Conjoint analysis with item randomize

Plus d'informations
il y a 1 mois 1 semaine #187540 par RitaShen
hi there,

I have a question about the conjoint analysis questions.

can I do the conjoint analysis with randomizing?

like this picture, there are 9 (1~9) features

but I want to show these 9 features randomize.

can I do this with LimeSurvey?

thanks
Pièces jointes :

Connexion ou Créer un compte pour participer à la conversation.

LimeSurvey Partners
Plus d'informations
il y a 1 mois 1 semaine #187547 par jelo
Réponse de jelo sur le sujet Conjoint analysis with item randomize
Limesurvey offers no Conjoint-Features. If you want to advance a workaround, please provide a LSS-export and the LS-version you use. Nobody likes LSQ-exports.

The meaning of the word "stable" for users
www.limesurvey.org/forum/development/117...ord-stable-for-users

Connexion ou Créer un compte pour participer à la conversation.

Plus d'informations
il y a 1 mois 1 semaine #187551 par Joffm
Réponse de Joffm sur le sujet Conjoint analysis with item randomize
Hi, Rita,

as you know the features in the Conjoint workaround are in a hardcoded HTML table.

The only idea I have is to put the rows into a javascript array, shuffle the array and then display the rows.

Joffm


Volunteers are not paid.
Not because they are worthless, but because they are priceless

Connexion ou Créer un compte pour participer à la conversation.

Plus d'informations
il y a 1 mois 1 semaine #187561 par RitaShen
sorry for that
here is the LSQ-export

Fichier attaché :

Nom du fichier : limesurvey...7584.lss
Taille du ficher :24 ko
Pièces jointes :

Connexion ou Créer un compte pour participer à la conversation.

Plus d'informations
il y a 1 mois 1 semaine #187568 par RitaShen
Hi Joffm,

I just tried to use Math.floor to do the conjoint analysis,
but it seems cannot work on the Limesurvey,
I'm not sure can anyone help me to solve this problem.

Here's the code that for conjoint analysis:
<span> Scenario 1 out of 5 </span>
 
<font size="3">
<table border="4" cellpadding="15" cellsapcing="0" width="90%">
	<col width="140">
	<col width="30">
	<col width="30">
	<tbody><tr>
	<th><br></th>
	<th><b>Candidate 1</b></th>
	<th><b>Candidate 2</b></th>
	</tr>
 
	<!--Create Placeholders for dimensions names (e.g., "att1") -->
	<!--Create Placeholders for candidate traits (e.g., "a1" for first candidate, "b1" for second candidate) -->
 
	<tr>
	<td id="att1"><br></td>
	<td id="a1"><br></td>
	<td id="b1"><br></td>
	</tr>	
	<tr>
	<td id="att2"><br></td>
	<td id="a2"><br></td>
	<td id="b2"><br></td>
	</tr>	
	<tr>
	<td id="att3"><br></td>
	<td id="a3"><br></td>
	<td id="b3"><br></td>
	</tr>
	</tbody></table>
</font>
 
<script>
	//Define the Dimensions
		var attRaw = ["Race/Ethnicity","OCCUPATION","PID"];
		var att = ["Race/Ethnicity","OCCUPATION","PID"];
		var attributes =["","",""];
 
	//Randomize the Order of Dimensions
		for (i=0; i<attRaw,length;i++){
		var rand1 = Math.floor(Math.random()*((attRaw.length-i)-0));
		attributes[i]=att[rand1];
		att.splice(rand1,1);}
 
	//Create Variables for Traits associated with each dimension
		var RACE_raw = ["White","Black","Hispanic","Asian"];
		var OCCUPATION_raw = ["Lawyer","teacher","business owner","Doctor"];
		var PID_raw = ["Democrat","Republican","Independent"]
 
	//Use math.random tp randomly select traits for each dimension for both candidates
		var RACE_a = RACE_raw[Math.floor(Math.random()*RACE_raw.length)];
		var OCCUPATION_a = OCCUPATION_raw[Math.floor(Math.random()*OCCUPATION_rawN.length)];
		var PID_a = PID_raw[Math.floor(Math.random()*PID_raw.length)];
 
		var RACE_b = RACE_raw[Math.floor(Math.random()*RACE_raw.length)];		
		var OCCUPATION_b = OCCUPATION_raw[Math.floor(Math.random()*OCCUPATION_raw.length)];	
		var PID_b = PID_raw[Math.floor(Math.random()*PID_raw.length)];		
 
	//Take indexOf the Dimension variable. This is the order of the Dimension variable
		var RACE_index = attributes.indexOf("Race/Ethnicity");
		var OCCUPATION_index = attributes.indexOf("OCCUPATION");
		var PID_index = attributes.indexOf("PID");
 
        //Use IndexOf Dimension and replace with appropriate trait for CandidateA
	// For instance, if "PID" is the 3rd element in the Dimension variable,
	//this will place Democrat/Republican/Independent as the 3rd element of the forst candidate's attributes
 
	att_a_traits[RACE_index] = RACE_a;
	att_a_traits[OCCUPATION_index] = OCCUPATION_a;
	att_a_traits[PID_index] = PID_a;
 
	//Do the same for the second candidate
	att_b_traits[RACE_index] = RACE_b;
	att_b_traits[OCCUPATION_index] = OCCUPATION_b;
	att_b_traits[PID_index] = PID_b;	
 
	//Create list of variables in the for loop
 
	att_list =["att1","att2","att3"];
	a_list =["a1","a2","a3"];
	b_list =["b1","b2","b3"];
 
	//For elements 1 to 3 in the Dimensions, First Candidate and Second Candidate variables.
	//The first line assigns Dimensions to each "id" tag in the first column of the HTML table
	//The second line assigns first candidate traits to each "id" tag in the second column of the HTML table
	//the Third line assigns first candidate traits to each "id" tag in the third column of the HTML table
 
	for(i=0;i<3;i++){
		document.getElementById(att_list[i]).innerHTML = attributes[i];
		document.getElementById(a_list[i]).innerHTML = att_a_traits[i];
		document.getElementById(b_list[i]).innerHTML = att_b_traits[i];
	}
</script>


mank thanks

Connexion ou Créer un compte pour participer à la conversation.

Commencez dès maintenant !

Créez simplement un compte et commencez à utiliser LimeSurvey dès aujourd'hui.

Inscrivez-vous maintenant

Inscrivez-vous à notre Newsletter!