Metholodogy
Lowy Institute Indonesia Poll 2021 — Charting their own course: How Indonesians see the world reports the results of a national survey of 3000 Indonesian adults conducted between 29 November and 24 December 2021. The questionnaire was developed by the authors, using the baseline of the Lowy Institute’s 2011 Indonesia Poll. The order of questions in the questionnaire was different from the order presented in this report.
The survey was conducted by Ipsos in Indonesia using a stratified random door-to-door sample with maximum 40 minutes length of interview across 33 provinces (i.e. all provinces of Indonesia excluding Kalimantan Utara). Quotas were set for each province, with broad age group and gender quotas, according to data from the Indonesian Central Agency on Statistics from 2020. Interviewers continued to seek respondents until each quota was filled and applied a Kish Grid where there was the possibility of having more than one member of a household that met the sample criteria. This technique ensures that respondents in the household are selected randomly. Face-to-face surveys continue to be the most reliable means of achieving accurate, nationally representative samples in Indonesia, particularly when there is a question of internet and phone access across a large and dispersed population.
On a simple random sample of 3000 responses, the approximate margin of error is 1.8%, which means there is a 95% chance that responses from the sample fall within a range of 1.8% either side of the notional collective response of the whole population. Since these samples were stratified (by state/territory, age group and gender), the error figure is a guide only. Where the results for a sub-sample are reported, the margin of error is greater. The sampling method employed means that results are generalisable to the national population and sampling errors and confidence intervals can be calculated.
Data quality checks for the survey included checks for ‘speeding’ (completing the survey rapidly when using computer-assisted programming) and ‘straight-lining’ (providing the same answer to every question of a bank of items with the same response options). Pilot interviews were conducted prior to fieldwork commencing and approximately 30% of respondents were called back by telephone to confirm that they had completed the survey as a part of quality control measures.
While the sample is nationally representative and clearly aligns with the 2020 Indonesian census data in terms of age, socio-economic status and location, the sample appears to over-represent respondents that identify with PDI-P as a party and say that they voted for President Joko Widodo in the 2019 presidential election. This may reflect a level of social desirability bias in the respondents.
Acknowledgements
Several questions in this report were modelled on those developed by other polling organisations, including the Pew Research Center, Australian Election Study, ANUPoll, and the Chicago Council on Global Affairs. Fieldwork was managed by Ambrosius Kenny and Dede Udayana from Ipsos Indonesia. John Davis of OmniPoll and Djayadi Hanan provided independent consulting and reviewed the questionnaire design. Edward Aspinall, Santo Darmosumarto, Greg Fealy, Dewi Fortuna Anwar, Frega Inkiriwang and Rizal Sukma provided feedback on the preliminary survey questions and design. Xuyang Dong, Teesta Prakash and Clare Caldwell of the Lowy Institute assisted in the preparation of the report. Ian Bruce and Brody Smith designed the report website.
The Indonesia Poll 2021 — Charting their own course: How Indonesians see the world survey and report is supported by the Department of Foreign Affairs and Trade. Responsibility for the views, information and advice expressed in this report are those of the authors and do not necessarily reflect the views of the Lowy Institute or the Australian government.