<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: linking levels in Discrete Choice experiment in Statistical Procedures</title>
    <link>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38733#M1620</link>
    <description>Sorry. Respond it so late.&lt;BR /&gt;
But not see what your data look like and what your output look like.&lt;BR /&gt;
Is your contract duration numeric variable?&lt;BR /&gt;
It seems to be a format problem.&lt;BR /&gt;
But I am not sure whether the following is what you need.&lt;BR /&gt;
&lt;BR /&gt;
[pre]&lt;BR /&gt;
proc format;&lt;BR /&gt;
 invalue            pricefmt&lt;BR /&gt;
        0 = 5&lt;BR /&gt;
      12,24= 0;&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
..................&lt;BR /&gt;
  price_two = input(contract_duration_value,pricfmt.);&lt;BR /&gt;
  format price_two dollar4.;&lt;BR /&gt;
&lt;BR /&gt;
[/pre]&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
Ksharp</description>
    <pubDate>Fri, 25 Jun 2010 04:19:34 GMT</pubDate>
    <dc:creator>Ksharp</dc:creator>
    <dc:date>2010-06-25T04:19:34Z</dc:date>
    <item>
      <title>linking levels in Discrete Choice experiment</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38730#M1617</link>
      <description>Dear all,&lt;BR /&gt;
&lt;BR /&gt;
I am going to conduct a discrete choice experiment about tariff choice.&lt;BR /&gt;
In the experiment, i want to include a discount for contract duration, that is, the longer the contract the higher the discount on final price.&lt;BR /&gt;
&lt;BR /&gt;
Thus, i have the attribute CONTRACT with levels 0, 12 and 24, and i have the attribute PRICE I with levels of +5, 0 and -5.&lt;BR /&gt;
&lt;BR /&gt;
I now want to link the levels of the first attribute to the ones of the second, so that every time an alternative possesses the CONTRACT level 24, the PRICE I level is -5, for instance. &lt;BR /&gt;
&lt;BR /&gt;
I hope someone can tell me how i can program this, and if it is doable at all.&lt;BR /&gt;
&lt;BR /&gt;
Thanks a lot!</description>
      <pubDate>Mon, 21 Jun 2010 21:08:42 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38730#M1617</guid>
      <dc:creator>oraider</dc:creator>
      <dc:date>2010-06-21T21:08:42Z</dc:date>
    </item>
    <item>
      <title>Re: linking levels in Discrete Choice experiment</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38731#M1618</link>
      <description>Hi. I do not understand your purpose total.&lt;BR /&gt;
Plz, give an example and what target do you need to achieve.</description>
      <pubDate>Tue, 22 Jun 2010 07:56:56 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38731#M1618</guid>
      <dc:creator>Ksharp</dc:creator>
      <dc:date>2010-06-22T07:56:56Z</dc:date>
    </item>
    <item>
      <title>Re: linking levels in Discrete Choice experiment</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38732#M1619</link>
      <description>Okay, let me explain it to you in more detail.&lt;BR /&gt;
&lt;BR /&gt;
I have a discrete choice / choice-based conjoint experiment with the 4 attributes:&lt;BR /&gt;
 - QoS&lt;BR /&gt;
 - speed&lt;BR /&gt;
 - contract duration (0 / 12 / 24)&lt;BR /&gt;
 - max. usage in giga byte (7.5 / 10 / 12.5)&lt;BR /&gt;
&lt;BR /&gt;
Another attribute is supposed to be&lt;BR /&gt;
 - price&lt;BR /&gt;
&lt;BR /&gt;
However, using this setting, awkward combinations would come up. Thus, I was planning to delete the initial price attribute and replace it by two other price attributes:&lt;BR /&gt;
 - price I (price per giga byte)&lt;BR /&gt;
 - price II (discount for longer contract duration)&lt;BR /&gt;
&lt;BR /&gt;
Price I:&lt;BR /&gt;
 - 1 level: $3.99&lt;BR /&gt;
 - is to be multiplied with a corresponding "max usage in gb" level (e.g. "10")&lt;BR /&gt;
&lt;BR /&gt;
Price II:&lt;BR /&gt;
 - 2 levels: "$5" and "$0"&lt;BR /&gt;
 - "$5" is only allowed to show up in combination with the level "0" of the "contract duration" attribute&lt;BR /&gt;
 - "$0" is only allowed to show up in combination with the levels "12" and "24" of the "contract duration" attribute&lt;BR /&gt;
- is to be added to the result of the Price I multiplikation above.&lt;BR /&gt;
&lt;BR /&gt;
Here is one example:&lt;BR /&gt;
&lt;BR /&gt;
Alternative 1                                   &lt;BR /&gt;
QoS "good"                                    &lt;BR /&gt;
Speed "very fast"                            &lt;BR /&gt;
Contract "0 months"                        &lt;BR /&gt;
max. usage "10 gb"                         &lt;BR /&gt;
price I "$39.90" (as 10x$3.99)          &lt;BR /&gt;
price II "5$"                                    &lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
Alternative 2&lt;BR /&gt;
QoS "excellent"&lt;BR /&gt;
Speed "normal"&lt;BR /&gt;
contract "12 months"&lt;BR /&gt;
max. usage "12.5 gb"&lt;BR /&gt;
price I "$49.90" (as 12.5x$3.99)&lt;BR /&gt;
price II "$0"&lt;BR /&gt;
&lt;BR /&gt;
Attributes price I &amp;amp; II are for the design only. In the questionnaire, the respondent will see one uniform price attribute only.&lt;BR /&gt;
&lt;BR /&gt;
What I need to know is, how do I assign the levels of "price II" to the corresponding levels of "contract duration", as "$5" is not supposed to be combined with "12" and "24", but only with "0".&lt;BR /&gt;
&lt;BR /&gt;
I hope this made my problem more clear. Many thanks in advance!</description>
      <pubDate>Tue, 22 Jun 2010 11:34:17 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38732#M1619</guid>
      <dc:creator>oraider</dc:creator>
      <dc:date>2010-06-22T11:34:17Z</dc:date>
    </item>
    <item>
      <title>Re: linking levels in Discrete Choice experiment</title>
      <link>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38733#M1620</link>
      <description>Sorry. Respond it so late.&lt;BR /&gt;
But not see what your data look like and what your output look like.&lt;BR /&gt;
Is your contract duration numeric variable?&lt;BR /&gt;
It seems to be a format problem.&lt;BR /&gt;
But I am not sure whether the following is what you need.&lt;BR /&gt;
&lt;BR /&gt;
[pre]&lt;BR /&gt;
proc format;&lt;BR /&gt;
 invalue            pricefmt&lt;BR /&gt;
        0 = 5&lt;BR /&gt;
      12,24= 0;&lt;BR /&gt;
run;&lt;BR /&gt;
&lt;BR /&gt;
..................&lt;BR /&gt;
  price_two = input(contract_duration_value,pricfmt.);&lt;BR /&gt;
  format price_two dollar4.;&lt;BR /&gt;
&lt;BR /&gt;
[/pre]&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
&lt;BR /&gt;
Ksharp</description>
      <pubDate>Fri, 25 Jun 2010 04:19:34 GMT</pubDate>
      <guid>https://communities.sas.com/t5/Statistical-Procedures/linking-levels-in-Discrete-Choice-experiment/m-p/38733#M1620</guid>
      <dc:creator>Ksharp</dc:creator>
      <dc:date>2010-06-25T04:19:34Z</dc:date>
    </item>
  </channel>
</rss>

