Electric Power Corporation Customer Satisfaction Survey 2014
Suesuega mo i latou o loo faaogaina le eletise, 2014
The EPC-Customer Satisfaction Survey 2014 collected information to obtain and establish a baseline for customer's satisfaction on the EPC services and to identify the areas of the corporation's services that need improvement. The CSS results are planned to provide updated information to design new strategies for improving the services of the corporation. The overall outcome of the CSS 2014 is to assist and recommend relevant strategies to improve and upgrade the service of the EPC to its clients.The Customer Satisfaction Survey 2014 was conducted on the domestic or household level as well as all the other types of customers registered with the corporation.
Kind of Data
Sample survey data [ssd]
v01: cleaned data de-identified.
Unit of Analysis
EPC customers such as domestic, commercial, school, religion, government, industrial, hotels
EPC users or customers
Producers and sponsors
Authoring entity/Primary investigators
Samoa Bureau of Statistics
Electric Power Corporation
Electric Power Corporation
Samoa Bureau of Statistics
Ministry of Finance - Budget Division
Processing of payment for survey resources to the suppliers and personnel salaries using government finance systems.
There were seven types of customers, namely: domestic, commercial, religion, school, government, hotel and industrial in the EPC frame or their list of population which was given to SBS for sampling selection. It took several months for both parties to sort the list of registered customers with the corporation especially the domestic clients, so that they can be easily searched and identified during the field work or data collection period, therefore the SBS offered it list of households as part of domestic customers for the EPC to avoid the delay with the survey timeframe.
The total number of households with SBS was 26,205 which were counted from the latest census of population and housing 2011. Out of that total households with SBS, 25,262 or 96percent of households were with electricity. The total number of customers proposed by the corporation was about 200 in which 100 from the domestic and 80 from the other types of customers, however to accommodate the non response cases, the SBS increased the sample size to 250 in which 150 were from household or domestic customers and 100 from other types of customers.
The sample of domestic customers for the CSS 2014 was drawn from the master sample frame of the list of occupied households compiled in the most recent Population and Housing Census 2011. The sample size was based on a 95 percent confidence interval of ± 5 percent margin of error. This means that if the survey found that 50 percent of respondents were satisfied with induction meter services of EPC, we could be 95 percent sure of getting the same result had we interviewed everyone in the population give or take 5 percent. An 80 percent response rate and a design-effect of 1.2 was used to allow for clustering of the complex design. After taking into account all those features, it resulted in the required sample size of 150 selected households.
In national statistical surveys, the region of Apia Urban Area (AUA) represented the urban population while the regions of North West Upolu (NWU), Rest of Upolu (ROU) and Savaii represented the rural population. Therefore in order to achieve the sample size of 150 for the domestic customers, a representative probability sample of households was selected in two stages.
The first stage involved the selection of clusters or enumeration area (EAs) from the master sample frame using stratified systematic sampling with probability proportional to size. A total of 30 primary sampling units or clusters were selected in which 6 clusters were from the urban areas and 24 clusters were selected from the rural areas. The design did not allow for replacement of clusters or households.
In the second stage, a total of 5 households were selected from each cluster using systematic equal probability selection. Normally an updated household listing from selected clusters could have been done to select 5 households. However, due to the delay in sorting of customers list and it was towards the end of the year, and the fact that the census 2011 was just completed in the previous three years, it was seen not necessary to conduct a fresh household listing which would have taken SBS another two months to carry out causing delay to the survey.
Other Types of Customers
The sample for the CSS other types of customers such as commercial, religion, school, government, hotel and industrial was drawn from the master sample frame of the list of all the 3767 customers registered with the EPC . The commercial type has 2587 customers, religion with 751customers, school with 229 customers, governments with 118 customers, hotels with 75 customers and industries with 47 customers .The sample size was based on a 95 percent confidence interval of ±5 percent margin of error, assuming an 80 percent response rate. To achieve a representative probability sample, the systematic method was used to select the 100 customers of other 6 types apart from the domestic customers.
A total of 150 households were selected to represent the domestic customers and 139 households were occupied during the field work period. Of the occupied households only 133 were successfully interviewed resulting in a household response rate of 95.7 percent. The 6 households which were selected but not able to answer the questionnaire because of they had no access to electricity during the survey period; most of them were in the island of Savaii.
For other types of EPC customers in which 100 were selected, only 97 customers were found during the survey period. From these customers, 94 were able to complete the survey while the others were no longer operating due to the following reasons: one was destroyed by tsunami, another changed its customer type, and the last was not in the location previously identified in the list of sample respondents.
This is explained in the final analytical report.
Given the complex sampling design used to control survey costs, sampling weights are routinely used in probability sampling to compensate for unequal probabilities of selection and adjustments for non-coverage of the population and non-response. The weights will ensure that the sample is representative of the national and regional population. The sampling weight for each household is the inverse of its overall selection probability with correction for non-response. Once those complex design features are compensated for, then weights can be used in the estimation of the population characteristics of interest and the sampling errors of the survey estimates. Unweighted numbers will be used to report response rates but all other survey estimates and precision will be based on weighted numbers. Therefore, the final CSS 2014 weighted number of households arrived at was 26,209 households of which 21 percent were urban households, and 79 percent were rural households.
The sample for the CSS other types of customers such as commercial, religion, school, government, hotel and industrial was drawn from the master sample frame of the list of all the 3767 customers registered with the EPC . The commercial type has 2587 customers, religion with 751 customers, school with 229 customers, governments with 118 customers, hotels with 75 customers and industries with 47 customers .
The sample size was based on a 95 percent confidence interval of ±5 percent margin of error, assuming an 80 percent response rate. To achieve a representative probability sample, the systematic method was used to select the 100 customers of other 6 types of non-domestic customers. The final weight for EPC other types of customers was 3759.
Please refer to the final analytical report.
Dates of Data Collection (YYYY/MM/DD)
Mode of data collection
Two senior staffs of the Census and survey division were working as supervisors and team leaders during the field work in two teams of 4 part timers in each team. Each team had their own van to cover their selected areas.The supervisors' role include the following:
- coordinate field data collection activities
- suplies of resources such as household lists, maps, questionnaires and other stationeries
- assist with any difficulties or problems with the selected customers.
Type of Research Instrument
A structured English questionnaire was prepared by the EPC team to collect the feedback from the corporation's customers. However, SBS made some improvements in terms of instructions between questionnaire sections in order to make the interviewing flow properly from beginning to end. The questionnaire was also translated into the Samoan language to complement the English questionnaire so that the interpretation of questions by the field enumerators was consistent in the field. A cover page of the questionnaire was also developed so that selected customer's identifications were clearly noted. The options for the survey status were also listed to account for non-coverage of EPC customers during the fieldwork.
The Survey Questionnaire consists of four sections with a cover page in the beginning for the Identification of selected households and other types of customers. Section A has seven questions about the type of meters the customers used and the service provided by EPC to pay bills and buy cash power units, and open questions to state some reasons why the customers were not satisfied with the service given by the EPC, areas of paying of electricity bills and selling cash power units. Section B contains five questions on the management of complaints lodged to the corporation and the satisfaction of service provided. Section C asked two types of questions in which one was a rating question on the perception of the customers of the EPC service, and the second was a ranking question of the mediums that the public used to get EPC public awareness. Section D was open for the customers to list any of their comments about the service of EPC for improvement.
Census and survey team
Samoa Bureau of Statistics
Samoa Bureau of Statistics
After coding, the computer data program was created using CSPro 5 software for data entry. After testing the program, the data entry was conducted in one week (March 24th-28th). The data editing, cleaning and weighting of the data took another two weeks (April 1st-11th) to complete, leaving three weeks (April 14th - May 2nd) to analyse and write the analysis report to meet the deadline.
Data editing was done using writing option in CSPro 5.0.
Estimates of Sampling Error
Any survey will be affected by sampling errors and non-sampling errors. The latter is difficult to measure but can be greatly reduced by the application of high quality survey management, efficient field supervisions, skilful enumerators, good control of data coding and data processing, sufficient resources, etc. Sampling errors are usually calculated using relevant sampling estimation formulae and computer programs. For the CSS 2014, the variance formula for complex design was used to calculate sampling errors. Dr Ren Ruilin of ICF Macro developed specific sampling error estimation templates in Excel for use by developing countries like Samoa where expensive computer programs like SAS could not be purchased. The Excel templates used the Taylor linearization method of variance estimation for survey estimates like means and proportions. The design effect (DEFT) for each estimate was also calculated whereby a DEFT value of 1.0 indicates that the complex design used was just as efficient as the simple random sampling and a value more than 1 indicates an increase in sampling error due to the design and vice versa. In addition, the confidence limits of 95 percent can also be estimated for each variable which provides the range of values for which the true value falls.
Details of sampling errors are presented in the sampling errors appendix of the report.
All information is protected under the Statistics Act 1971
The EPC microdata is available for distribution as licensed-use files. Please contact the identified contact persons to request for the dataset.
Conditions for use of licensed datasets are:
1. The data and other materials provided by the Samoa Bureau of Statistics (SBS) will not be redistributed or sold to other individuals, institutions, or organizations without the written agreement of the SBS and Electric Power Corporation.
2. The data will be used for statistical and scientific research purposes only. They will be used solely for reporting of aggregated information or the development of statistical models, and not for investigation of specific individuals or organizations.
3. No attempt will be made to re-identify respondents, and no use will be made of the identity of any person or establishment discovered inadvertently. Any such discovery would immediately be reported to the SBS and EPC
4. No attempt, without prior approval, will be made to produce links among datasets provided by the SBS, or among data from the SBS and other datasets that could identify individuals or organizations, nor for destroying the business operations of individuals or organizations.
5. Any books, articles, conference papers, theses, dissertations, reports, or other publications that employ data obtained from the SBS will cite the source of data in accordance with the Citation Requirement provided with the dataset.
6. An electronic copy of all reports and publications based on the requested data will be sent to the SBS and EPC
7. The original collector of the data, the SBS, and the relevant funding agencies bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
8. The primary and other researchers who will be involved in using the data must be identified.
9. The researchers' organization must be identified as must a suitable representative of the organization who must be a signatory to the license.
10. The intended use of the data including a list of expected outputs and the organization's dissemination policy must be identified.
11. A formal agreement must be signed that the files will not be shared beyond the boundaries of the organization. In the case of a blanket agreement where it is agreed that the data can be used broadly within the receiving organization in a secure manner, the receiving organization must demonstrate a capacity to manage the data files in a secure manner (with an identified individual assigned formal responsibility for doing so) and each additional new user be made aware of the terms and conditions that apply to the data files. This must be achieved by having the users sign an affidavit. Where a blanket agreement exists and data security procedures are in place, it will not be necessary for the users to destroy the data after use is complete.
Samoa Bureau of Statistics, Electric Power Corporation Customer Satisfaction Survey 2014 (WSEPC 2014), Version 01 of the public-use dataset (April 2014), provided by the Samoa Bureau of Statistics. http://126.96.36.199/index.php/catalog/central"
Disclaimer and copyrights
The user of the data acknowledges that Samoa Bureau of Statistics and Electric Power Corporation bear no responsibility for use of the data or for interpretations or inferences based upon such uses.
A Memorandum of Understanding between Samoa Bureau of Statistics and Electric Power Corporation was signed on February 6th 2014, for conducting the Customer Satisfaction Survey 2014 to collect feedback on the services provided by EPC to all its clients. All information and data obtained, interpreted and presented in the Report to EPC belong to EPC. Any organization that wish to use the CSS data may use it upon obtaining written approval of EPC.