Lawrence McCandless

Associate professor at Simon Fraser University, Interests in biostatistics, Bayesian inference, and epidemiology

[Lawrence McCandless @LCMcCandless]

Postdoc position in the Faculty of Health Sciences @SFU in Vancouver in Environmental Epidemiology! Come work with us to study the effects of air pollution on children's respiratory, neurocognitive and cadiometabolic development @SFU_FHS

[SFU Health Sciences @SFU_FHS]

#JOBALERT: We're hiring for a postdoc position in environmental epidemiology! Work with Ryan Allen and @LCMcCandless to study the effects of air pollution on children's respiratory, neurocognitive and cardiometabolic development.

Learn more: https://t.co/Bh0Xd1B6Qd

[ISEE_job @isee_job]

#Postdoctoral scholar position available in #environmental #epidemiology Simon Fraser University @SFU Will work w/Drs Ryan Allen & Lawrence McCandless on a birth cohort study of #air #pollution & #children's #health in #Mongolia. https://t.co/XPHevmSNmJ @IseeSnrn #ISEE_job

[SFU Health Sciences @SFU_FHS]

Learn more about this job opportunity at: https://t.co/jsPntlKhw9

#Postdoc #Epidemiology #biostatistics #ISEE_job #EnvEpi

[Lawrence McCandless @LCMcCandless]

From Reprints and Reflections in IJE. A paper from 1991.

How Independent Are “Independent” Effects? Relative Risk Estimation When Correlated Exposures Are Measured Imprecisely

https://t.co/QMbhgTkC9w

[Lawrence McCandless @LCMcCandless]

P-value function depicts the full range of hypotheses that are compatible with the data.
They allow a more nuanced interpretation of evidence versus significant/nonsignificant.
I first encountered them in Epidemiology: An Introduction by @ken_rothman

[Lawrence McCandless @LCMcCandless]

A biostatistics tutorial published in Statistics in Medicine about p-value functions.

https://t.co/T6blEcevMR

[SER @societyforepi]

VanderWeele comments on why there is need for the sufficient cause model today in @AmJEpi: https://t.co/uZOPY71zgB #SER50thAnniversary

[Laurent Azoulay @profLAzoulay]

This is a must read.

Spoiler alert: case-control studies are not the problem...

Discussion of Schuemie et al: “A plea to stop using the case‐control design in retrospective database studies” https://t.co/rDIewYweuG

[Lawrence McCandless @LCMcCandless]

Congrats to Harry Zhuang for NSERC PGSD: "Bayesian factor analysis for high-dimensional correlated exposure variables with application to environmental epidemiology."

@sfu_fhs doctoral students win awards to support their interdisciplinary research.  

https://t.co/lIHQLctENP

[Lawrence McCandless @LCMcCandless]

Quantile regression should be more widely used to measure weak effects in epidemiology.  Great example: 

Associations between ambient air pollutant concentrations and birth weight: A quantile regression analysis.

https://t.co/QcbNTtDt1i

[Sherri Rose @sherrirose]

Important shift in the clinical literature. @NEJM releases new guidelines for statistical reporting of p-values. https://t.co/QHV78aKtIM

[Lawrence McCandless @LCMcCandless]

Using simulation studies to evaluate statistical methods

Tutorial in Biostatistics in Statistics in Medicine

https://t.co/g4kDySKP0E

https://t.co/JBkWeRlM0y

[Lawrence McCandless @LCMcCandless]

New paper by @GhassanHamraPhD on Bayesian analysis of 25 highly correlated biomarkers of environmental chemical exposures.

Prenatal exposure to endocrine disrupting chemicals in relation to autism spectrum disorder and intellectual disability.

https://t.co/KpXroAU111

[SFU Health Sciences @SFU_FHS]

Missed Sander Greenland's presentation of "Statistics as a condemned building: A demolition and reconstruction plan" on February 15 at #SFU?

Watch the video recording online here: https://t.co/KdLYfPMY8e

@Lester_Domes @CANSSIINCASS

[Lawrence McCandless @LCMcCandless]

New study led by my trainee Brendan Bernardo using Bayesian analysis of the MIREC Study. We examine PCB exposure during pregnancy and autistic behaviour in children, with new Bayesian measurements of uncertainty and effect size

https://t.co/a1GaWHFylg

[Lawrence McCandless @LCMcCandless]

New study by trainee Tian Li. We analyze data from an RCT of Housing First as a means of ending homelessness for people living with mental illness in Vancouver. Used Bayesian sensitivity analysis to measure the impact of non-ignorable dropout

https://t.co/xhSeW5B13a

[SER @societyforepi]

47 editors of 35 respiratory, sleep, and critical care journals made recommendations for increasing rigor and validity in observational studies. What do you think? https://t.co/gcKbPriZTv

[Lawrence McCandless @LCMcCandless]

@randyboyes @SFU_FHS @bharath_kv @Lester_Domes @CANSSIINCASS The link should be posted in just over a week.

[Lawrence McCandless @LCMcCandless]

Delighted to announce that Sander Greenland will present: “Statistics as a condemned building: A demolition and reconstruction plan.“

Feb 15 1530-1630 at Simon Fraser University, Faculty of Health Sciences, room SWH10081 (Saywell Hall)

@SFU_FHS @Lester_Domes @CANSSIINCASS

[IJERPH @IJERPH_MDPI]

Interesting article on Assessing the Relation between Plasma PCB Concentrations and Elevated Autistic Behaviours using Bayesian Predictive Odds Ratios.

#autism #PCB
https://t.co/AvNE6uJ2rh