Important: Read this before posting to this forum

  1. This forum is for questions related to the use of Apollo. We will answer some general choice modelling questions too, where appropriate, and time permitting. We cannot answer questions about how to estimate choice models with other software packages.
  2. There is a very detailed manual for Apollo available at http://www.ApolloChoiceModelling.com/manual.html. This contains detailed descriptions of the various Apollo functions, and numerous examples are available at http://www.ApolloChoiceModelling.com/examples.html.
  3. Before asking a question on the forum, users are kindly requested to follow these steps:
    1. Check that the same issue has not already been addressed in the forum - there is a search tool.
    2. Ensure that the correct syntax has been used. For any function, detailed instructions are available directly in Apollo, e.g. by using ?apollo_mnl for apollo_mnl
    3. Check the frequently asked questions section on the Apollo website, which discusses some common issues/failures. Please see http://www.apollochoicemodelling.com/faq.html
    4. Make sure that R is using the latest official release of Apollo.
  4. If the above steps do not resolve the issue, then users should follow these steps when posting a question:
    1. provide full details on the issue, including the entire code and output, including any error messages
    2. posts will not immediately appear on the forum, but will be checked by a moderator first. This may take a day or two at busy times. There is no need to submit the post multiple times.

Data set with missing values

Ask general questions about data for choice modelling that are not Apollo specific but relevant to Apollo users.
Post Reply
Blake Huang
Posts: 9
Joined: 08 Dec 2020, 11:30

Data set with missing values

Post by Blake Huang » 03 Apr 2022, 11:08

Hello Prof. Hess,

My data set inherently has missing values. I designed 9 SP scenarios with different variables between each 3 scenarios, but the alternatives are the same for all scenarios. For example, I considered 3 variables in Scenario 1-3, 2 additional variables in Scenario 4-6, and 3 additional variables in Scenario 7-9. Since Apollo cannot deal with the data set with missing values, what should be done with the data in this case?

ID X1 X2 X3 X4 X5 X6 X7 X8 choice
1 3 85 14 2
2 2 105 11 1
3 3 95 14 3
4 1 105 11 50 3 3
5 1 85 8 30 1 1
6 3 105 14 50 3 2
7 1 1 1 1 1 1 1 1 1
8 2 2 2 2 2 2 2 2 2
9 3 3 3 3 3 3 3 3 3

Best regards
Yue

stephanehess
Site Admin
Posts: 632
Joined: 24 Apr 2020, 16:29

Re: Data set with missing values

Post by stephanehess » 04 Apr 2022, 17:23

Hi

could you be a bit more specific about the setup of your data and how you want to model it?

Thanks
--------------------------------
Stephane Hess
www.stephanehess.me.uk

Blake Huang
Posts: 9
Joined: 08 Dec 2020, 11:30

Re: Data set with missing values

Post by Blake Huang » 05 Apr 2022, 03:26

Hi, Prof. Hess,
I am very sorry for not describing my problem clearly. For example, let's assume that each respondent is required to complete 18 (9+9) hypothetical scenarios.

Scenario 1-9: including 8 attributes, and then 9 scenarios are obtained through uniform design.
Scenario 10-18: including 10 attributes (8+2), among which 2 attributes are newly added. Through uniform design again, we have 9 scenarios.

An illustrative data format is shown as follows:
ID X1 X2 X3 X4 X5 choice
1 1 1 1 - - 1
1 2 2 2 - - 2
1 3 3 3 - - 3
1 4 4 4 4 4 3
1 5 5 5 5 5 2
1 6 6 6 6 6 1

Since the choice options are the same in all scenarios, we wonder if we can put the data together to build an MNL model?

stephanehess
Site Admin
Posts: 632
Joined: 24 Apr 2020, 16:29

Re: Data set with missing values

Post by stephanehess » 05 Apr 2022, 10:49

Sorry, this is still not clear. Can you show the entire data, plus your proposed model specification?
--------------------------------
Stephane Hess
www.stephanehess.me.uk

Blake Huang
Posts: 9
Joined: 08 Dec 2020, 11:30

Re: Data set with missing values

Post by Blake Huang » 05 Apr 2022, 14:02

Dear Prof. Hess,

This is my model specification, and you can check the attachment for the complete data format.

V[['alt1']] = asc_1 + b_tt * cartime + b_pollution * carpollution

V[['alt2']] = asc_2 + b_tt * prtime + b_fee * prfee + b_capacity_2 * capacity + b_comfort2_2 * comfort2 + b_comfort3_2 * comfort3 + b_ratio_2 * ratio + b_comment1_2 * comment1 + b_comment2_2 * comment2 + b_pollution * prpollution

V[['alt3']] = asc_3 + b_tt * bustime + b_fee * busfee + b_pollution * buspollution
Attachments
1649162883(1).png
1649162883(1).png (112.34 KiB) Viewed 2438 times

stephanehess
Site Admin
Posts: 632
Joined: 24 Apr 2020, 16:29

Re: Data set with missing values

Post by stephanehess » 06 Apr 2022, 07:58

Hi

you can just make the attribute 0 when it's missing. See also this example file where the service quality attribute is not present for RP in the data http://apollochoicemodelling.com/files/ ... NL_RP_SP.r

Stephane
--------------------------------
Stephane Hess
www.stephanehess.me.uk

Blake Huang
Posts: 9
Joined: 08 Dec 2020, 11:30

Re: Data set with missing values

Post by Blake Huang » 08 Apr 2022, 12:51

That's exactly how I deal with it. I just want to make sure it's the right way to do it. Thank you, Prof. Hess.

stephanehess
Site Admin
Posts: 632
Joined: 24 Apr 2020, 16:29

Re: Data set with missing values

Post by stephanehess » 08 Apr 2022, 13:16

The only thing you need to be careful with in that context is with categorical variables. For a continuous variable, using 0 for missing data will course make sense, but for a categorical variable, you need to think about whether 0 is also already a level that is used
--------------------------------
Stephane Hess
www.stephanehess.me.uk

Post Reply