Primary data on "Sensitivity analyses for data missing at random versus missing not at random using Latent Growth Modelling: A practical guide for randomised controlled trials"

Other Areas

Authors(s) / Creator(s)

Staudt, Andreas
Baumann, Sophie

Abstract

The data come from the PRINT study ("Testing a proactive expert system intervention to prevent and to quit at-risk alcohol use"), a randomized controlled trial. The sample of alcohol consumers from the general population (N = 1646) was randomized into an intervention and control group. All alcohol consumers were included in the study, regardless of the amount consumed. Standardized assessments took place at baseline, 3, 6, 12 and 36 months. The intervention group received three individualized feedback letters at baseline, after 3 and 6 months. The letters were automatically compiled by a computer-based expert system according to predefined decision rules and were based on the self-report data of the study participants at the respective measurement points. The letters contained individualized feedback on alcohol consumption, alcohol-related risk, motivation to change and other psychological variables (self-efficacy, decision balance, behavior change strategies). The intervention was based on the Transtheoretical Model of Behavior Change. The control group did not receive any feedback. The aim was to reduce the average amount of drinking after 12 or 36 months.

Persistent Identifier

https://doi.org/10.5160/psychdata.stas21pr11

Year of Publication

2022

Funding

German Research Foundation (BA 5858/2-1, BA 5858/2-3)

Citation

Staudt, A. & Baumann, S. (2022). Primary data on "Sensitivity analyses for data missing at random versus missing not at random using Latent Growth Modelling: A practical guide for randomised controlled trials" (Version 1.0.0) [Data and Documentation]. Trier: Research Data Center at ZPID. https://doi.org/10.5160/psychdata.stas21pr11

Study Description

Research Questions/Hypotheses:

The aim of this work was to illustrate sensitivity analyses for different missing data mechanisms (missing at random vs. missing not at random) using latent growth curve modelling. This can be used to answer the question: How do conclusions about intervention efficacy change if one alters the assumptions about the process that resulted in missing data?

Research Design:

Fully standardised survey instrument (provides question formulation and answer options); repeated measurement

Measurement Instruments/Apparatus:

The information in the data set was completely self-reported, with the exception of the randomised group membership ("aprint")and the variable "rgroup", which contains each person's membership in one of 16 possible patterns of missing values. Allquestions had a closed response format. Only age ("age") was asked with a free text field. The question on "sex" had two responseoptions (male and female). To record the educational background, the participants were asked about their highest school-leavingqualification. For this purpose, they were presented with an exhaustive list of possible degrees, which were then transferred intothe dichotomous variable "edu". The variable "together" (relationship status) was formed from several sub-questions, namelyquestions on marital status (single, married living together or separated, divorced, widowed), current relationship (if not married)and living situation (do you live with your partner?). The variables "aauditc" to "eauditc" each contain the AUDIT-C score, thesum score of the first three questions of the Alcohol Use Disorders Identification Test. The AUDIT-C score at baseline ("aauditc")was used to form the alcohol-related risk "arisk", using gender-specific cut-offs (4 or more for women and 5 or more for men).Further information can be found in the published study protocol (Baumann et al., BMC Public Health 2018).

Data Collection Method:

Survey in the presence of an investigator

  • computer-assisted
  • special apparatus or measuring instruments, namely
    Baseline: Questionnaire on tablet PCs; All further measurement time points: Computer-assisted telephone interviews

Survey in the absence of an investigator

  • telephone survey
  • online survey

Population:

Alcohol consumers from the general population

Survey Time Period:

5 measurement points: T0 (baseline), T1 (3 months later), T2 (6 months later), T3 (12 months later), T4 (36 months later).

Sample:

Full survey; others: Over a period of 2.5 months, all clients appearing in the waiting area of the registration office in Greifswald were proactively approached by study assistants. All clients who met the inclusion criteria and provided written informed consent were included in the study.

Gender Distribution:

56 % female participants
44 % male participants

Age Distribution: 18-64 years

Spatial Coverage (Country/Region/City): Germany/-/Greifswald

Subject Recruitment:

  • Proactive recruitment of all clients in the waiting area of the residents' registration office in Greifswald by study assistants
  • A total of 3 x 5,- EUR voucher as incentive (baseline, T3 and T4)
  • Advance announcement of follow-up surveys by letter or e-mail in advance
  • At least 10 telephone contact attempts per measurement point
  • Mailing of questionnaires (paper-pencil or online) with a reminder letter if participants could not be reached by telephone
  • Address research via population registers

Sample Size:

1646 individuals

Return/Drop Out:

Response rates:

  • T1: 85% (n = 1407)
  • T2: 81% (n = 1335)
  • T3: 80% (n = 1314)
  • T4: 65% (n = 1074)

stas21pr11_readme.txt
Text file - 5 KB
Sharing Level 1 (Scientific Use)
Description: Description of the files

stas21pr11_pd.txt
Text file - 62 KB
MD5: 2807108ce7950727c9d73f4739869072
Sharing Level 1 (Scientific Use)
Description: Primary data file

stas21pr11_kb.txt
Text file - 3 KB
Sharing Level 1 (Scientific Use)
Description: Codebook for the primary data file stas21pr11_pd.txt

1a_uncond_lgm_linear.inp.txt
Text file - 1 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 1a input – Preliminary model with linear growth factor

1a_uncond_lgm_linear.out.txt
Text file - 12 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 1a output – Preliminary model with linear growth factor

1b_uncond_lgm_quadratic.inp.txt
Text file - 1 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 1b input – Preliminary model with quadratic growth factor

1b_uncond_lgm_quadratic.out.txt
Text file - 14 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 1b output – Preliminary model with quadratic growth factor

1c_uncond_lgm_cubic.inp.txt
Text file - 1 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 1c input – Preliminary model with cubic growth factor

1c_uncond_lgm_cubic.out.txt
Text file - 16 KB
Sharing Level 1 (Scientific Use)
Description: Mplus Syntax 1c output – Preliminary model with cubic growth factor

2a_unadj_mar_model.inp.txt
Text file - 2 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 2a input – Unadjusted MAR model

2a_unadj_mar_model.out.txt
Text file - 25 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 2a output – Unadjusted MAR model

2b_adj_mar_model.inp.txt
Text file - 3 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 2b input – Adjusted MAR model

2b_adj_mar_model.out.txt
Text file - 44 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 2b output – Adjusted MAR model

3a_dk_survival_indicators.inp.txt
Text file - 3 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3a input – Diggle Kenward selection model with survival indicators

3a_dk_survival_indicators.out.txt
Text file - 51 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3a output – Diggle Kenward selection model with survival indicators

3b_dk_multinomial_indicators.inp.txt
Text file - 4 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3b input – Diggle Kenward selection model with multinomial missing indicators

3b_dk_multinomial_indicators.out.txt
Text file - 63 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3b output – Diggle Kenward selection model with multinomial missing indicators

3c_wc_survival_indicators.inp.txt
Text file - 4 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3c input – Wu Carroll shared parameter model with survival indicators

3c_wc_survival_indicators.out.txt
Text file - 42 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3c output – Wu Carroll shared parameter model with survival indicators

3d_wc_multinomial_indicators.inp.txt
Text file - 4 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3d input – Wu Carroll shared parameter model with multinomial indicators

3d_wc_multinomial_indicators.out.txt
Text file - 50 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3d output – Wu Carroll shared parameter model with multinomial indicators

3e_pattern_mixture_cc.inp.txt
Text file - 5 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3e input – Pattern mixture model with complete case missing variable restriction

3e_pattern_mixture_cc.out.txt
Text file - 58 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3e output – Pattern mixture model with complete case missing variable restriction

3f_pattern_mixture_nc.inp.txt
Text file - 5 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3f input – Pattern mixture model with neighbouring case missing variable restriction

3f_pattern_mixture_nc.out.txt
Text file - 58 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3f output – Pattern mixture model with neighbouring case missing variable restriction

3g_pattern_mixture_ac.inp.txt
Text file - 5 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3g input – Pattern mixture model with available case missing variable restriction

3g_pattern_mixture_ac.out.txt
Text file - 58 KB
Sharing Level 1 (Scientific Use)
Description: MPlus Syntax 3g output – Pattern mixture model with available case missing variable restriction

Position Name Label Valid Values Missing Values
1 ID Identification variable 1-1646 "sequential identification number" -9999 "missing value: not specified"
2 SEX sex 0 "male" 1 "female" -9999 "missing value: not specified"
3 AGE Age in years 18-64 "Age in years" -9999 "missing value: not specified"
4 EDU Educational background 0 "less than 12 years of school education" 1 "12 or more years of school education" -9999 "missing value: not specified"
5 TOGETHER Living together with a partner 0 "no" 1 "yes" -9999 "missing value: not specified"
6 HEALTH Self-reported health in general 1 "excellent" 2 "very good" 3 "good" 4 "fair" 5 "poor" -9999 "missing value: not specified"
7 SMOKE Smoking 0 "non-smokers (never and former smokers)" 1 "current smokers (occasional and daily smokers)" -9999 "missing value: not specified"
8 ARISK Alcohol-related risk level at baseline 0 "low-risk alcohol use (AUDIT-C sum score < 4 for women and < 5 for men)" 1 "at-risk alcohol use (AUDIT-C sum score >= 4 for women and >= 5 for men)" -9999 "missing value: not specified"
9 APRINT Study condition 0 "control group" 1 "intervention group" -9999 "missing value: not specified"
10 AAUDITC AUDIT-C sum score at t0 1-12 "AUDIT-C sum score at t0" -9999 "missing value: not specified"
11 BAUDITC AUDIT-C sum score at t1 0-12 "AUDIT-C sum score at t1" -9999 "missing value: not specified"
12 CAUDITC AUDIT-C sum score at t2 0-12 "AUDIT-C sum score at t2" -9999 "missing value: not specified"
13 DAUDITC AUDIT-C sum score at t3 0-12 "AUDIT-C sum score at t3" -9999 "missing value: not specified"
14 EAUDITC AUDIT-C sum score at t4 0-12 "AUDIT-C sum score at t4" -9999 "missing value: not specified"
15 RGROUP Missing data patterns 1-16 "16 missing data patterns" -9999 "missing value: not specified"
Page 1 of 2
Items per page: 10 25 50
Utilized Test Methods
Bush K, Kivlahan DR, McDonell MB, Fihn SD, Bradley KA. The AUDIT alcohol consumption questions (AUDIT-C): an effective brief screening test for problem drinking. Arch Intern Med. 1998;158:1789–95. https://doi.org/10.1001/archinte.158.16.1789.
Further Reading
Baumann S, Staudt A, Freyer-Adam J, Bischof G, Meyer C, John U. Effects of a brief alcohol intervention addressing the full spectrum of drinking in an adult general population sample: a randomized controlled trial. Addiction. 2021;116:2056–66. https://doi.org/10.1111/add.15412.
Baumann S, Staudt A, Freyer-Adam J, John U. Proactive expert system intervention to prevent or quit at-risk alcohol use (PRINT): study protocol of a randomized controlled trial. BMC Public Health. 2018;18(1):851. https://doi.org/10.1186/s12889-018-5774-1
Enders CE, Staudt A, Freyer-Adam J, Meyer C, Ulbricht S, John U, Baumann S. Brief alcohol intervention at a municipal registry office: reach and retention. Eur J Public Health. 2021;31:418–23. https://doi.org/10.1093/eurpub/ckaa195.
Staudt A, Freyer-Adam J, Meyer C, Bischof G, John U, Baumann S. The moderating effect of educational background on the efficacy of a computer-based brief intervention addressing the full spectrum of alcohol use: Randomized controlled trial. JMIR Public Health & Surveillance. 2022;8(6):e33345. https://doi.org/10.2196/33345
Staudt A, Freyer-Adam J, John U, Meyer C, Baumann S. Stability of at-risk alcohol use screening results in a general population sample. Alcohol Clin Exp Res. 2020;44(6):1312-20. https://doi.org/10.1111/acer.14340
Staudt A, Freyer-Adam J, Meyer C, Bischof G, John U, Baumann S. Does prior recall of past week alcohol use affect screening results for at-risk drinking? Findings from a randomized study. PLoS One. 2019;14(6):e0217595. https://doi.org/10.1371/journal.pone.0217595