1 ALSPAC Data Measures of Childhood Incontinence.

12
1 ALSPAC Data Measures of Childhood Incontinence

Transcript of 1 ALSPAC Data Measures of Childhood Incontinence.

Page 1: 1 ALSPAC Data Measures of Childhood Incontinence.

1

ALSPAC Data

Measures of Childhood Incontinence

Page 2: 1 ALSPAC Data Measures of Childhood Incontinence.

2

Or, if you’re squeamish…

Page 3: 1 ALSPAC Data Measures of Childhood Incontinence.

3

How many kittens do you own?

Page 4: 1 ALSPAC Data Measures of Childhood Incontinence.

4

Repeated questions:

Page 5: 1 ALSPAC Data Measures of Childhood Incontinence.

5

Repeated questions: - Binary

Zero One

Page 6: 1 ALSPAC Data Measures of Childhood Incontinence.

6

Repeated questions: - Ordinal

Zero One Two ~ DSM4 criterion

Page 7: 1 ALSPAC Data Measures of Childhood Incontinence.

7

Repeated questions

• Asked at:

• 4½ years ~ KK• 5½ years ~ KM• 6½ years ~ KP• 7½ years ~ KR • 9½ years ~ KU

Page 8: 1 ALSPAC Data Measures of Childhood Incontinence.

8

Why mixture models?

• Previous work (clinical/epidemiological) has provided evidence for subgroups– Different aetilogies– Different comorbid factors– Different long-term outcomes

• Variability in development poorly captured by standard growth models– Relapsing group

Page 9: 1 ALSPAC Data Measures of Childhood Incontinence.

9

BW frequencies (complete case)Boys Girls

4.5yr

Dry 62% 77%

“Infrequent” 27%38%

17%23%

“Frequent” 11% 6%

5.5yr

Dry 72% 84%

“Infrequent” 21%28%

13%16%

“Frequent” 7% 3%

6.5yr

Dry 76% 87%

“Infrequent” 20%24%

11%14%

“Frequent” 5% 2%

7.5yr

Dry 81% 90%

“Infrequent” 16%19%

9%10%

“Frequent” 3% 1%

9.5yr

Dry 87% 94%

“Infrequent” 11%13%

5%6%

“Frequent” 2% 1%

Page 10: 1 ALSPAC Data Measures of Childhood Incontinence.

10

Infrequent bedwetting

Page 11: 1 ALSPAC Data Measures of Childhood Incontinence.

11

Frequent Bedwetting

Page 12: 1 ALSPAC Data Measures of Childhood Incontinence.

12

Planned models

• LLCA replication of Croudace AJE model– Incorporate covariates into above

• LLCA/LCGA models of frequent wetters (binary)– Assessment of gender invariance with knownclass

• Parallel modelling of day/night wetting• Ordinal modelling of 3-level measures

– Incorporate covariates– Risk of later binary outcome