaCB3AWOWtU/w-d-xo.html) or this video which explains how to convert odds ratio to confidence intervals (th-cam.com/video/G5sqDwiwm68/w-d-xo.htmlsi=W5c64U-96KWvChNa). Otherwise, you could run the data after restructuring in STATA (www.peretaberner.eu/how-to-estimate-and-interpret-marginal-effects-from-logit-model-with-stata/). Good luck!

Thank you so much@@eugenleo

As your question was good and indicated demand for marginal effects calculation, I developed a video for this. Enjoy: th-cam.com/video/5YqAgIiHRCM/w-d-xo.html

Thank you, pleasure to know it. Feel free to watch my video with the step-by-step analysis (very slow but with comments) and the recent with a plugin that makes analysis easier. I hope it helps.

@@eugenleo yes, i did look at it. My DCE had only 3 attributes with 3 levels each so it was more easy. But your videos are the best for anyone to just understand about DCE in general. Good job there, cheers.

Thank you, Richard. I did not get the question: do you mean, can you use the video to legitimise the method selection, or do you mean "orthogonal design"? If I got your question correctly, I would argue for the depth of information that you receive with a DCE as a good legitimation. An orthogonal design (at least how I understand it) can be tested with multiple between subject randomised experiments. Or you may look for Solomon Experimental Design that combines within and between designs in one. Yet, if it is not about legitimation but about explanation of what you show - this would work perfectly. You can show, for instance, all the attributes, levels, and their interaction. I hope I answered your question.

?

Welcome! Feel free to watch the other videos from the playlist ;)

Now, you are well equiped for a DCE ;)

Welcome! Don't forget to watch the next video - I made a mistake but corrected it afterwards. ;)

Hi! Unfortunately, I work very seldom with STATA. I think the biggest issue is the data preparation - you need to refromat the tables. If I were you, I would make all the restructuring in SPSS (if you install the software you get first month free). You save the final file as *.dta for Stata. Analysing data in STATA is not the problem at all afterward - you run the command 'logit final_decision attr1 attr2 (... for scalable attributes, in our example efficiency_gain) attr1lvl1 attr1lvl2 (...for other attributes)'. As in my videos (please watch the video on the fast analysis of a DCE) I code my attributes and levels as dummies, you can treat them as scalable variables. If you recode variables as categoricall/nominal, you use the command "logit final_decision i.attr1 i.attr2 (... for nominal variables)". I hope it helps you further. PS: Theoretically, you can make restructuring even in Excel, but it will be a long and painful process ;)

By the way, in STATA you can calculate marginal means, i.e. % of preference and not only the odds ratios (exp(B)) as in SPSS.

Hello. Could you explain, what you mean by "status quo"? Randomized attributes?

@@eugenleo What you called 'none of the proposed options' is called company car in my study, because it was the status quo (if they didn't change their choice in comparison with the original situation).

@@lelavanosselaer8884 you will need to calculate the final_decision variable differently. All other restructuring remains the same. I think...

@@lelavanosselaer8884 it is hard to say without being at my PC and seeing the file. Let's think about it in the following way. If option 1 is preferred it gets a 1 (decision = 1 and index2 = 1) and option 2 gets a 0. If option 2 is preferred, option 1 gets a zero and option 2 gets a one (decision = 2 and Index2 = 2). If "none of the options is selected (decision = 3), then both options get a zero (bone of them is preferred). Then you don't need a 3 in the final_decision. The variable is then binary and you run a logistic regression. I hope it helps. Have a nice evening!

@@lelavanosselaer8884 you can do, or just arrange a meeting with me. I should have time this week. calendly.com/yevgen-bogodistov Yet, I won't be able to look at it before Monday.

You add them as scalable (ordinal) covariates in the model (independent variables). The DV remains 'final decision'. Based on the Exp(B) you can say now, in how much an increase in one unit of, e.g. "ambition" increases willingness to retain the person in the team. Did I answer your question or did you ask something different? ;)

Welcome. I plan to add some new tricks soon. Good luck with your research!

@@eugenleo would love to read that.. Thanks

Indeed, I had this issue recently too. The check variable helps indicate the issue. Thank you and good luck with your research!

@@eugenleo Do you have a video on this? I use yes and no for different attributes. How do I solve this problem? I do not understand what is meant by 'add an and to the if function'. Thank you in advance!

@@lelavanosselaer8884 Not at the moment. But here is the code that we used: IF (attr1 = "Competitiveness" & attr1fop = "high" | attr2 = "Competitiveness" & attr2fop = "high" | attr3 = "Competitiveness" & attr3fop = "high" | attr4 = "Competitiveness" & attr4fop = "high" | attr5 = "Competitiveness" & attr5fop = "high" | attr6 = "Competitiveness" & attr6fop = "high" | attr7 = "Competitiveness" & attr7fop = "high" | attr8 = "Competitiveness" & attr8fop = "high" | attr9 = "Competitiveness" & attr9fop = "high" | attr10 = "Competitiveness" & attr10fop = "high") Competitiveness_high=1. We had the same anserws for the variables "Competitiveness", "Ambition", etc. These variables had the same values - no, low, medium, and high. So we needed to go through each of them and code accordingly. I hope it helps! I'll try to record a video on this.

@@lelavanosselaer8884 Yes (it is still uploading, but soon you will be able to watch it): th-cam.com/video/L9yKY11A-Tc/w-d-xo.html

@@eugenleo Dear Sir Bogodistov, thank you very much for this video!

To the best of my knowledge, it is not meant for menu-based choice modelling. Of course you can try to program it manually, but I did not find out how to do it. Maybe this will be the new development for the tool.

@@eugenleo Thank you very much. I took the liberty to send you an email regarding this, I hope you don't mind. Thank you again for your time.

@@marcelochafla5190 I'll respond next week.

@@marcelochafla5190 I would aproach the issue like this: th-cam.com/video/gUjr7w2i8lE/w-d-xo.html

Hi Swalha! I made a bunch on video also with a step-by-step experiment development. You can find more suggestions there. I use Excel, SPSS, and SDT Conjoint tool (github.com/astrezhnev/conjointsdt). Also here: th-cam.com/video/KXSgJpQ0NyA/w-d-xo.html, th-cam.com/video/7lSvr_n76p4/w-d-xo.html

Дякуємо 👍

I assume tha you mean "decision" variable... You can find it in 13'30'' of the video. In Qualtrics, you indicate your preference. This preference is saved as the answer to the question as 1 (Option 1) or 2 (Option 2). You use these variables as the dependent variable. In the first restructuring you create the variable "decision" were you put the answers from Qualtrics. Yet, after the second restructuring, you have to convert these values into 1 or 0. If the Option 1 was selected, the according option should become 1 and 0 otherwise. I do it in 45'25'' of the video. I hope it helps you with the analysis! Good luck!

Welcome! Good luck with your research!

It seems that Qualtrics requires the full account for JavaScript (www.qualtrics.com/support/survey-platform/managing-your-account/trial-accounts/). Just use the PHP approach, as it works with all types of accounts. Yet, pay attention: if you have a free account, you cannot download the data file. Of course, you can activate a 1-month trial to save the data. It works, but after 1 month you will have to upgrade. Contact your university or a partner university as they usually have institutional accounts, i.e. 50+ licences. They might make you full access to your thesis writing.

@@eugenleo Thank you very much for your kind response, I wanted to stick with the php approach from the beginning, but than had problems to find a free server to upload the files..

@@user-hj3rj3dt4t I use the zzz.com.ua. It is not free, but the first year costs about 4 EUR. They also have the free version but it has issues. Actually, most free hosting platforms have some issues. Investing 4 EUR into research might be a good idea. If you just want to try it out, you can send me the phphfile and I'll upload it to my server. But I can do it once to test, as I have no opportunity to upload files constantly (and you will have to make 4-5 trial&error phases until you DCE looks prefect).

Thank you for your help!

Hm, I don't know as I never met the situation. Do you mean that the attribute order remains the same while levels vary? Then this is just the regular setting in SDT. If you want that the order to the appearance of attributes varies additional to levels, then you check the respective box in the settings. But if you want that some attributes are shown in a constant order and the others vary, you need to program. Download the php/javascript file, go through the randomisation part of it and rewrite it. My programming knowledge might not be sufficient but it should be a relatively easy procedure.

Welcome! I have recently made a short video on use of pictures within a DCE. Enjoy ;)

Thank you for your comment. Here is the link to the QSF-file. tango.kl.com.ua/mci/Meetings_BAO_TH-cam.qsf Enjoy!

Yes, absolutely. The tool has been developed by researchers. You can find the APA-citation in the manual file.

@@eugenleo thank you

Thank you for the comment. 1: yes, there are several tools for DCE development. There is even a manual way to do it. Maybe once I'll make a video for this. Otherwise, simply google for the tools - there are plenty of them. I use Qualtrics as we have an institutional account. And there is a plugin that makes DCE easy to implement. Yet, if you develop the items manually, you may use ANY platform. Once I'll explain how. 2: I've never worked with the platform. But go for it, if it works. My email: yevgen.bogodistov(g)mci.edu

Welcome! Let me know if I can be of assistance :)

Hi! As you are not the first one, who asks this question, I developed a very short video on how to introduce the button "None of the proposed options". th-cam.com/video/IOXjm4cZwAc/w-d-xo.html Good luck and let me know, if I can be of any assistance.

th-cam.com/video/IOXjm4cZwAc/w-d-xo.html Here is a video, where I show how to do it correctly :)

It is a good question, thank you. As far as I understand, DCE is the art of conjoint. The selection options are presented in a different way - instead of ranking the item, you present the in a form of a manipulation - the participant sees only the two (or more) products from which she has to select one. This different way of presentation makes DCE to an experiment which may be seen as a different method. But (to the best of my understanding) the logic behind the method is pretty the same - to find out the preferences of the participant.

@@eugenleo Thank you so much.

I would like to do it, but the data comes from a real study which has not been published yet. Maybe we will add the data after it will have been published.

would really help to have to files

@@wildgameestate425 I plan to upload the files as soon as the project is published. But it might take a while...

@@eugenleo Any chance you could upload the data?