# Estimating the Demand Function for Residential City Gas in South Korea: Findings from a Price Sensitivity Measurement Experiment

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

^{3}a year, showing a penetration rate of 83%. Since there are still small and medium-sized urban areas that want to receive RCG but cannot be supplied, CG operators are continuously expanding their investment in areas without piping networks. In addition, as the CG pipe network, which has been installed for 40 years, becomes superannuated, the project to replace the old pipe network with a new one is actively underway.

## 2. Methodology

#### 2.1. Review of Previous Related Studies

#### 2.2. Method

#### 2.3. Step 1: Establishing Hypothetical Price Change Alternatives

#### 2.4. Step 2: Collecting Data through a Survey

#### 2.5. Step 3: Analyzing Collected Data

## 3. Results

#### 3.1. Data

^{3}, the average monthly income of respondent households, and the total number of members of respondent households, respectively. In addition, $D$, $H$, and $M$ indicate whether respondents’ households use CG only for cooking, whether respondents’ households use an individual heating system, and whether the respondent lives in the Seoul Metropolitan area.

#### 3.2. Results

^{2}, standard errors of regression (SER), and Akaike information criterion (AIC). In general, a larger adjusted-R

^{2}is preferred, and a smaller SER and AIC. In addition, to comparing the predictive power among models, the root mean square percent error (RMS%E) is estimated for all models. The model with this smallest value can be considered the model with the highest predictive power.

^{2}, the smallest SER, the smallest AIC, and the smallest RMS%E. The price elasticity of demand was obtained as −0.570, securing statistical significance. Since its absolute value is less than 1, it can be seen that demand is inelastic in relation to price change. The income elasticity was found to be 0.038, holding statistical significance. Thus, demand is also inelastic in respect of income change.

^{2}, the smallest SER, the smallest AIC, and the smallest RMS%E was Model 6. The price and income elasticities of demand were revealed as –0.512 and 0.069, respectively, and both had statistical significance. The qualitative interpretation of the magnitude of these two elasticities is not different from the estimation results using the LS method.

## 4. Discussion

^{3}. This value is useful for computing the economic benefits arising from enforcing a new RCG supply project: in other words, the economic benefit of carrying out the project to supply 1 million m

^{3}of RCG every year amounts to around KRW 2.1 billion.

## 5. Conclusions

^{2}, SER, AIC, and RMS%E were employed.

## Author Contributions

## Funding

## Institutional Review Board Statement

## Informed Consent Statement

## Data Availability Statement

## Conflicts of Interest

## References

- Anozie, A.N.; Bakare, A.R.; Sonibare, J.A.; Oyebisi, T.O. Evaluation of cooking energy cost, efficiency, impact on air pollution and policy in Nigeria. Energy
**2007**, 32, 1283–1290. [Google Scholar] [CrossRef] - Permadi, D.A.; Sofyan, A.; Oanh, N.T.K. Assessment of emissions of greenhouse gases and air pollutants in Indonesia and impacts of national policy for elimination of kerosene use in cooking. Atmos Environ.
**2017**, 154, 82–94. [Google Scholar] [CrossRef] [Green Version] - Lim, H.J.; Yoo, S.H. Natural gas consumption and economic growth in Korea: A causality analysis. Energy Sources B Econ. Plan Policy
**2012**, 7, 169–176. [Google Scholar] [CrossRef] - Jang, J.; Lee, J.; Yoo, S.H. The public’s willingness to pay for securing a reliable natural gas supply in Korea. Energy Policy
**2014**, 69, 3–13. [Google Scholar] [CrossRef] - Kim, H.J.; Lim, S.Y.; Yoo, S.H. Are Korean households willing to pay a premium for induction cooktops over gas stoves? Sustainability
**2017**, 9, 1546. [Google Scholar] [CrossRef] [Green Version] - Kim, H.J.; Lim, S.Y.; Yoo, S.H. The convenience benefits of the district heating system over individual heating systems in Korean households. Sustainability
**2017**, 9, 1348. [Google Scholar] [CrossRef] [Green Version] - Beierlein, J.G.; Dunn, J.W.; McConnon, J.C. The demand for electricity and natural gas in the Northeastern United States. Rev. Econ. Stat.
**1981**, 63, 403–408. [Google Scholar] [CrossRef] - Blattenberger, G.R.; Taylor, L.D.; Rennhack, R.D. Natural gas availability and the residential demand for energy. Energy J.
**1983**, 4, 23–45. [Google Scholar] [CrossRef] - Herbert, J.H. Data analysis and the estimation of aggregate natural gas demand per customer. J. Econ. Soc. Meas.
**1986**, 4, 165–174. [Google Scholar] [CrossRef] - Lee, R.S.; Singh, N. Patterns in residential gas and electricity consumption: An econometric analysis. J. Econ. Soc. Meas.
**1994**, 12, 165–174. [Google Scholar] - Balestra, P.; Nerlove, M. Pooling cross section and time series data in the estimation of a dynamic model: The demand for natural gas. Econometrica
**1996**, 34, 585–612. [Google Scholar] [CrossRef] - Cordano, A.L.V.; Zellou, A.M. Super cycles in natural gas prices and their impact on Latin American energy and environmental policies. Res. Policy
**2020**, 65, 101513. [Google Scholar] [CrossRef] - Gong, C.; Gong, N.; Qi, R.; Yu, S. Assessment of natural gas supply security in Asia Pacific: Composite indicators with compromise Benefit-of-the-Doubt weights. Res. Policy
**2020**, 67, 101671. [Google Scholar] [CrossRef] - Yoo, S.H.; Lim, H.J.; Kwak, S.J. Estimating the residential demand function for natural gas in Seoul with correction for sample selection bias. Appl. Energy
**2009**, 86, 460–465. [Google Scholar] [CrossRef] - Payne, J.E.; Loomis, D.; Wilson, R. Residential natural gas demand in Illinois: Evidence from the ARDL bounds testing approach. J. Reg. Anal. Policy
**2011**, 41, 138–147. [Google Scholar] - Wadud, Z.; Dey, H.S.; Kabir, M.A.; Khan, S.I. Modeling and forecasting natural gas demand in Bangladesh. Energy Policy
**2011**, 39, 7372–7380. [Google Scholar] [CrossRef] [Green Version] - Dagher, L. Natural gas demand at the utility level: An application of dynamic elasticities. Energy Econ.
**2012**, 34, 961–969. [Google Scholar] [CrossRef] - Ota, T.; Kakinaka, M.; Kotani, K. Demographic effects on residential electricity and city gas consumption in the aging society of Japan. Energy Policy
**2018**, 115, 503–513. [Google Scholar] [CrossRef] [Green Version] - Gautam, T.K.; Paudel, K.P. The demand for natural gas in the Northeastern United States. Energy
**2018**, 158, 890–898. [Google Scholar] [CrossRef] - Alberini, A.; Khymych, O.; Ščasný, M. Responsiveness to energy price changes when salience is high: Residential natural gas demand in Ukraine. Energy Policy
**2020**, 144, 111534. [Google Scholar] [CrossRef] - Kostakis, I.; Lolos, S.; Sardianou, E. Residential natural gas demand: Assessing the evidence from Greece using pseudo-panels, 2012–2019. Energy Econ.
**2021**, 99, 105301. [Google Scholar] [CrossRef] - Filippini, M.; Kumar, N. Gas demand in the Swiss household sector. Appl. Econ. Lett.
**2021**, 28, 359–364. [Google Scholar] [CrossRef] - Li, J.M.; Dong, X.C.; Jiang, Q.Z.; Dong, K.Y. Urban natural gas demand and factors analysis in China: Perspectives of price and income elasticities. Pet. Sci.
**2022**, 19, 429–440. [Google Scholar] [CrossRef] - Burke, P.J.; Yang, H. The price and income elasticities of natural gas demand: International evidence. Energy Econ.
**2016**, 59, 466–474. [Google Scholar] [CrossRef] [Green Version] - Malzi, M.J.; Ettahir, A. Responsiveness of residential natural gas demand to elderly, urban population and density: Evidence from organization for economic Co-operation and development countries. Int. J. Energy Econ. Policy
**2019**, 9, 388. [Google Scholar] [CrossRef] - Malzi, M.J.; Sohag, K.; Vasbieva, D.G.; Ettahir, A. Environmental policy effectiveness on residential natural gas use in OECD countries. Res. Policy
**2020**, 66, 101651. [Google Scholar] [CrossRef] - Lewis, R.C.; Shoemaker, S. Price-sensitivity measurement: A tool for the hospitality industry. Cornell Hotel Restaur. Adm. Q.
**1997**, 38, 44–54. [Google Scholar] [CrossRef] - Raab, C.; Mayer, K.; Kim, Y.S.; Shoemaker, S. Price-sensitivity measurement: A tool for restaurant menu pricing. J. Hosp. Tour. Res.
**2009**, 33, 93–105. [Google Scholar] [CrossRef] - Lim, S.Y.; Min, J.S.; Yoo, S.H. Price and income elasticities of residential heat demand from district heating system: A price sensitivity measurement experiment in South Korea. Sustainability
**2021**, 13, 7242. [Google Scholar] [CrossRef] - Bassett, G.; Koenker, R. Asymptotic theory of least absolute error regression. J. Am. Stat. Assoc.
**1978**, 73, 618–622. [Google Scholar] [CrossRef] - Alexander, D.L.; Kern, W.; Neil, J. Valuing the consumption benefits from professional sports franchises. J. Urban Econ.
**2000**, 48, 321–337. [Google Scholar] [CrossRef]

Variables | Definitions | Minimum | Maximum | Skewness | Kurtosis | Median | First Quartile | Third Quartile | Mean | Standard Deviation | Expected Sign |
---|---|---|---|---|---|---|---|---|---|---|---|

RCG | Household consumption of residential city gas (RCG) per month (unit: m^{3}) | 2.40 | 333.00 | 1.10 | 2.91 | 55.00 | 33.00 | 74.00 | 57.33 | 34.47 | |

P | Price of RCG (unit: KRW per m^{3}) | 88.24 | 2666.67 | 0.95 | 0.47 | 1028.57 | 875.00 | 1333.33 | 1132.56 | 340.95 | (−) |

Y | Household income per month (unit: KWR 1 million = USD 870) | 1.00 | 20.00 | 1.23 | 3.91 | 4.80 | 3.50 | 6.00 | 5.02 | 2.15 | (+) |

F | Number of members in the respondent household | 1.00 | 7.00 | −0.27 | −0.19 | 4.00 | 2.00 | 4.00 | 3.30 | 1.11 | (+) |

D | Whether the respondent uses RCG only for cooking (0 = no; 1 = yes) | 0.00 | 1.00 | −2.28 | 3.20 | 1.00 | 1.00 | 1.00 | 0.88 | 0.33 | (−) |

H | Whether the heating method of the household is an individual heating system (0 = no; 1 = yes) | 0.00 | 1.00 | −2.30 | 3.27 | 1.00 | 1.00 | 1.00 | 0.87 | 0.33 | (+) |

M | Whether the respondent resides in the Seoul Metropolitan area (0 = no; 1 = yes) | 0.00 | 1.00 | −0.14 | −1.98 | 1.00 | 0.00 | 1.00 | 0.53 | 0.50 | (?) |

Variables ^{1} | Model 1 | Model 2 | Model 3 | Model 4 | Model 5 | Model 6 |
---|---|---|---|---|---|---|

Constant | 8.194 * (27.04) | 7.388 * (40.57) | 7.271 * (37.22) | 6.742 * (33.35) | 7.424 * (40.74) | 7.316 * (37.39) |

$\mathrm{ln}P$ | −0.676 * (−17.85) | −0.567 * (−25.25) | −0.566 * (−25.18) | −0.576 * (−24.52) | −0.572 * (−25.44) | −0.570 * (−25.36) |

$\mathrm{ln}Y$ | 0.058 * (2.31) | 0.035 * (2.07) | 0.035 * (2.07) | 0.199 * (12.83) | 0.038 * (2.23) | 0.038 * (2.23) |

$\mathrm{ln}F$ | 0.359 * (20.00) | 0.358 * (19.97) | 0.361 * (20.13) | 0.361 * (20.11) | ||

D | −1.764 * (−88.64) | −1.660 * (−25.41) | −1.626 * (−23.83) | −1.745 * (−84.32) | −1.650 * (−25.25) | |

H | 0.109 ^{#}(1.66) | 0.122 ^{#}(1.79) | 0.100 (1.52) | |||

M | −0.033 * (−2.32) | −0.045 * (−3.30) | −0.044 * (−3.23) | |||

F-values | 161.30 * | 2278.22 * | 1823.84 * | 1602.88 * | 1828.82 * | 1524.85 * |

(p-values) | (0.000) | (0.000) | (0.000) | (0.000) | (0.000) | (0.000) |

Adjusted-R^{2} | 0.068 | 0.673 | 0.673 | 0.644 | 0.674 | 0.674 |

Standard error of regression | 0.7319 | 0.4335 | 0.4334 | 0.4523 | 0.4330 | 0.4330 |

Akaike information criterion | 4904.9 | 2585.8 | 2585.4 | 2773.9 | 2581.4 | 2581.2 |

RMS%E ^{2} | 32.131 | 13.905 | 13.899 | 14.421 | 13.862 | 13.857 |

Sample size | 4430 | 4430 | 4430 | 4430 | 4430 | 4430 |

^{1}Explained in Table 1.

^{2}RMS%E denotes the root mean square percent error. * and

^{#}denote statistical significance at the 5% and 10% levels, respectively. t-values are given in parentheses below the estimates.

Variables ^{1} | Model 1 | Model 2 | Model 3 | Model 4 | Model 5 | Model 6 |
---|---|---|---|---|---|---|

Constant | 7.631 * (35.31) | 6.821 * (47.74) | 6.644 * (43.37) | 6.511 * (41.08) | 6.787 * (47.46) | 6.636 * (43.26) |

$\mathrm{ln}P$ | −0.648 * (−24.00) | −0.509 * (−28.87) | −0.509 * (−28.91) | −0.518 * (−28.14) | −0.510 * (−28.94) | −0.512 * (−29.02) |

$\mathrm{ln}Y$ | 0.144 * (8.09) | 0.062 * (4.71) | 0.063 * (4.73) | 0.163 * (13.40) | 0.071 * (5.32) | 0.069 * (5.24) |

$\mathrm{ln}F$ | 0.359 * (25.47) | 0.357 * (25.38) | 0.370 * (26.32) | 0.366 * (26.01) | ||

D | −1.807 * (−115.75) | −1.626 * (−31.73) | −1.598 * (−29.87) | −1.798 * (−110.77) | −1.623 * (−31.67) | |

H | 0.182 * (3.54) | 0.179 * (3.34) | 0.175 (3.40) | |||

M | −0.015 (−1.32) | −0.036 * (−3.38) | −0.037 * (−3.48) | |||

F-values | 258,565.4 * | 575,844.1 * | 576,797.9 * | 532,772.7 * | 576,797.2 * | 578,049.2 * |

(p-values) | (0.000) | (0.000) | (0.000) | (0.000) | (0.000) | (0.000) |

Adjusted-R^{2} | 0.065 | 0.672 | 0.672 | 0.643 | 0.672 | 0.673 |

Standard error of regression | 0.7503 | 0.4342 | 0.4341 | 0.4533 | 0.4340 | 0.4338 |

Akaike information criterion | 4624.1 | 2728.3 | 2725.9 | 2913.1 | 2724.8 | 2722.2 |

RMS%E ^{2} | 34.643 | 13.869 | 13.888 | 14.560 | 13.818 | 13.842 |

Sample size | 4430 | 4430 | 4430 | 4430 | 4430 | 4430 |

^{1}Explained in Table 1.

^{2}RMS%E denotes the root mean square percent error. * denotes statistical significance at the 5%. t-values are given in parentheses below the estimates.

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Kim, J.-H.; Hwang, B.-S.; Yoo, S.-H.
Estimating the Demand Function for Residential City Gas in South Korea: Findings from a Price Sensitivity Measurement Experiment. *Sustainability* **2022**, *14*, 7229.
https://doi.org/10.3390/su14127229

**AMA Style**

Kim J-H, Hwang B-S, Yoo S-H.
Estimating the Demand Function for Residential City Gas in South Korea: Findings from a Price Sensitivity Measurement Experiment. *Sustainability*. 2022; 14(12):7229.
https://doi.org/10.3390/su14127229

**Chicago/Turabian Style**

Kim, Ju-Hee, Byoung-Soh Hwang, and Seung-Hoon Yoo.
2022. "Estimating the Demand Function for Residential City Gas in South Korea: Findings from a Price Sensitivity Measurement Experiment" *Sustainability* 14, no. 12: 7229.
https://doi.org/10.3390/su14127229