Questions tagged [choice-modeling]
This is for questions about discrete choice modeling
102
questions
0
votes
0
answers
4
views
Looking for statistical modeling approaches/examples for "difference in cost per click/conversion" on Facebook split tests
Mainly looking for references to articles, guides, and vignettes that tackles this or similar problems, thanks!
Trying to find the best modeling approach for Facebook ad data. I want to model 'cost ...
0
votes
0
answers
6
views
How scale heterogeneity can be a source of correlation?
First off, I'd like to put this clearly that I am new to logit models and I am trying to learn their basics. So far, I have understood that in the sphere of multinomial logit models and MXL, there are ...
0
votes
0
answers
6
views
Issues using multinomial logit on choice-based conjoint experiment data with a panel structure
In most choice-based conjoint survey experiments, respondents answer multiple choice questions, thus the data have a panel structure. Multinomial logit is a common model used with these data to ...
0
votes
0
answers
3
views
Predicting probability of choice across different choice sets
I have data where people saw a series of 2 forced choices. Those choices were a random selection from a set of 4. So, from a set {A, B, C, D} participants saw two random options (e.g., {A, D} or {B, C}...
0
votes
0
answers
16
views
Choice Based Conjoint 'no-choice' MNL model validation
I have conducted a CBC with each choice task consisting of 2 concepts and a no-choice option.
For training my MNL model, I added a column to the dataset that takes the value one (for both concepts) ...
1
vote
0
answers
12
views
Condition logit model: Weighted mean of ratios of coefficients of subgroups does NOT equal the ratios of coefficients of the whole sample, why?
I am well aware that when one splits the sample into subgroups (e.g. sex, country, whatever), and then estimates any logistic regression model, the coefficients are not comparable between (otherwise ...
1
vote
1
answer
124
views
Interaction between alternative-specific and individual-specific variables in a conditional logistic regression
I am interested in the moderating effect of a voter's political knowledge on the effect of a voter's candidate evaluations on vote choice. I am trying to estimate conditional logit models to analyze ...
0
votes
1
answer
15
views
Population overlap of random distributions of binary choices
I’m trying to figure out how to calculate the overlap (concurrence) of certain building features, for example: high-efficiency windows, thick insulation, efficient lights, etc. I know the probability ...
0
votes
0
answers
208
views
How to choose alternative specific constant (ASC) in multinomial logistic regression in R? (unlabeled choice experiments)
I am trying to replicate my colleague's NLOGIT analysis using R. This analysis was for a discrete choice experiment in which fisherman chose whether to opt into a hypothetical environmental protection ...
2
votes
0
answers
21
views
How much confidence to have data is correct based on checking N samples
If I have a dataset of size $N$, and choose $n$ samples, where $k$ of the samples are OK, how confident can I be that the dataset is OK?
To make it more concrete, suppose I have a dataset D1 with 5,...
0
votes
0
answers
64
views
Statistical test to test differences between 2 categorical variables
I have a data set outline preferences for 3 groups of subjects regarding payments and game features. The set looks like this:
payment_source_preference
favorite_feature
Group
GroupSize
NoPreference
...
1
vote
1
answer
143
views
Logit-Poisson Trick
Consider an analysis of discrete-choice logit,
where the independent variables vary with the
alternatives. Suppose that each individual is
represented once in the sample, and that different
...
0
votes
0
answers
204
views
Calculating willingness to pay in mixed logit model with lognormally distributed price parameter
I am analyzing data from a discrete choice experiment (five attributes, including price attribute). For the mixed logit specification, I assumed normal distribution for the four non-price parameters; ...
0
votes
0
answers
30
views
Testing of significant mean/median difference between two computed log-normal distributions
I don´t know if this is possible to test, but I have estimated two mixed logit regressions on two different datasets and the resulting coefficients of the independent variables are assumed to be ...
0
votes
0
answers
26
views
Integrating case-specific variables in a conditional logit model
I am doing conditional logit (CL) analysis to model decisions. Next to alternative-specific variables I also have case-specific variables in the dataset. As far as I understand the CL, I can integrate ...
0
votes
1
answer
16
views
Repeated Selection of 2 random options, how to model it
Probelem/Idea
I am thinking of using an analysis with a methodology similar to the one ESPN is using to rank NBA players:
...
1
vote
0
answers
70
views
How to implement nested logit model if the choice set for each individual is dynamic changing
I think this question is similar to Discrete choice model with different choice set for each sample, but that question does not have an answer. I have a dataframe in which individuals have dynamic ...
0
votes
0
answers
11
views
How to choose scoring scheme for ordinal categorical variable?
I would like to perform logistic regression of skin damage by use of some drugs(all subjects will be applied with the same drug) with clinical change as ordinal categorical variable. Clinical change ...
1
vote
0
answers
38
views
Endogeneity in Discrete Choice Models
Suppose we are trying to estimate a model to predict failure of a company as a function of some firm-level and macroeconomic variables using a logistic regression
$Y_{it} = X_{it} \beta + \epsilon_{...
1
vote
1
answer
79
views
Why isn't the probability of an event happening in $L$ days given the probability $p$ it happens on any day $\frac{(2^L - 1)}{p^{-L}}$?
I feel like this is probably a dumb question, but there is something I am fundamentally misunderstanding here.
The problem is essentially the same as the one mentioned in this question. I understand ...
0
votes
1
answer
27
views
"nested choice" multinomial model
I would describe a model (and solve with the stan software) a process like this:
for i = 1...N consumers
the i-th consumer is allowed to choose an item out of 7. 6 ...
1
vote
0
answers
67
views
Classification of logit and probit models
Savolainen et al. (2011) has a review of discrete choice models used in accident analysis. The paper offers a classification of these models (see image), but some models (e.g. 'Partial proportional ...
1
vote
1
answer
27
views
Which choice model to analyse my binary stated choice experiment data to estimate willingess-to-pay?
I followed the recipe of a stated-choice experiment in political science https://doi.org/10.1093/pan/mpt024 (they call it "conjoint" but I think this term is debated).
In the end I made the ...
1
vote
0
answers
9
views
Randomisation uneven in a choice experiment - what could help to overcome associated problems?
We conducted a choice experiment of the type forced-choice, choose between A or B. A or B are products that are described using 5 attributes. These 5 attributes have different attribute levels that ...
1
vote
0
answers
82
views
Which test should I use for a three alternative forced choice experiment?
I am running an online survey experiment where participants are randomly assigned to different treatment groups. They are asked to make a three alternative forced choice (3AFC) decision, i.e., pick A, ...
2
votes
0
answers
94
views
nominal regression, kinda. What is the right terminology for this
tl;dr
This looks cool, relates possible to discrete regression, but I don't know the term for what it is to do this.
I want to learn more. It looks interesting and useful. Can you point me to ...
0
votes
0
answers
9
views
Expected value of conditional choice probability [duplicate]
I would like to compute the conditional choice probability which is defined as follows
\begin{equation}
p_k=Prob(f(m_k)+u_k>f(m_i)+u_i, \forall i\neq k|m)
\end{equation}
where $u_i, i=1,...,N$ are ...
1
vote
0
answers
25
views
Appropriate model for path choice data
I have data from a path choice experiment in which shopping mall visitors chose among different path alternatives at several intersections. Additionally, I have measures of spatial syntax for the ...
1
vote
1
answer
29
views
Recalibration of constants with ordered logit for forecasting
I have estimated an order logit model: I have one utility function (without constant, in the form $\sum_i \beta_i * x_i$) with cuts and I estimated the $\beta_i$ and the cuts on revealed preference ...
6
votes
1
answer
110
views
$R^2$ of Logistic Regression Without Intercept?
I am calibrating a logistic regression for a survey data which comes from a binary stated choice experiment. The stated choice experiment was an unlabeled one, which means that all the variables ...
1
vote
0
answers
83
views
Discrete choice model with different choice set for each sample
Data
I have observational data of $N$ rows (samples). In row $n$ individual $k_n \in \{1, \ldots, K\}$ from a population of $K \ll N$ individuals chooses one option $y^{k_n}_n$ from $J_n$ options, ...
3
votes
1
answer
110
views
multilevel discrete choice model
Say a preference-survey asks respondents which of four products they prefer. For each product, I have the respondent's alternative specific covariate (let's say price) for each alternative included in ...
1
vote
0
answers
38
views
Do I have a true within-subject design?
I am currently in the design phase for an experiment on different packaging attributes and their effects on an actual purchasing choice. In this context, I am asking myself a possibly trivial question:...
1
vote
0
answers
24
views
Modeling and updating the reliability of two sources of information
I do not know the general framework this might fall under, apologies for the vague title.
Assume that a decision maker's choice is dependent on two sources of information $f_1$ and $f_2$. Assume for ...
1
vote
0
answers
296
views
How to estimate a nested logit model using mlogit in R in the case of panel data and degenerate branche?
I'm using a Discrete Choice Experiment.
I have 9 choice sets with 3 alternatives (2 alternatives and an opt-out), the alternatives are described with 4 attributes.
I want to use a nested logit model ...
3
votes
1
answer
417
views
How to add Indivivual Specific Variables for unlabelled alternative (using interactions) using mlogit with R?
I’m using DCE with unlabelled alternatives, 9 choice set with 3 alternative each (2 option and Optout alternative), described with 4 attributes.
I've started with a conditional logit (with only ...
0
votes
0
answers
111
views
R MLogit 'system is singular' error
I'm running a choice model comparing how users choose between multiple options in an app.
I have the data formatted for use with MLogit:
Price and dist_rank_cat are features that vary by ...
2
votes
0
answers
21
views
Choose number or nothing with machine learning
I want to do supervised learning. I have a labeled dataset. Each label is normally a real number between [0,1] corresponding to a location of a certain object in the data, or NAN if the object is not ...
1
vote
1
answer
160
views
Statistical test for 3-way choice data
I have a data set of a 3-way mate choice experiment between species a, b and c. I aim to test whether males courted more often with females of their own species. The dependent variable is count data ...
2
votes
1
answer
540
views
latent class model on choice data with gmnl - choosing starting values
I want to run a LCMNL (using the gmnl-package) on choice data. I read that starting values can influence class allocation since LCMNL can have several optima. I found the following example code that I ...
2
votes
1
answer
336
views
nested logit with individual level fixed effect (panel data)
As is stated in the title, I have several questions concern the combination of nested logit and panel data.
1, Can we run nested logit with the individual fixed effect? this is useful when one has ...
0
votes
0
answers
118
views
I'm trying to analyze my data using mlogit. I get singularity issues. I am very new to statistical modelling. Help appreciated!
The csv for the dataframe is here.
Basically the column Mode represents the transportation choice available for the user to go to the airport, Choice represents the user's choice, and all the other ...
1
vote
1
answer
266
views
Conditional logit or multinomial logit?
I have the following problem I need to use a discrete choice model to determine the time values (VOT) of 3 transport alternatives (car, bus and train). Looking at the literature of the discrete choice ...
2
votes
1
answer
110
views
Logistic regression when the number of options differs by group?
I have data from a laboratory experiment in which I look at the effect of expanding the choice set on a particular option being chosen. The idea is that introducing an Option "B" reduces demand for an ...
1
vote
0
answers
126
views
Experimental design for discrete choice response
I'm designing a survey where people need to choose one of three transportation alternatives. Here are the alternatives, their specific factors/attributes and the levels I intend to use for each:
<...
2
votes
0
answers
87
views
How to treat different status quo groups in a choice experiment?
I have a choice experiment where respondents choose between a status quo and one alternative. Before the choice questions, respondents are allocated to four different groups which determine the levels ...
0
votes
2
answers
90
views
What is the appropriate test for a choice experiment where multiple subjects perform the experiment multiple times?
I'm testing multiple subjects in a choice task where they are either right or wrong. By chance they would choose the right answer 50% of the time. Each of my 11 subjects performs the test 24 times.
To ...
3
votes
1
answer
305
views
Probability of choosing the degenerate branch in a nested multinomial logit
This may be an obvious question, but I'm flummoxed.
Let's say I've got a nested logit model with a degenerate nest—say, a healthcare choice model where the branches are Home vs. Hospital. The Home ...
1
vote
0
answers
173
views
Independence of irrelevant alternatives practical example
I have frequently heard descriptions of the IIA problem for logit regression phrased in terms of the famous red bus/blue bus, or some direct metaphor for that thing. However, I was curious as to what ...
0
votes
0
answers
118
views
Choice design acc. to d-efficiency (Ngene): more than one block per respondent?
I have a question with regard to choice design for discrete choice experiments.
Quite some time ago I conducted a choice experiment and now I am trying to publish a paper on that study. I got some ...