the purpose of this session to introduce the practice dataset (musp) to examine distributions to...

38
The purpose of this session • To introduce the practice dataset (MUSP) • To examine distributions • To perform a preliminary analysis: know your data!

Upload: patrick-warner

Post on 11-Jan-2016

216 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

The purpose of this session

• To introduce the practice dataset (MUSP)

• To examine distributions

• To perform a preliminary analysis: know your data!

Page 2: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

The MUSP CohortMater-University Study of Pregnancy

• 8556 pregnant women recruited at first antenatal visit 1981-1984 at the Mater Mother’s Hospital, Brisbane

• Follow-up of mother-child sets

Page 3: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

The MUSP cohort

• Follow-ups (mother and child) at delivery + 3 days, 6 months, 5 years, 14 years, 21 years (ongoing)

• Current cohort of approximately 5000

• Some repeated pregnancies, multiple births

Page 4: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Information collected

• Socio-demographic information, health behaviour• Mental health, stressors, family functioning,

relationships• Biological data: pregnancy, delivery history• Physical, developmental assessment of child• Child behaviour • Health outcomes (mother and child)

Page 5: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Data structures

• Individual ID number (codea)

• Longitudinal record

codea a1 a2 a3…b1 b2 b3…c1 c2 c3….

• Restructure for ‘repeated measures’ analysis

Page 6: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Format:

codea a b c1 d1……. c2 d2……. c3 d3…….

1234 1 4 15.2 6….…. 16.6 9……. 18.6 11…….

Format:

codea time a b c d

1234 1 1 4 15.2 6 1234 2 1 4 16.6 91234 3 1 4 18.6 11

Longitudinal file

Stacked filerepeated measures

Time-dependent variables

Time-constant variables

Page 7: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Longitudinal file: mps.SinglePregnancyMother

Used for examining change over time within persons

Stacked file: mps.MentalHealth

Used for repeated measures analysis

Data Sets

Page 8: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

The research questions

• Does mother’s mental health change over time?

• What factors (time-constant, time-dependent) predict mother’s mental health?

• What factors predict change in mother’s mental health?

Page 9: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Mother’s mental health

• 14 ordinal items on a five point scale: summed to make score 10 (good) – 50 (bad)

• Measured at six times so far:FCV, + 3 days, + 6 months, + 5 years,

+ 14 years, + 21 years

• Missing values and attrition

Page 10: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Possible predictors

• Age at First Clinic Visit

• Health status: time-dependent

• …………

Page 11: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Missing values and attrition

• Distribution

• Change over time

• Correlations over time

• Determinants of mental health

Page 12: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Missing values and attrition

Page 13: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Attrition and Missing Values

• Attrition high; include only those present at all phases FCV to +14 yearsN =4470

• Missing values elsewhere on particular items, comparatively infrequent.

Page 14: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Distribution (uses stacked file)

Page 15: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!
Page 16: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!
Page 17: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Change over time – grouped (uses stacked)

Page 18: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Variable Label N Mean Median Std Dev Minimum Maximum Skewness Kurtosis

amh bmh emh hmh kmh nmh

FCV + 3 days + 6 months + 5 years +14 years +21 years

4411 4463 4456 4455 4461 676

15.38 15.06 14.81 16.19 16.63 17.92

14.30 13.60 13.60 15.00 15.70 17.10

4.61 4.67 4.67 5.12 5.50 5.69

10.00 10.00 10.00 10.00 10.00 10.00

50.00 50.00 50.00 44.30 50.00 48.60

1.47 1.87 1.68 1.35 1.19 1.26

3.00 6.57 4.15 2.46 1.48 2.83

Variable Label N Mean Median Std Dev Minimum Maximum Skewness Kurtosis

lamh lbmh lemh lhmh lkmh lnmh

FCV + 3 days + 6 months + 5 years +14 years +21 years

4411 4463 4456 4455 4461 676

1.593 1.515 1.454 1.705 1.749 1.966

1.668 1.526 1.526 1.792 1.902 2.092

0.753 0.790 0.803 0.775 0.805 0.714

0.000 0.000 0.000 0.000 0.000 0.000

3.714 3.714 3.714 3.564 3.714 3.679

-0.278 -0.234 -0.072 -0.397 -0.419 -0.584

-0.465 -0.613 -0.778 -0.404 -0.474 0.047

Summary statistics for mental health score (high=poor)

Summary statistics for log(mental health score-9)

Page 19: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Poor Mental Health

GoodMental Health

Page 20: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Change over time – individual (uses longitudinal)

Page 21: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Poor Mental Health

GoodMental Health

Worsening

Improving

Page 22: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Poor Mental Health

GoodMental Health

Worsening

Improving

Page 23: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Correlations over time

Page 24: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Correlations for mental health score

Pearson Correlation Coefficients Number of Observations

FCV + 3 d + 6 m + 5 y +14y +21y

FCV 1.00000 4411

0.54331 4405

0.52288 4397

0.42221 4398

0.34201 4402

0.31288 665

+ 3 days 0.54331 4405

1.00000 4463

0.50318 4449

0.42270 4449

0.33176 4455

0.33231 674

+ 6 months 0.52288 4397

0.50318 4449

1.00000 4456

0.49279 4441

0.41533 4447

0.36792 675

+ 5 years 0.42221 4398

0.42270 4449

0.49279 4441

1.00000 4455

0.52577 4446

0.37132 673

+14 years 0.34201 4402

0.33176 4455

0.41533 4447

0.52577 4446

1.00000 4461

0.51146 676

+21 years 0.31288 665

0.33231 674

0.36792 675

0.37132 673

0.51146 676

1.00000 676

Page 25: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Correlations for log(mental health score-9)

Pearson Correlation Coefficients Number of Observations

FCV + 3 d + 6 m + 5 y +14y +21y

FCV 1.00000 4411

0.55385 4405

0.52858 4397

0.43313 4398

0.35467 4402

0.36037 665

+ 3 days 0.55385 4405

1.00000 4463

0.55643 4449

0.45615 4449

0.36176 4455

0.35962 674

+ 6 months 0.52858 4397

0.55643 4449

1.00000 4456

0.50648 4441

0.43387 4447

0.40551 675

+ 5 years 0.43313 4398

0.45615 4449

0.50648 4441

1.00000 4455

0.53554 4446

0.43299 673

+14 years 0.35467 4402

0.36176 4455

0.43387 4447

0.53554 4446

1.00000 4461

0.56196 676

+21 years 0.36037 665

0.35962 674

0.40551 675

0.43299 673

0.56196 676

1.00000 676

Page 26: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!
Page 27: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

= 0.456 = 0.684

Page 28: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Determinants of mental health

Page 29: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Marital Status: a89 Frequency Percent Cumulative Frequency

Cumulative Percent

Missing 33 0.74 33 0.74

SINGLE 348 7.79 381 8.52

DE FACTO 374 8.37 755 16.89

MARRIED 3638 81.39 4393 98.28

SEPARATED-DIVORCED 70 1.57 4463 99.84

WIDOWED 6 0.13 4469 99.98

PARTNER IN PRISON 1 0.02 4470 100.00

Marital Status at FCV

Combine “Other”

Page 30: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Poor Mental Health

GoodMental Health

Page 31: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Means 2xSEM

Excluding “missing” and “other”Poor Mental Health

GoodMental Health

Page 32: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Single mothers poorer mental health at FCV, same at 6m, then widening gap

Poor Mental Health

GoodMental Health

Page 33: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Descriptive analysis

• Determinants of mental health (time-dependent)

Page 34: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Health Status at 5, 14 and 21 years

Table of HStatus by time

HStatus(Health Status) time

Frequency Col Pct

+ 5 years

+14 years

+21 years Total

Missing 6 0.13

7 0.16

1 0.15

14

Excellent 1061 23.74

993 22.21

76 11.23

2130

Good 2603 58.23

2445 54.70

291 42.98

5339

Fair 687 15.37

872 19.51

234 34.56

1793

Poor 113 2.53

153 3.42

60 8.86

326

Very Poor 0 0.00

0 0.00

15 2.22

15

Total 4470 4470 677 9617

Frequency Missing = 3793

Page 35: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Better physical health, better mental health, at all times

Poor Mental Health

GoodMental Health

Physical Health

Page 36: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Better physical health, better mental health, at all times, association stronger at 14 years

Poor Mental Health

GoodMental Health

Physical HealthTime

Page 37: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

Poor Mental Health

GoodMental Health

Time

Poor Physical Health

Excellent Physical Health

Page 38: The purpose of this session To introduce the practice dataset (MUSP) To examine distributions To perform a preliminary analysis: know your data!

The MUSP dataset

• The subset available for all phases to 21 years (N = 667)in a ‘stacked’ file: MentalHealth

• Outcome: Logged maternal mental health score

• Time-constant variables: At FCV: Marital status, Income, Education, Age group, Number of previous pregnancies, Country of birth, Time in Australia

• Time-dependent variables: Physical health status