34 CHAPTER IV Results and Analysis This chapter describes the result and analysis of this study. This chapter begins with an explanation of the analysis and result of the descriptive statistics. Moreover, in the second section it elucidates the result from the MNL also with the respondent demographic characteristics results. IV.1 Introduction This study is aims to understand the potential impacts of autonomous vehicle influencing people’s decision for commuting in IKN. The descriptive statistical analysis was firstly analysed. The respondent of this study coming from the civil servants who work in the Ministry office and they are knowing that their ministry will be moved to IKN, there are 17 different ministry which are occurred in this study. Later the MNL was conducted by using python- Biogeme to analysed the result of stated choice experiment. IV.2 Descriptive Statistic The respondent is collected form civil servant who works in the Ministry of the Republic of Indonesia. A total of 351 respondents that have been gathered by using third party by Populix. IV.2.1 Age Figure IV. 1 Respondent Age A total of 351 respondents have been gathered. As it can be seen in Figure IV.1 the age of the respondents is dominated by respondents aged 36-40 years, with a total of 147 people (42). Respondents with an age range of 30-35 years are the second largest with a total of 86 people (24%), the third is with an age range of 25-29 years with a total of 78 people (22%), the fourth 20-24 1% 25-29 22% 30-35 24% 36-40 42% 46-50 11% >50 0%Age 35 is respondents with an age range of 46-50 years as many as 37 people (11%). Finally, for the 20-24 years, two respondents (1%) and one respondent aged over 50 years (1%). IV.2.2 Gender Figure IV. 2 Respondent Gender As can be seen from Figure IV.2 above. Of a total of 351 respondents, half dominated by female respondents, with 204 respondents (58%), while the rest were male, with 147 respondents (42%). IV.2.3 Income Figure IV. 3 Respondent Income As can be seen from Figure IV.3 above, it can be concluded that the amount of income with the most respondents is Rp. 5,000,000 – 10,000,000 from a total of 351 respondents, there are 134 respondents (38.17%). Furthermore, respondents with a total income of Rp. 10,000,001 – Rp. 15,000,000 were 91 respondents (25.92%). Respondents with an income of Rp. 15,000,001 Male 42% Female 58% Gender Rp 5.000.000 -Rp 10.000.000 38% Rp 10.000.001 - Rp 15.000.000 26% Rp 15.000.001 -Rp 20.000.000 14% Rp 20.000.001 -Rp 25.000.000 17% Rp 25.000.001- Rp 30.000.000 5% > Rp 30.000.001 0%Income 36 – Rp. 20,000,000 as many as 48 respondents (13.67%). Furthermore, for respondents with a total income of Rp. 20,000,001 – 25,000,000, there were 59 respondents (16.80%) out of a total of 351 respondents. Finally, for the income range of Rp. 25,000,0001 – Rp. 30,000,000 and income above Rp. 30,000,001, there were 17 people (4.8%) and 2 people (0.5%) respondents. IV.2.4 Living Area The respondent are came from civil servant who works in some of the Ministry in Jakarta, therefore the respondents which are gathered came from Jakarta Greater Area. It can be seen in Table IV.1 shows the respondent domicile area and the numbers. Table IV.1 Respondent Domicile Domicile N Percentage Jakarta 301 86% Tangerang 18 5% Bekasi 14 4% Depok 8 2% Bogor 5 1.5% Tangerang Selatan 5 1.5% Total 351 100% From Table IV.1 above, the respondents obtained were dominated by people who live in Jakarta with the amount of respondent are 301 peoples or around 86% from the total respondents. Second is from Tangerang with 18 respondents (5%), the third is from Bekasi with 14% respondents (4%), fourth is from Depok with 8 respondents (2%). Lastly, the respondents which gathered from Bogor and Tangerang Selatan are 5 peoples (1.5%) from 351 respondents in total. IV.2.5 Respondent Ministry Background Furthermore, Table IV.2 explains the details of civil servants from which ministries were obtained in this study. Of the 351 data that has been collected, it can be seen there are civil servants from 17 (seventeen) ministries and the remaining 29 (twenty-nine) people who are family members of civil servants who work in the ministry. The highest is from the Ministry of State Secretariat with 38 respondents (9.97%), the second is coming from the Ministry of Trade with 34 respondents (9.68%), third is from the Ministry of Finance with 32 respondents (9.11%). However, the smallest number of respondents in this study are from the Ministry of 37 Manpower and the Ministry of Village, Development of Disadvantaged Regions, and Transmigration, with six respondents being (1.7%). Table IV.2 List of the Ministry Ministry N Percentage Ministry of Public Works and Housing 10 2,84% Ministry of Social Affairs 22 6,26% Ministry of Religious Affairs 23 6,55% Ministry of Stated-Owned Enterprises 12 3,41% Coordinating Ministry for Economic Affairs 14 3,98% Ministry of Manpower 6 1,7% Ministry of Trade 34 9,68% Coordinating Ministry for Human Development and Cultural Affairs 19 5,41% Coordinating Ministry for Political, Legal, and Security Affairs 11 3,13% Coordinating Ministry for Maritime and Investment Affairs 21 5,98% Ministry of State Secretariat 38 9,97% Ministry of National Development Planning 28 7,97% Ministry of Finance 32 9,11% Ministry of State Apparatus Utilization and Bureaucratic Reform 22 6,26% Ministry of Agrarian Affairs and Spatial Planning 14 3,98% Ministry of Foreign Affairs 10 2,84% Ministry of Village, Development of Disadvantaged Regions, and Transmigration 6 1,7% Others 29 8,26% Total 351 100% IV.3 Choice Model Analysis After collecting data from respondents, researchers used multinomial logit (MNL) model techniques with Python-Biogeme to further analysed the data (Bierlaire, 2016). Using MNL, we identify the relevant attributes. The utility is a sign of worth to a person or respondent. According to the utility maximization rule, a person will choose the option from their collection 38 of accessible options that will maximize their utility. The rule assumes that there is a function that describes a person's utility valuation for each alternative and contains attributes of alternatives and personal traits (Kamakura, 1989) In this research, researchers set autonomous vehicle (AV) becomes references alternative. The travel cost (TC) variables are specified as generic in this model. This implies that an increase of one unit of travel cost has the same impact on modal utility for all six modes. It can be seen in Table IV.3 regarding travel cost, which showed that the results of travel cost are negatively significant. Which also indicated that an increase of cost will reduce the probability of people in using the modes.