Handling Missing Data on ALSPAC

1
Handling Missing Data on ALSPAC

• Paul Clarke
• (CMPO, University of Bristol)
• ALSPAC Social Science User Group meeting
• 21 May 2008

2
Outline

• What causes missing data?
• Types of missing data
• Methods for missing data quick overview
• ALSPAC Blitz on non-respondents
• Investigating MNAR data in ALSPAC

3
Example ALSPAC analysis

• At age 11
• Outcome Mood (ordinal, 3 categories)
• Depressive symptoms, maternally rated
• Main exposure Physical activity (score)
• Measured on actigraph, 3 days
• Adjustment
• BMI (score)
• Sex, Age at screening
• Ordinal logistic regression

4
Missing Value (MV) pattern1
1All MV patterns lt 200 cases ignored
5
What causes missing data?
Interviewer effectiveness Incentive for
participant Loyalty
Letter Telephone calls Interviewer visits
Non-contact
6

• Result of processes leading to
• Refusal to answer questions (item)
• Refusal to participate (unit)
• No contact (unit)
• Longitudinal-specific attrition drop-out
• Non-response mechanism(s) - NRM

7
Rubins definitions1

• Missing Completely At Random (MCAR)
• Independent of observed variables
• Missing At Random (MAR)
• NRM depends only on observed variables
• Missing Not At Random (MNAR)
• NRM depends on missing variables too

1Little Rubin (2002) Statistical Analysis with
Missing Data
8
Directed Acyclic Graph (DAG)
Y
X
R
C

• R independent ? data MCAR

9
MAR data
Y
X
R
C

• R indirectly related to Y through X and C

10
Methods for MAR data

• Complete cases analysis/Listwise deletion
• Weighting
• Weighting classes, post-stratification
• (Single) imputation methods
• e.g. regression, hot-deck/nearest-neighbour
• Multiple imputation methods
• e.g. Norm, MICE
• Semiparametric estimators

11
Imputation in practice pitfalls1

• Omitting the outcome
• Imputing non-normal variables
• MAR completely implausible
• Convergence of iterative procedures

1Sterne et al. (2008) British Medical Journal
12
Complex methods

• Analysis model
• e.g. Ordinal logistic regression
• Imputation model Missing given Observed
• ALL assume MAR data

13
MAR data in reality
?
Y
X
R
C

• Unknown factors drive non-response

• correlated with model predictors

• but not with Y

14
Why is this important?

• Weakness of MAR How do we know?
• Central problem missing data is missing!
• MAR is a leap of faith

15
MNAR data
?
Y
X
R
C

• Unknowns directly correlated with Y?

16
Physical activity example
?
Mood
Phys Act
R
BMI, Sex, Age

• NRM is mother-driven (child age 11)
• Child must wear actigraph for 3 days
• Mother must assess her childs mood

17
ALSPAC Blitz

• Co-ordinated by Family Liaison Unit
• 4 tranches Nov 2007-May 2008
• Target 5000 teenagers not in last 2 waves
• Mini-clinic for difficult to persuade

18
Proposed analysis

• MAR is context dependent
• Risky behaviours (Glyn Lewis, et al)
• Outcomes Cannabis use, sexual practices, etc
• Risk factors mental health, sensation seeking,
  etc
• Basic analysis
• Compare follow-up with main sample
• Still differences after adjustment?

19
Unit non-response

• 100 follow-up rate unlikely!
• Directly model NRM
• Continuum of non-response
• Hard to contact less like main sample
• Weighting scheme (Alho 1990 Wood et al. 2006)
• Lower bound for MNAR bias

20
Item non-response

• Parallel qualitative post
• Items questions on risky behaviours
• What mechanisms drive non-response?
• Test hypotheses from this project