-
Estimating Total Energy Demand from Incomplete Data Using Non-parametric Analysis
Benard Mworia Warutumo,
Pius Nderitu Kihara,
Levi Mbugua
Issue:
Volume 6, Issue 1, February 2020
Pages:
1-11
Received:
12 November 2019
Accepted:
6 December 2019
Published:
8 January 2020
Abstract: The validity and usefulness of empirical data requires that the data analyst ascertains the cleanliness of the collected data before any statistical analysis commence. In this study, petroleum demand data for a period of 24 hours was collected from 1515 households in 10 clusters. The primary sampling units were stratified into three economic classes of which 50% were drawn from low class, 28% from medium class and 22% from high class. 63.6% of the questionnaires were completed whereas incomplete data was computed using multivariate imputation by chained equation with the aid of auxiliary information from past survey. The proportion of missing data and its pattern was ascertained. The study assumed that missing data was at random. Nonparametric methods namely Nadaraya Watson, Local Polynomial and a design estimator Horvitz Thompson were fitted to aid in the estimation of the total demand for petroleum which has no close substitute. The performance of the three estimators were compared and the study found that the Local Polynomial approach appeared to be more efficient and competitive with low bias. Local polynomial estimator took care of the boundary bias better as compared to Nadaraya Watson and Horvitz Thompson estimators. The results were used to estimate the long time gaps in petroleum demand in Nairobi county, Kenya.
Abstract: The validity and usefulness of empirical data requires that the data analyst ascertains the cleanliness of the collected data before any statistical analysis commence. In this study, petroleum demand data for a period of 24 hours was collected from 1515 households in 10 clusters. The primary sampling units were stratified into three economic classe...
Show More
-
Impact of Loss and Gain Forecasting on the Behavior of Pricing Decision-making
Inga Toma,
Dursun Delen,
Gregory Moscato
Issue:
Volume 6, Issue 1, February 2020
Pages:
12-19
Received:
29 December 2019
Accepted:
8 January 2020
Published:
4 February 2020
Abstract: Recent forecasting research has shown a paradigm shift from algorithm aversion to appreciation. Despite growing trust in technological decision support, business decisions are often made based on gut feeling and intuition, ignoring part or all of the available data and information. Creating effective decision support solutions necessitates the understanding of the impact of emerging artificial intelligence and machine learning technologies on business decision-making processes. This study examines whether forecasting information delivery at a time when a business decision is made influences or changes the decision maker’s mind, thereby leading to a different decision. The study employs a 2 × 2 between-subject experimental setting where forecasted results (gain/loss) and automated advice (risk/certainty) were crossed-examined. A sample of 137 participants was asked to make four different product price change decisions assisted by automated decision aid. The experiment involved two independent samples, one taken from Amazon Mechanical Turk workers and the other from the members of LinkedIn managerial groups. Results show that decision-makers are more likely to rely on automated recommendation and change their initial decision when forecasted decision outcomes lead to gain, whereas they would discount algorithmic aid if a loss is forecasted. This research adds to the extant literature in the field of human-technology interactions and contributes to the descriptive and prescriptive decision theories by illustrating that gain forecasting has a higher impact on the algorithm appreciation than loss forecasting.
Abstract: Recent forecasting research has shown a paradigm shift from algorithm aversion to appreciation. Despite growing trust in technological decision support, business decisions are often made based on gut feeling and intuition, ignoring part or all of the available data and information. Creating effective decision support solutions necessitates the unde...
Show More
-
Using Data Mining Techniques and R Software to Analyze Crime Data in Kenya
Stephen Mangara Wainana,
Joseph Njuguna Karomo,
Rachael Kyalo,
Noah Mutai
Issue:
Volume 6, Issue 1, February 2020
Pages:
20-31
Received:
8 January 2020
Accepted:
31 January 2020
Published:
14 February 2020
Abstract: Crimes have been the most dangerous threat to peace, development, human right, social, political and economic stability in Kenya. There is a great need to eradicate crime to facilitate development and counter all vices that are caused by crime. Efficient management of crime requires an adequate understanding of the patterns in which crime occur to put the appropriate measures in place for crime prevention. Crime has been in existence since the beginning of time hence will remain, and one of the solutions is to identify the pattern in which it occurs to prevent or counter it effectively as it occurs. The main objective of the study was to find out how different crimes are related. The study considered a number of data mining techniques which included; clustering, specifically k-means algorithm, mapping and APRIORI algorithm to analyze how different crimes are related and how often they occur. Crime cases were found to be decreasing over the years under study and counties with a high population reported higher number of crimes as compared to those with low population. The study suggested that these crimes could be controlled by directing more resources in the highly populated counties. The study leaves a research gap where the same crime data could be analyzed using time series methods since observed crime offenses are recorded alongside the time they occur.
Abstract: Crimes have been the most dangerous threat to peace, development, human right, social, political and economic stability in Kenya. There is a great need to eradicate crime to facilitate development and counter all vices that are caused by crime. Efficient management of crime requires an adequate understanding of the patterns in which crime occur to ...
Show More
-
Haversine Formula and RPA Algorithm for Navigation System
Nyein Chan Soe,
Thin Lai Lai Thein
Issue:
Volume 6, Issue 1, February 2020
Pages:
32-40
Received:
22 January 2020
Accepted:
11 February 2020
Published:
19 February 2020
Abstract: The system uses a geographic information system to analyze and monitor traffic congestion and use GPS data for public transport planning in Yangon, Myanmar. The system provides accurate maps for estimating traffic conditions more efficiently from GPS data, saving more time. The proposed system displays changes in the position, distance and direction of vehicles traveling on the streets of Yangon by using traffic state and routing pattern algorithm. There established centralized GPS server database infrastructure provides any kind of analysis that requires GPS traffic data stored in a distributed client-server environment. In this system, a statement of user desired traffic jams between the source and destination is estimated and the results are presented with a Map. This system is for analyzing traffic data, avoiding traffic congestion and obtaining optimal routes with a modified A* algorithm. GPS data (current location) and user search area using the K-d tree and Haversine algorithm are required. Second, look for traffic jam data with Google's traffic layer and the routing matrix pattern algorithm. Finally, Analysis the traffic by Smart-A* and then show the result of traffic congestion statement and best optimal route. In the case, there are three main components: Data Collection, Data Extraction and Implementation. And this is Client-Server database system that storing the data and server in the cloud Virtual Machine (VM).
Abstract: The system uses a geographic information system to analyze and monitor traffic congestion and use GPS data for public transport planning in Yangon, Myanmar. The system provides accurate maps for estimating traffic conditions more efficiently from GPS data, saving more time. The proposed system displays changes in the position, distance and directio...
Show More
-
Comparative Analysis of the Cox Semi-parametric and Weibull Parametric Models on Colorectal Cancer Data
Usman Umar,
Marafa Haliru Muhammad
Issue:
Volume 6, Issue 1, February 2020
Pages:
41-47
Received:
26 January 2020
Accepted:
13 February 2020
Published:
17 March 2020
Abstract: The survival and hazard functions are key concepts in survival analysis for describing the distribution of event times. The survival function gives, for every time, the probability of surviving (or not experiencing the event). The hazard function gives the potential that the event will occur, per time unit, given that an individual has survived up to the specified time. While these are often of direct interest, many other quantities of interest (e.g., median survival) may subsequently be estimated from knowing either the hazard or survival function. This research was a five-year retrospective study on data from a record of colorectal cancer patients that received treatments from 2013 to 2017 in Radiotherapy Department of Usmanu Danfodiyo University Teaching Hospital, Sokoto, being it one of the cancer registries in Nigeria. 9 covariates were selected to fit colorectal cancer data using Cox and Weibull Regression Models. From the result it is concluded that the predictor variables could significantly predict the survival of colorectal cancer patients using Cox. Also the result of the Weibull Proportional Hazard Model shows that the model is adequate enough to predict the survival of the colorectal patients. The A. I. C result shows that, according to our colorectal cancer data, the semi-parametric Cox regression model performed better than the parametric Weibull proportional hazards model. However, in the present study, the Cox model provided an efficient and a better fit to the study data than Weibull model.
Abstract: The survival and hazard functions are key concepts in survival analysis for describing the distribution of event times. The survival function gives, for every time, the probability of surviving (or not experiencing the event). The hazard function gives the potential that the event will occur, per time unit, given that an individual has survived up ...
Show More
-
Comparative Analysis of Sarima and Setar Models in Predicting Pneumonia Cases in Kenya
Fredrick Agwata Nyamato,
Anthony Wanjoya,
Thomas Mageto
Issue:
Volume 6, Issue 1, February 2020
Pages:
48-57
Received:
24 February 2020
Accepted:
6 March 2020
Published:
18 March 2020
Abstract: Kenya is a country located in Eastern part of Africa with approximate population of 46.5 million, with majority of the population constituting youths under the age of 35 years. The country has experienced increased morbidity rate arising from Pneumonia disease like other countries all over the world. As per recent studies 2 million children lose lives from pneumonia disease [1]. This study applies two models, one is linear model Seasonal autoregressive model (SARIMA) and another is a non-linear model called self-Excited Threshold Autoregressive (SETAR) in projection of cases in Kenya. Data for usage for purpose of this study was obtained Ministry of Health of Kenya of a period of 20 years from January 1999 to December 2018. The data collected is seasonal the number of case from period to period depending on climatic condition. Although both models performs well in pneumonia projection, non-linear SETAR models outperforms linear SARIMA. By carrying out a comparative analysis by use of Diebold-Mariano test, which revealed that there were no significant difference in the forecasting performance of the two models. The best model identified between the two models i.e. SETAR which best fit the data, can be applied in predicting pneumonia cases beyond the period under consideration. Other studies can be carried to come up with a model for every specific region in the country, to assist in resources allocation to specific parts of the country.
Abstract: Kenya is a country located in Eastern part of Africa with approximate population of 46.5 million, with majority of the population constituting youths under the age of 35 years. The country has experienced increased morbidity rate arising from Pneumonia disease like other countries all over the world. As per recent studies 2 million children lose li...
Show More
-
Bayesian Trivariate Analysis of an Opinion Poll: With Application to the Kenyan Pollss
Jeremiah Kiingati,
Samuel Mwalili,
Anthony Waititu
Issue:
Volume 6, Issue 1, February 2020
Pages:
58-63
Received:
15 January 2020
Accepted:
4 February 2020
Published:
24 March 2020
Abstract: There has been a growing interest by political pundits and scholars alike to predict the winner of the presidential elections. Although forecasting has now quite a history, we argue that the closeness of recent Kenyan presidential opinion polls and the wide accessibility of data should change how presidential election forecasting is conducted. We present a Bayesian forecasting model that concentrates on the national wide pre-election polls prior to 2013 general elections and considers finer details such as third-party candidates and self-proclaimed undecided voters. We incorporate our estimators into WinBUGS to determine the probability that a candidate will win an election. The model predicted the outright winner for the 2013 Kenyan election.
Abstract: There has been a growing interest by political pundits and scholars alike to predict the winner of the presidential elections. Although forecasting has now quite a history, we argue that the closeness of recent Kenyan presidential opinion polls and the wide accessibility of data should change how presidential election forecasting is conducted. We p...
Show More