Lclogit: A Stata Command for Fitting Latent-Class Conditional Logit Models via the Expectation-Maximization Algorithm

Pacifico, Daniele; Yoo, Hong Il

doi:10.1177/1536867x1301300312

Cited by 131 publications

(130 citation statements)

References 8 publications

Supporting

Mentioning

120

Contrasting

Order By: Relevance

“…An interesting feature of this choice experiment is that the majority of respondents (57.5%) always chose one option, typically routine monitoring (49.1%), with fewer preferring CPM (8.4%). In DCE parlance, this is referred to as “non‐trading.” Based on standard information criteria (Pacifico & Yoo, ), the latent class analysis identified three groups of respondents: Prefer CPM (12% of women) who indicated a preference for CPM in the majority of choices; Prefer Monitoring (59%) who preferred routine monitoring in the majority of choices; and Traders (29%) who were prepared to swap between CPM and routine monitoring. The factors influencing choice as described by the latent class analysis are reported in Table .…”

Section: Resultsmentioning

confidence: 99%

“…Based on the results of the qualitative research and pilot survey, we hypothesised that we could categorise women into groups based on the similarity of their preferences, or how they made choices, between routine monitoring and CPM. Given the potential for such groups to exist, we used latent class analysis (Pacifico & Yoo, ), similar to cluster analysis, to analyse the choices women made. This assumes that the probability an individual will choose a particular option is conditional on them belonging to a particular group and is a widely used in the analysis of choices in health care (Zhou, Thayer, & Bridges, ).…”

Section: Methodsmentioning

confidence: 99%

“…Accordingly, we used latent class analysis (Pacifico & Yoo, 2013) to investigate the choices respondents made, taking into account the potential for respondents to be characterised into separate groups based on the similarity of their choice behaviour. The choice probabilities are thus estimated according to the following:…”

Section: Appendixmentioning

confidence: 99%

See 2 more Smart Citations

My mind is made up: Cancer concern and women’s preferences for contralateral prophylactic mastectomy

et al. 2019

View full text Add to dashboard Cite

The fear of cancer recurrence is cited as a motivator of women's preferences between routine monitoring and contralateral prophylactic mastectomy (CPM) as methods of managing ongoing breast cancer risk. We conducted a discrete choice experiment among a general community sample of women who completed 12 hypothetical choices between routine monitoring and CPM described by aspects of treatment efficacy, safety, cost and involvement in decision‐making. Respondents also completed a modified cancer worry question to assess cancer concern. Approximately 57.5% of 464 women always chose one option, typically routine monitoring. The majority (71.5%) reported being concerned about cancer recurrence when completing choice tasks. Latent class analysis identified three groups: preferred routine monitoring; preferred CPM; and “traders” (willing to swap between options). Among traders, women were less likely to choose an option associated with higher risk of recurrence. Women were more likely to choose options associated with less‐intrusive monitoring methods and where they were involved in decision‐making. Women concerned about cancer recurrence were more likely to choose CPM over monitoring. This study shows that women's preferences about how to manage breast cancer recurrence risk reflect the importance of the associated health effects, experience of care and attitudes to cancer recurrence.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

My mind is made up: Cancer concern and women’s preferences for contralateral prophylactic mastectomy

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Second, heterogeneity in respondent preferences is examined through latent class analysis, by variant, using the lclogit command in Stata (Pacifico & Yoo, 2013). This analysis assumes that respondents can be divided into subgroups (or classes) depending on their preferences.…”

Section: Analyses Of Quantitative Datamentioning

confidence: 99%

An exploration of the non‐iterative time trade‐off method to value health states

et al. 2018

View full text Add to dashboard Cite

Time Trade‐Off (TTO) usually relies on “iteration,” which is susceptible to bias. Discrete Choice Experiment with duration (or DCETTO) is free of such bias, but respondents find this cognitively more challenging. This paper explores non‐iterative TTO with or without lead time: NI(LT)TTO. In NI(LT)TTO, respondents see a series of independent pairwise choices without iteration (similar to DCETTO), but one of the two scenarios always involves full health for a shorter duration (similar to TTO). We compare three different “types” of NI(LT)TTO relative to DCETTO. Each type is presented in two “modes”: (a) verbally tabulated (as in a DCE) and (b) with visual aids (as in a TTO). The study has 8 survey variants, each with 12 experimental choice tasks and a 13th task with a logically determined answer. Data on the 12 experimental choices from an online survey of 6,618 respondents are modelled, by variant, using conditional logistic regressions. The results indicate that NI(LT)TTO is feasible, but some relatively mild states appear to have implausibly low predicted values, and the range of predicted values is much narrower than in DCETTO. The presentation of NI(LT)TTO tasks needs further improvement.

show abstract

“… Regarding latent class models, the numerical maximization method can be difficult because the inverted Hessian or approximate Hessian is hard to calculate with a large number of parameters (Train, ). We estimate the parameters with the expectation‐maximization (EM) algorithm using the Stata command lclogit (Pacifico & Yoo, ).…”

mentioning

confidence: 99%

Consumer valuation of personal information in the age of big data

Lim

Woo

Lee

et al. 2017

Asso for Info Science & Tech

View full text Add to dashboard Cite

In a big data environment, there are growing concerns about the violation of consumer rights regarding information privacy. To induce rational regulations for protecting personal information, it is necessary to separately estimate consumers' values related to different types of personal information. In this article, discrete choice experiments using hypothetical information leakage situations given certain compensation amounts and discrete choice models were used to quantitatively analyze the value of personal information. The results indicate that consumers generally place high value on information that could cause immediate and actual damage from the leakage after identification, such as basic personal information and purchase list and payment information. Consumers value location information and personal medical information differently based on their perceived importance of privacy and their prior experience with personal information leakage. We suggest that the level of regulation should differ according to the type of personal information based on the consumers' valuation. This article contributes to a better understanding of a quantitative approach to pricing personal information.

show abstract

Lclogit: A Stata Command for Fitting Latent-Class Conditional Logit Models via the Expectation-Maximization Algorithm

Abstract: In this article, we describe lclogit, a Stata command for fitting a discrete-mixture or latent-class logit model via the expectation-maximization algorithm.

Cited by 131 publications

References 8 publications

My mind is made up: Cancer concern and women’s preferences for contralateral prophylactic mastectomy

My mind is made up: Cancer concern and women’s preferences for contralateral prophylactic mastectomy

An exploration of the non‐iterative time trade‐off method to value health states

Consumer valuation of personal information in the age of big data

Contact Info

Product

Resources

About