Research consultancy

CHAPTER THREE

RESEARCH METHODOLOGY

3.0 Introduction

This section presents a detailed description on how the study will be carried out and collecting the necessary data for the study. It therefore covers the research design, study area, data sources, data processing, data analysis techniques and anticipated limitations of the study.

3.1 Research Design

The study used quantitative methods of research so as to obtain the viable data and this shall include structured secondary data in the records of the Ministry of health.

3.2 Data Sources.

Secondary data was obtained from the data base, records, publications and journals in the ministry of health.

3.3 Data processing and Data analysis techniques

The process of data processing involved editing in order to check for errors and omissions and coding to reduce the data to a meaningful pattern of responses. Model specification and soft wares employed in the tabulation and processing of the findings will be done in order to prepare data, analyze and compile a research report.

The study used time series analysis and descriptive statistics was used to describe the information got from the field this will be inform of graphs and tables

Data Analysis involved applying statistical techniques on it for easy presentation. It included the interpretation of research findings in the light of the research questions, and objectives to determine if the results are consistent with those research questions.

3.3.1 Descriptive analysis.

3.3.2 Time series analysis

By the nature of data which is the time series

The analysis however will concentrate on trend and seasonality of malaria prevalence

Assuming a multiplicative model, then 𝑌𝑡=𝑇𝑡∗𝑆𝑡

Where 𝑌𝑡 is the mortality series, 𝑇𝑡 is Trend and 𝑆𝑡 is the seasons.

This employs ARIMA modeling and it includes the following data exploration techniques.

a. Graphical presentation

This involved plotting the series 𝑌𝑡 against time t.

b. Non parametric tests for trend

Run’s test: The runs test (Bradley, 1968) can be used to decide if a data set is from a random process.

A run is defined as a series of increasing values or a series of decreasing values. The number of increasing, or decreasing, values is the length of the run. In a random data set, the probability that the (i+1)^th value is larger or smaller than the i^th value follows a binomial distribution, which forms the basis of the runs test. Testing procedure

Ho: the malaria prevalence series is stationary

Ha: the malaria prevalence series is non-stationary.

Test statistic

Where m=number of pluses Decision rule is at α=0.05

The researcher will reject Ho if Z>𝑍_∝/2 i.e. if the computed Z statistic is greater than the notable value and then conclude with (1-α)*100% confidence, the series has trend.

Test for seasonality

In this research, the researcher will use the Kruskal-Wallis test which is an alternative for the parametric one-way analysis of variance test, if there are two or more independent groups to compare (Siegel & Castellan 1988).

The test is described as below; Ho: the series has no seasonality Ha: the series has seasonality

Test statistics, H to compare with  (Chi square)

n_i is the number of observations in the i^th season N is the total number of specific seasons

Ri= 𝑟𝑎𝑛𝑘 (𝑦𝑖) Yi is the specific season for time t. Critical region

Reject Ho if

3.4.3 Autoregressive Integrated Moving Average (ARIMA)

This is also known as the Box-Jenkins model. This methodology will be used to forecast the malaria prevalence for children aged below 15 years. The model is based on the assumption that the time series involved are stationary. Stationary will first be checked and if not found, the series will be differenced d times to make it stationary and then the Autoregressive Moving Average (ARMA) (p, q) will be applied. The ARIMA procedure provides a comprehensive set of tools for univariate time series model identification, parameter estimation, and forecasting, and it offers great flexibility in the kinds of ARIMA models that can be analyzed. The ARIMA procedure supports seasonal, subset, and factored ARIMA models; intervention or interrupted time series models; multiple regression analysis with ARMA errors; and rational transfer function models of any complexity. The Box-Jenkins methodology has four steps that will be followed when forecasting malaria prevalence among children as below;

Identification.0 This involves finding out the values of p, d, and q

where;

P is the number of autoregressive terms

d is the number of times the series is differenced

q is the number of moving average terms

The identification here was done basing on the correlogram plot obtained. Where both autocorrelation and partial correlation cuts of at a certain point, we conclude that the data follows an autoregressive model. The order p, of the ARIMA model is obtained by identifying the number of lags moving in the same direction. In case the series was non stationary, the number of times we difference the series to obtain stationarity is the value of d.

Estimation. This involves estimation of the parameters of the Autoregressive and Moving average terms in the model. The nonlinear estimation will be used.

Diagnostic checking. Having chosen a particular ARIMA model, and having estimated its parameters, we now examine whether the chosen model fits the data reasonably well. The simple

test of the chosen model was done to see if the residuals estimated from this model are white noise. If they are, we can accept the particular fit and if not, the model will have to be started over.

Forecasting. Exponential smoothing methods was used for making forecasts. While exponential smoothing methods do not make any assumptions about correlations between successive values of the time series, in some cases you can make a better predictive model by taking correlations in the data into account. Autoregressive Integrated Moving Average (ARIMA) models include an explicit statistical model for the irregular component of a time series that allows for non-zero autocorrelations in the irregular component.

The forecast for the year 2018 will be done by regressing malaria prevalence against time

The residence and region will be analyzed using the ANOVA test by regressing malaria prevalence (dependent) on the dummies for place of residence and dummies for region using SPSS since residence and region are both categorical independent variables.

   Y_t =β_o+β₁D_R+β₂D_C+β₃D_N+β₄D_E

Where Yt is the malaria prevalence at the time in a given region and residence

D_R is a dummy for rural , D_R =1 if Rural , 0 other wise

D_C is a dummy for central, D_c=1 if central, 0 otherwise

D_N is a dummy for north , D_N= 1 if North , 0 otherwise

D_E is a dummy for East, D_E=1 if East, 0 otherwise

3.8 Ethical considerations

The researcher began data collection by explaining the purpose of the research, which basically meant to help decision makers of ministry of health Uganda and the users of the information from other health organizations and hospitals. Respondents were informed that the purpose of the information shall be strictly for academic purposes only and the information provided was treated with highest level of confidentiality.

CHAPTER FOUR

PRESENTATION OF RESULTS

4.0 Introduction

         4.1 Comparison of Malaria Cases Residence

Table 1: Comparison of Malaria Cases Residence

The above table shows the statistics obtained from places of residences on the malaria prevalence from the year 2006 to 2015 making it a total of 10observations.

The study shows that rural residence had mean total malaria cases of 3109.70 with a standard deviation of 665.553 while urban residence had mean of 428.90 with a standard deviation of 207.819. This implies that there was much variation in the data in urban centers compared to rural areas for the last 10 years and the prevalence was high in towns compared to villages for last 10 years.

This indicates that there is more malaria cases in towns than in rural areas , it further proves the point that perhaps urban people are better informed on the different ways of preventing malaria that is why there are fewer malaria cases in towns than villages.

4.1.2 Comparison of Malaria Cases by Region

The table below gives a comparison of the malaria cases (prevalence) among different regions across the Country-Uganda that was collected from time series data for last Ten years.

Table 2: Comparison of Malaria Cases by Region

From the above table the study revealed that Northern region had the highest registered number of malaria cases with highest mean of 1011.00 and standard deviation of 247.958 followed by Eastern with a mean of 1000.90 and the standard deviation 249.880.  Western and central regions had mean malaria cases of 833.60 and 693.60 with the standard deviation of 261.615 and 693.60 respectively. Despite eastern region registering the highest number of malaria there was little variation in the data.

This also shows that majority of people in northern Uganda have malaria than any other region in Uganda showing that there is need for the government to increase omn the camp[aighns of fighting malaria in the area.

Table 3: correlations

The table above shows the relationship between the numbers of registered malaria cases by region for the children below 5 years from 2006 to 2015. The correlations between north and east, north and west, north and central are -0.061, .790^** and .547 respectively and correlations are only significant between north and west.

That between east and west, east and central, west and central, is -0.061, .790^** and .547, respectively and correlation is significant between central and west. For significance it implies that those regions almost registered the similar number of cases during the same period or the prevalence rate was the same across those regions.

4.1.4 Correlations of Malaria Cases by Residence

Table 4: Correlations of Malaria Cases by Residence

The above table shows that relationship of malaria prevalence by residence in Uganda for the study that was conducted. There is a high significant and positive relationship of 0.698^* between rural and urban areas and the results are significant since sig 0.000<0.05. This results indicates that malaria cases in both regions are high and there is a high positive relationship between the regions in terms of malaria prevalence.

4.1.5 Determination of the distribution of malaria across Regions

The results above were obtained to determine the distribution of malaria across Regions by using Kruskal-Wallis Test since region is categorized into four categories i.e. north, east, west and central. From the above test the significant value obtained is 0.647 which is greater than 0.05 therefore we fail reject the null hypothesis and conclude that the distribution of total malaria cases is the same across categories of region.

4.1.6 Regression of total malaria cases on rural and urban

Table 5: Regression of total malaria cases on rural and urban

The R-value tells us about correlation coefficient (1.000) means that there is a very high positive relationship between malaria cases by region and total malaria cases. R Square value explains the percentage contribution of the independent variables on the dependent variable.

Therefore approximately 100% of the variations in the total malaria cases are explained by the changes in the malaria cases of both rural and urban areas.

Table 6: ANOVA

The above ANOVA table explains the overall significant of the model. Basing on the hypothesis that the independent variable shave no effect on malaria case, since the sig value 0.00 <0.05 we reject the hypothesis and conclude that the independent variables (places of residence) have an effect on the total malaria cases.

Table 7: Coefficients

The table is used to explain the effect of places of residence on malaria cases. The model is estimated as Y=B+B₁X₁+B₂X₂ where B is constant, B₁ is coefficient for rural and B₂ is the coefficient for urban.

From the model the coefficients are -1.849, 1.001, and .995 for B, B₁, and B₂ respectively. All the effects are significant since the sig-values for both rural and urban are less than 0.05.  In summary residences from urban areas have higher chances of contracting malaria compared to their village counterparts.

4.1.8 Forecasting model for the year 2018

Table 8: Forecasting model for the year 2018

The model from the above table was obtained by regressing total malaria cases against time to be able to forecast malaria cases for the 2018. The model is written as Y=B+B₁X₁ where B is constant B₁ is the coefficient of years. Hence the model is fitted as Y=-40825.148+22.065X₁

4.1.9 Autoregressive Integrated Moving Average forecasting

Table 9: Autoregressive Integrated Moving Average forecasting

The forecasting of the model required to first test the principle of stationary in order to find out if the time series was stationary non stationary hence use the unit root test. From the above results the Dickey Fuller value (18)>stationary R-squared (0.749) therefore we accept the hypothesis and conclude that there is a nit root hence non stationary of the time series data.

4.1.10 correlation between rural and urban

Table 10: correlation between rural and urban

The study indicates that there is a strong correlation between rural and urban in malaria prevalence, this is shown by the mean value of 0.698.

This finding shows that when there is a strong relationship between rural and urban in malaria prevalence.

4.1.11 Correlation between the regions

Table 11: 4.1.11 Correlation between the regions

From the figure above the results indicates that the R Square 0.877 implying that 87.7 of malaria prevalence is due the difference in the regions, this is also indicated by significance level of 0. .004 <0.05, therefore the results rejects the null hypothesis and the conclusion that there is a difference in malaria prevalence among the regions.

Table 12:ANOVA

From the results the significance level is 0.004 implying that the study rejects the null hypothesis, Since sig 0.004 <0.05 and the study concludes that there is a difference in malaria prevalence among the regions.

This implied that the central has lower cases of malaria compared to north, east and west, then reject null hypothesis and conclude that there is a difference in malaria prevalence by region.

Forecast

In the year 2007 the total malaria cases were lower compared to 2016, 2017 and 2018. It was evidenced that the year 2007 registered the least number of malaria cases. However malaria cases again shoot up between 2008 and 2010 as seen on the graph, the graph further indicates that malaria cases are on the rise.

CHAPTER FIVE

SUMMARY OF FINDINGS, CONCLUSION AND RECOMMENDATIONS

5.0 Introduction

This chapter discusses what various scholars have written about the research findings;

5.1 summary of findings

The results shows that there was much variation in the data in urban centers compared to rural areas for the last 10 years and the prevalence was high in towns compared to villages for last 10 years.

Findings revealed that Northern region had the highest registered number of malaria cases with highest mean of 1011.00 and standard deviation of 247.958 followed by Eastern with a mean of 1000.90 and the standard deviation 249.880.  Western and central regions had mean malaria cases of 833.60 and 693.60 with the standard deviation of 261.615 and 693.60 respectively. Despite eastern region registering the highest number of malaria there was little variation in the data.

The table above shows the relationship between the numbers of registered malaria cases by region for the children below 5 years from 2006 to 2015. The correlations between north and east, north and west, north and central are -0.061, .790^** and .547 respectively and correlations are only significant between north and west.

That between east and west, east and central, west and central, is -0.061, .790^** and .547, respectively and correlation is significant between central and west. For significance it implies that those regions almost registered the similar number of cases during the same period or the prevalence rate was the same across those regions.

The central has lower cases of malaria compared to north, east and west, then reject null hypothesis and conclude that there is a difference in malaria prevalence by region.

In the year 2007 the total malaria cases were lower compared to 2016, 2017 and 2018. It was evidenced that the year 2007 registered the least number of malaria cases. However malaria cases again shoot up between 2008 and 2010 as seen on the graph, the graph further indicates that malaria cases are on the rise, the total malaria cases for 2018 will be 5329.

5.2 Conclusion

The study concludes that there is variation in malaria prevalence across the region some regions had higher malaria cases than others.

The study also concludes that malaria cases are on the rise.

The study also states that the variations in the total malaria cases are explained by the changes in the malaria cases of both rural and urban areas.

The study also concludes that malaria is high in the rural areas than urban areas.

5.3 Recommendation

The study recommends more infighting malaria so that the challenges brought by malaria are worked upon.

The study also recommends that the government should increase the number of health workers in the government hospital

Regions with high malaria levels should increase findings for the rural health facilities especially in northern Uganda.

5.4 Areas of further study

The study recommends the following areas for further study;

• The influence of mosquito nets on malaria prevention
• The influence of foreign aid on the influence of education of malaria prevalence in Africa.
• The influence of malaria medicine on malaria prevention

REFERENCES

Clark TD, Njama-Meya D, Nzarubara B, Maiteki-Sebuguzi C, Greenhouse B, Staedke SG, Kamya MR, Dorsey G, Rosenthal PJ. Incidence of malaria and efficacy of combination antimalarial therapies over 4 years in an urban cohort of Ugandan children. PLoS One. 2010;5:e11759

Francis D, Nsobya SL, Talisuna A, Yeka A, Kamya MR, Machekano R, Dokomajilar C, Rosenthal PJ, Dorsey G. Geographic differences in antimalarial drug efficacy in Uganda are explained by differences in endemicity and not by known molecular markers of drug resistance. J Infect Dis. 2006;193:978–986.

Okello PE, Van Bortel W, Byaruhanga AM, Correwyn A, Roelants P, Talisuna A, D’Alessandro U, Coosemans M. Variation in malaria transmission intensity in seven sites throughout Uganda. Am J Trop Med Hyg. 2006;75:219–225

President’s Malaria Initiative. President’s Malaria Initiative Uganda Malaria Operational Plan for FY 2010. 2010

Rowe AK, Kachur SP, Yoon SS, Lynch M, Slutsker L, Steketee RW. Caution is required when using health facility-based data to evaluate the health impact of malaria control efforts in Africa. Malar J. 2009;8:209.

Uganda Bureau of Statistics. Uganda Demographic and Health Survey 2006. 2007.

Uganda Bureau of Statistics. Uganda Malaria Indicator Survey 2009. 2010.

Uganda Ministry of Health. Uganda Malaria Control Strategic Plan 2005/6–2009/10. 2005

Uganda Ministry of Health. Uganda Malaria Control Strategic Plan 2005/6–2009/10. 2005

World Health organisation 2015

World Health Organization’s World Malaria Report 2013 and the Global Malaria Action Plan

World Malaria Report.; Geneva: 2008