TIME SERIES ANALYSIS ON THE TOTAL NUMBER OF PATIENTS TREATED FOR MALARIA FEVER (BETWEEN 2001 AND 2010)

Format: MS WORD |  Chapter: 1-5 |  Pages: 65-80

TIME SERIES ANALYSIS ON THE TOTAL NUMBER OF PATIENTS TREATED FOR MALARIA FEVER (BETWEEN 2001 AND 2010)

ABSTRACT

This project work reveled the rate at which people are infected with malaria the least square method used for analysis showed that people are infected with malaria irrespective of the time and seasons of a successive year. There is no noticeable direction as regarding the number of patients treated for malaria over time. Also, the analysis from autoregressive moving average report shows that both autoregressive and moving average of order four were both appropriate while the report from autocorrelation and autocovanance does not indicate any noticeable trend in the number of patients treated for malaria.

CHAPTER ONE

INTRODUCTION

The term time series refers to the quantitative method used in determination pattern in data collected over time e.g weekly monthly, quarterly or yearly. Time series is the statistic tool or methodology that can be used to transform past experience to predict future event which would enable the researcher or organization to plan. It gives information about how the particular case of study has been behaving in the past and present and such information can be used in prediction. For example, in this study, we are going to see how change occur over mouths in each year in the occurrence of the disease in an hospital.  As a result of this, we will be able to know certain factor responsible for increase or decrease in the rate of infection of the disease over the period of time. Record of time series data can be made in the following ways:

1. Through Cumulative Figures: These represent value of input through the quarter. We must always bear in mind the different when handling time series data and as certain which particular type we are dealing with in every case.
2. Cumulative Type Added Compilation: some cases when an added compilation introduced for the cumulative type of data the figure which are related to month of the year and not the total for month. Furthermore, the characteristic movement, seasonal variation Irregular variation in the analysis of time series, we have two types of model are generally accepted as good approximation of the true data association among the component of observed data, they are the most commonly assumed relationship between time series and its components. These are additive model and Multiplicative mode. All-time series contain at least one of four of its components. These components are:
3.  Long term trend
4. Seasonal variation

iii.   Cyclical variation

1. Irregular or random variation value

Long Term Trend Component

This can be referred to the general path in which time series graph appear to follow over a long period of time, in other word, it is the long-term increase or decrease in a variable being measured over time for example a company planning her expense on goods to produce in the next three or four years has consider demand at a particular time.

HERE IS WHAT OUR HAPPY CLIENTS ARE SAYING