A simulation study of the behaviour of the logrank test under different levels of stratification and sample sizes
- Authors: Jubane, Ido
- Date: 2013
- Subjects: Statistics , Survival analysis (Biometry)
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11784 , http://hdl.handle.net/10353/d1018558 , http://hdl.handle.net/10353/d1018559 , Statistics , Survival analysis (Biometry)
- Description: In clinical trials, patients are enrolled into two treatment arms. A researcher may be interested in studying the effectiveness of a new drug or the comparison of two drugs for the treatment of a disease. This survival data is later analysed using the logrank test or the Cox regression model to detect differences in survivor functions. However, the power function of the logrank test depends solely on the number of patients enrolled into the study. Because statisticians will always minimise type I and type II errors, a researcher carrying out a clinical trial must define beforehand, the number of patients to be enrolled into the clinical study. Without proper sample size and power estimation a clinical trial may fail to detect a false hypothesis of the equality of survivor functions. This study presents through simulation, a way of power and sample size estimation for clinical trials that use the logrank test for their data analysis and suggests an easy method to estimate power and sample size in such clinical studies. Findings on power analysis and sample size estimation on logrank test are applied to two real examples: one is the Veterans' Administration Lung Cancer study; and the other is the data from a placebo controlled trial of gamma interferon in chronic granulotomous disease.
- Full Text:
- Date Issued: 2013
- Authors: Jubane, Ido
- Date: 2013
- Subjects: Statistics , Survival analysis (Biometry)
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11784 , http://hdl.handle.net/10353/d1018558 , http://hdl.handle.net/10353/d1018559 , Statistics , Survival analysis (Biometry)
- Description: In clinical trials, patients are enrolled into two treatment arms. A researcher may be interested in studying the effectiveness of a new drug or the comparison of two drugs for the treatment of a disease. This survival data is later analysed using the logrank test or the Cox regression model to detect differences in survivor functions. However, the power function of the logrank test depends solely on the number of patients enrolled into the study. Because statisticians will always minimise type I and type II errors, a researcher carrying out a clinical trial must define beforehand, the number of patients to be enrolled into the clinical study. Without proper sample size and power estimation a clinical trial may fail to detect a false hypothesis of the equality of survivor functions. This study presents through simulation, a way of power and sample size estimation for clinical trials that use the logrank test for their data analysis and suggests an easy method to estimate power and sample size in such clinical studies. Findings on power analysis and sample size estimation on logrank test are applied to two real examples: one is the Veterans' Administration Lung Cancer study; and the other is the data from a placebo controlled trial of gamma interferon in chronic granulotomous disease.
- Full Text:
- Date Issued: 2013
Modelling the impact of risk factors affecting TB treatment
- Authors: Tsuro, Urgent
- Date: 2013
- Subjects: Diseases -- Risk factors , Tuberculosis -- Epidemiology , Multidrug resistance
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11787 , http://hdl.handle.net/10353/d1019782 , Diseases -- Risk factors , Tuberculosis -- Epidemiology , Multidrug resistance
- Description: The Tuberculosis infection rate has been generally escalating due to poor health conditions in the Gweru district of Zimbabwe. The study therefore seeks to identify the risk factors that affect TB treatment in the Gweru district. A cross sectional study was carried out in which a questionnaire was employed for data collection on 113 respondents. A binary logistic regression model was employed for data analysis. A total of 98 TB patients were interviewed: [50 respondents (44.0%) had Multi-drug resistant Tuberculosis and 63 respondents (56.0%) had general Tuberculosis). Before being enrolled into the study, an informed consent form was given to each of the participants. The data was then put into excel and later transferred to SPSS for analysis. Out of the 14 potential risk factors of TB treatment, only 6 variables (side effects, gender, alcohol use, HIV status, smoking during the treatment period and having been pre-exposed to TB drugs) were statistically significant in their association with treatment failure.
- Full Text:
- Date Issued: 2013
- Authors: Tsuro, Urgent
- Date: 2013
- Subjects: Diseases -- Risk factors , Tuberculosis -- Epidemiology , Multidrug resistance
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11787 , http://hdl.handle.net/10353/d1019782 , Diseases -- Risk factors , Tuberculosis -- Epidemiology , Multidrug resistance
- Description: The Tuberculosis infection rate has been generally escalating due to poor health conditions in the Gweru district of Zimbabwe. The study therefore seeks to identify the risk factors that affect TB treatment in the Gweru district. A cross sectional study was carried out in which a questionnaire was employed for data collection on 113 respondents. A binary logistic regression model was employed for data analysis. A total of 98 TB patients were interviewed: [50 respondents (44.0%) had Multi-drug resistant Tuberculosis and 63 respondents (56.0%) had general Tuberculosis). Before being enrolled into the study, an informed consent form was given to each of the participants. The data was then put into excel and later transferred to SPSS for analysis. Out of the 14 potential risk factors of TB treatment, only 6 variables (side effects, gender, alcohol use, HIV status, smoking during the treatment period and having been pre-exposed to TB drugs) were statistically significant in their association with treatment failure.
- Full Text:
- Date Issued: 2013
A cross-sectional study to ascertain the prognostic factors and symptoms associated with cryptococcal meningitis cases treated at the East London Hospital complex
- Authors: Okorie, Ikechukwu Obinna
- Date: 2012
- Subjects: Meningitis -- South Africa -- Eastern Cape , Tuberculosis -- South Africa -- Eastern Cape , Public health -- South Africa -- Eastern Cape , Hospitals -- South Africa -- Eastern Cape
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11782 , http://hdl.handle.net/10353/d1016194 , Meningitis -- South Africa -- Eastern Cape , Tuberculosis -- South Africa -- Eastern Cape , Public health -- South Africa -- Eastern Cape , Hospitals -- South Africa -- Eastern Cape
- Description: The focus of this study is to identify the potential prognostic factors and symptoms that are associated with Cryptococcal Meningitis and to establish a statistical model for the prediction of outcomes (survival and mortality) among in-hospital patients. Materials and Method: The hospital admission books in the medical wards and pharmacy of the East London Hospital Complex were searched to identify the folder numbers of all the patients that were admitted, diagnosed and or treated for Cryptococcal Meningitis at the hospital between the 1st of January 2009 and the 31st of August 2012. 237 folders out of 519 folders reviewed had confirmed cases of Cryptococcal Meningitis. Data on patients’ demographics, In-hospital care, and Concurrent infection/health condition were collected and analysed in a cross-sectional study, using the univariable and multiple logistic regression. Analysis of data was done with SAS version 9.1.3 and NCSS version 2007 software. Results: In a multivariable logistic analysis of variables found to be significantly associated with Cryptococcal Meningitis in a univariable logistic regression, Being Conscious (i.e. a Glasgow Coma score of 15) (OR= 5.34,CI=2.85-9.99 p =<0.000); Having no history of TB infection (OR=28.91, CI= 3.68-226.89, p = <0.001); No Fits (OR = 2.59, CI= 1.18-5.68 p = 0.017); Being a non-smoker (OR =2.22,CI=1.13-4.34 p = 0.020); and Adhering to treatment instruction and guidelines (OR = 2.38, 1.15-4.89, p = 0.019) were the variables found to be significantly associated with the survival of a Cryptococcal Meningitis patient. The uninterrupted use of Amphotericin B (OR=3.04, CI=1.06-8.72, P=0.038) as a first line regimen was also found to be significantly associated with survival.On the other hand, being unconscious (i.e. Glasgow Coma score <15) (OR =5.34, CI=2.85-9.99, p = < 0.000), Currently having a TB infection (OR = 9.20, CI=2.77-30.57, p = < 0.000), Not adhering to treatment guidelines (OR=2.38, CI=1.15-4.89, p=0.019 ); Being a smoker (OR = 2.22, CI=1.13-4.34, p = 0.020) and having Fits (OR=2.59 CI=1.18-5.68 p=0.017 ) were found to be significantly associated with mortality. Headache (p= 0.505) was found not to be a significant predictor of survival contrary to the findings in many publications on Cryptococcal Meningitis. Owing to time constraint, testing data was not collected to validate the prognostic models. However, model diagnostics was done and the relevant statistics confirmed the goodness of fit and the predictive ability of the model Conclusion: It has been established in this study that certain baseline variables can be helpful in the prognosis of Cryptococcal Meningitis infection. It is therefore believed that these variables will help in improving the prognosis of the infection especially at the East London Hospital Complex. Though the statistical models will work well in predicting the outcome of Cryptococcal Meningitis infection for patients admitted at the East London Hospital Complex, adequate precaution must be exercised while attempting to apply it in other geographical areas.
- Full Text:
- Date Issued: 2012
- Authors: Okorie, Ikechukwu Obinna
- Date: 2012
- Subjects: Meningitis -- South Africa -- Eastern Cape , Tuberculosis -- South Africa -- Eastern Cape , Public health -- South Africa -- Eastern Cape , Hospitals -- South Africa -- Eastern Cape
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11782 , http://hdl.handle.net/10353/d1016194 , Meningitis -- South Africa -- Eastern Cape , Tuberculosis -- South Africa -- Eastern Cape , Public health -- South Africa -- Eastern Cape , Hospitals -- South Africa -- Eastern Cape
- Description: The focus of this study is to identify the potential prognostic factors and symptoms that are associated with Cryptococcal Meningitis and to establish a statistical model for the prediction of outcomes (survival and mortality) among in-hospital patients. Materials and Method: The hospital admission books in the medical wards and pharmacy of the East London Hospital Complex were searched to identify the folder numbers of all the patients that were admitted, diagnosed and or treated for Cryptococcal Meningitis at the hospital between the 1st of January 2009 and the 31st of August 2012. 237 folders out of 519 folders reviewed had confirmed cases of Cryptococcal Meningitis. Data on patients’ demographics, In-hospital care, and Concurrent infection/health condition were collected and analysed in a cross-sectional study, using the univariable and multiple logistic regression. Analysis of data was done with SAS version 9.1.3 and NCSS version 2007 software. Results: In a multivariable logistic analysis of variables found to be significantly associated with Cryptococcal Meningitis in a univariable logistic regression, Being Conscious (i.e. a Glasgow Coma score of 15) (OR= 5.34,CI=2.85-9.99 p =<0.000); Having no history of TB infection (OR=28.91, CI= 3.68-226.89, p = <0.001); No Fits (OR = 2.59, CI= 1.18-5.68 p = 0.017); Being a non-smoker (OR =2.22,CI=1.13-4.34 p = 0.020); and Adhering to treatment instruction and guidelines (OR = 2.38, 1.15-4.89, p = 0.019) were the variables found to be significantly associated with the survival of a Cryptococcal Meningitis patient. The uninterrupted use of Amphotericin B (OR=3.04, CI=1.06-8.72, P=0.038) as a first line regimen was also found to be significantly associated with survival.On the other hand, being unconscious (i.e. Glasgow Coma score <15) (OR =5.34, CI=2.85-9.99, p = < 0.000), Currently having a TB infection (OR = 9.20, CI=2.77-30.57, p = < 0.000), Not adhering to treatment guidelines (OR=2.38, CI=1.15-4.89, p=0.019 ); Being a smoker (OR = 2.22, CI=1.13-4.34, p = 0.020) and having Fits (OR=2.59 CI=1.18-5.68 p=0.017 ) were found to be significantly associated with mortality. Headache (p= 0.505) was found not to be a significant predictor of survival contrary to the findings in many publications on Cryptococcal Meningitis. Owing to time constraint, testing data was not collected to validate the prognostic models. However, model diagnostics was done and the relevant statistics confirmed the goodness of fit and the predictive ability of the model Conclusion: It has been established in this study that certain baseline variables can be helpful in the prognosis of Cryptococcal Meningitis infection. It is therefore believed that these variables will help in improving the prognosis of the infection especially at the East London Hospital Complex. Though the statistical models will work well in predicting the outcome of Cryptococcal Meningitis infection for patients admitted at the East London Hospital Complex, adequate precaution must be exercised while attempting to apply it in other geographical areas.
- Full Text:
- Date Issued: 2012
Comparison of the prevalence of HIV infection in circumcised and uncircumcised men from Salima District in Malawi
- Authors: Kankuwe, Hector Master
- Date: 2012
- Subjects: HIV infections -- Malawi , Initiation rites -- Malawi
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11778 , http://hdl.handle.net/10353/462 , HIV infections -- Malawi , Initiation rites -- Malawi
- Description: The overall objective of the study was to investigate the relationship between male circumcision status and HIV infection in men from Salima district in Malawi. A cross-sectional survey-based study of men aged 15 years or more was conducted at three sites in Salima district, each of which targeted 90 participants, half of whom were circumcised and the other half uncircumcised. These participants had already decided on their own to visit HIV Testing and Counseling centres at these sites to know their HIV serostatus. Consenting men were drawn into the study using quota sampling, interviewed through a structured questionnaire in local language and tested for HIV during January and March 2011. Measures of association were performed using analysis of contingency tables and Pearson’s chi-square tests or Fisher’s exact tests for comparison of proportions in STATA version 11.0 and PASW Statistics 18.0 software. Unadjusted odds ratios were used to approximate the direction and strength of association. Further, a multivariable logistic regression model was fit to determine which other variables were significantly associated with HIV infection. The study was approved by University of Fort Hare Interim Research Ethics Committee and National Health Sciences Research Committee in Malawi. The overall prevalence of HIV infection was 11.5 percent. However, it was less than half in circumcised males (7.4 percent) compared with uncircumcised counterparts (15.6 vi percent). While Fisher’s exact test revealed a borderline statistically significant association between male circumcision status and HIV infection (p 0.055), Pearson’s chi-square test showed a stronger significant association between the two variables ( p 0.036). The strength of the association was manifested by the odds of HIV infection being roughly 0.43 times lower for circumcised males than their uncircumcised counterparts with a 95 percent confidence interval of (0.20 0.96). Although the association was maintained after controlling for some variables, it lost statistical significance when adjusted for other variables. A multivariable logistic regression revealed that three other variables had significant associations with HIV infection and these were: falling in the age group of 25 years or more (OR 4.69; p 0.020), having had sex with an HIV positive partner (OR 12.15; p 0.000) and having contracted a sexually transmitted infection (OR 3.25; p 0.032). Male circumcision status is significantly related to HIV infection. Although the study involved a small sample size and undertaken in one district in Malawi, the finding is consistent with existing clinic-based findings in literature that indicate a lower risk of HIV infection in circumcised males than in uncircumcised males. Consequently, male circumcision could be considered if it can prove to be a public health intervention in the Malawi context aimed at reducing the risk of uncircumcised males becoming infected by HIV.
- Full Text:
- Date Issued: 2012
- Authors: Kankuwe, Hector Master
- Date: 2012
- Subjects: HIV infections -- Malawi , Initiation rites -- Malawi
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11778 , http://hdl.handle.net/10353/462 , HIV infections -- Malawi , Initiation rites -- Malawi
- Description: The overall objective of the study was to investigate the relationship between male circumcision status and HIV infection in men from Salima district in Malawi. A cross-sectional survey-based study of men aged 15 years or more was conducted at three sites in Salima district, each of which targeted 90 participants, half of whom were circumcised and the other half uncircumcised. These participants had already decided on their own to visit HIV Testing and Counseling centres at these sites to know their HIV serostatus. Consenting men were drawn into the study using quota sampling, interviewed through a structured questionnaire in local language and tested for HIV during January and March 2011. Measures of association were performed using analysis of contingency tables and Pearson’s chi-square tests or Fisher’s exact tests for comparison of proportions in STATA version 11.0 and PASW Statistics 18.0 software. Unadjusted odds ratios were used to approximate the direction and strength of association. Further, a multivariable logistic regression model was fit to determine which other variables were significantly associated with HIV infection. The study was approved by University of Fort Hare Interim Research Ethics Committee and National Health Sciences Research Committee in Malawi. The overall prevalence of HIV infection was 11.5 percent. However, it was less than half in circumcised males (7.4 percent) compared with uncircumcised counterparts (15.6 vi percent). While Fisher’s exact test revealed a borderline statistically significant association between male circumcision status and HIV infection (p 0.055), Pearson’s chi-square test showed a stronger significant association between the two variables ( p 0.036). The strength of the association was manifested by the odds of HIV infection being roughly 0.43 times lower for circumcised males than their uncircumcised counterparts with a 95 percent confidence interval of (0.20 0.96). Although the association was maintained after controlling for some variables, it lost statistical significance when adjusted for other variables. A multivariable logistic regression revealed that three other variables had significant associations with HIV infection and these were: falling in the age group of 25 years or more (OR 4.69; p 0.020), having had sex with an HIV positive partner (OR 12.15; p 0.000) and having contracted a sexually transmitted infection (OR 3.25; p 0.032). Male circumcision status is significantly related to HIV infection. Although the study involved a small sample size and undertaken in one district in Malawi, the finding is consistent with existing clinic-based findings in literature that indicate a lower risk of HIV infection in circumcised males than in uncircumcised males. Consequently, male circumcision could be considered if it can prove to be a public health intervention in the Malawi context aimed at reducing the risk of uncircumcised males becoming infected by HIV.
- Full Text:
- Date Issued: 2012
Prevalence, seasonal trends and incidences of cattle tuberculosis and brucellosis in the Cacadu municipality, Eastern Cape, South Africa
- Authors: Nombebe, Thobeka
- Date: 2012
- Subjects: Tuberculosis in cattle -- South Africa -- Eastern Cape , Brucellosis in animals -- South Africa -- Eastern Cape , Dairy farms -- South Africa -- Eastern Cape , Mycobacterium tuberculosis -- South Africa -- Eastern Cape
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11783 , http://hdl.handle.net/10353/d1016200 , Tuberculosis in cattle -- South Africa -- Eastern Cape , Brucellosis in animals -- South Africa -- Eastern Cape , Dairy farms -- South Africa -- Eastern Cape , Mycobacterium tuberculosis -- South Africa -- Eastern Cape
- Description: A cross-sectional study was conducted from February 2011 to August 2012 to investigate the status and identify risk factors for Bovine Tuberculosis (BTB) and cattle Brucellosis. A total of 1277 cattle from 6 selected dairy farms were tested. The farms were purposively selected on suspected risk. Samples were analysed using Rose Bengal Test (RBPT) and Complement Fixation Test (CFT) for Brucellosis and Comparative Intradermal Tuberculin Test (CITT) for BTB. The results revealed the overall prevalence of 1.6% for Brucellosis and no BTB was found. Logistic regression analysis revealed that age of cattle, herd size and number of calves a cow has had significant association with Brucellosis with p-values 0.0071, 0.0490 and 0.000 respectively. The role of location (p>0.05), gender (p>0.05) and breed (p>0.05) in the occurrence of the disease was not statistically significant at α=0.05, although higher rates were obtained in females and Jersey breed. Questionnaires were also administered to 47 individuals a total of 12 females and 35 males. Most respondents were not aware about cattle brucellosis and cattle tuberculosis. Consumption of raw or unpasteurized milk still occurs with 74.75% of respondents revealed.
- Full Text:
- Date Issued: 2012
- Authors: Nombebe, Thobeka
- Date: 2012
- Subjects: Tuberculosis in cattle -- South Africa -- Eastern Cape , Brucellosis in animals -- South Africa -- Eastern Cape , Dairy farms -- South Africa -- Eastern Cape , Mycobacterium tuberculosis -- South Africa -- Eastern Cape
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11783 , http://hdl.handle.net/10353/d1016200 , Tuberculosis in cattle -- South Africa -- Eastern Cape , Brucellosis in animals -- South Africa -- Eastern Cape , Dairy farms -- South Africa -- Eastern Cape , Mycobacterium tuberculosis -- South Africa -- Eastern Cape
- Description: A cross-sectional study was conducted from February 2011 to August 2012 to investigate the status and identify risk factors for Bovine Tuberculosis (BTB) and cattle Brucellosis. A total of 1277 cattle from 6 selected dairy farms were tested. The farms were purposively selected on suspected risk. Samples were analysed using Rose Bengal Test (RBPT) and Complement Fixation Test (CFT) for Brucellosis and Comparative Intradermal Tuberculin Test (CITT) for BTB. The results revealed the overall prevalence of 1.6% for Brucellosis and no BTB was found. Logistic regression analysis revealed that age of cattle, herd size and number of calves a cow has had significant association with Brucellosis with p-values 0.0071, 0.0490 and 0.000 respectively. The role of location (p>0.05), gender (p>0.05) and breed (p>0.05) in the occurrence of the disease was not statistically significant at α=0.05, although higher rates were obtained in females and Jersey breed. Questionnaires were also administered to 47 individuals a total of 12 females and 35 males. Most respondents were not aware about cattle brucellosis and cattle tuberculosis. Consumption of raw or unpasteurized milk still occurs with 74.75% of respondents revealed.
- Full Text:
- Date Issued: 2012
A cox proportional hazard model for mid-point imputed interval censored data
- Authors: Gwaze, Arnold Rumosa
- Date: 2011
- Subjects: Statistics -- Econometric models , Survival analysis (Biometry) , Mathematical statistics -- Data processing , Nonparametric statistics , Sampling (Statistics) , Multiple imputation (Statistics)
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11780 , http://hdl.handle.net/10353/385 , http://hdl.handle.net/10353/d1001135 , Statistics -- Econometric models , Survival analysis (Biometry) , Mathematical statistics -- Data processing , Nonparametric statistics , Sampling (Statistics) , Multiple imputation (Statistics)
- Description: There has been an increasing interest in survival analysis with interval-censored data, where the event of interest (such as infection with a disease) is not observed exactly but only known to happen between two examination times. However, because so much research has been focused on right-censored data, so many statistical tests and techniques are available for right-censoring methods, hence interval-censoring methods are not as abundant as those for right-censored data. In this study, right-censoring methods are used to fit a proportional hazards model to some interval-censored data. Transformation of the interval-censored observations was done using a method called mid-point imputation, a method which assumes that an event occurs at some midpoint of its recorded interval. Results obtained gave conservative regression estimates but a comparison with the conventional methods showed that the estimates were not significantly different. However, the censoring mechanism and interval lengths should be given serious consideration before deciding on using mid-point imputation on interval-censored data.
- Full Text:
- Date Issued: 2011
- Authors: Gwaze, Arnold Rumosa
- Date: 2011
- Subjects: Statistics -- Econometric models , Survival analysis (Biometry) , Mathematical statistics -- Data processing , Nonparametric statistics , Sampling (Statistics) , Multiple imputation (Statistics)
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11780 , http://hdl.handle.net/10353/385 , http://hdl.handle.net/10353/d1001135 , Statistics -- Econometric models , Survival analysis (Biometry) , Mathematical statistics -- Data processing , Nonparametric statistics , Sampling (Statistics) , Multiple imputation (Statistics)
- Description: There has been an increasing interest in survival analysis with interval-censored data, where the event of interest (such as infection with a disease) is not observed exactly but only known to happen between two examination times. However, because so much research has been focused on right-censored data, so many statistical tests and techniques are available for right-censoring methods, hence interval-censoring methods are not as abundant as those for right-censored data. In this study, right-censoring methods are used to fit a proportional hazards model to some interval-censored data. Transformation of the interval-censored observations was done using a method called mid-point imputation, a method which assumes that an event occurs at some midpoint of its recorded interval. Results obtained gave conservative regression estimates but a comparison with the conventional methods showed that the estimates were not significantly different. However, the censoring mechanism and interval lengths should be given serious consideration before deciding on using mid-point imputation on interval-censored data.
- Full Text:
- Date Issued: 2011
Preliminary investigation into estimating eye disease incidence rate from age specific prevalence data
- Authors: Majeke, Lunga
- Date: 2011
- Subjects: Medicine -- Research -- Statistical methods , Eye -- Diseases -- Statistics , Incidence functions , Regression analysis -- Data processing , Regression analysis -- Mathematical models -- Evaluation , Medical statistics
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11776 , http://hdl.handle.net/10353/464 , Medicine -- Research -- Statistical methods , Eye -- Diseases -- Statistics , Incidence functions , Regression analysis -- Data processing , Regression analysis -- Mathematical models -- Evaluation , Medical statistics
- Description: This study presents the methodology for estimating the incidence rate from the age specific prevalence data of three different eye diseases. We consider both situations where the mortality may differ from one person to another, with and without the disease. The method used was developed by Marvin J. Podgor for estimating incidence rate from prevalence data. It delves into the application of logistic regression to obtain the smoothed prevalence rates that helps in obtaining incidence rate. The study concluded that the use of logistic regression can produce a meaningful model, and the incidence rates of these diseases were not affected by the assumption of differential mortality.
- Full Text:
- Date Issued: 2011
- Authors: Majeke, Lunga
- Date: 2011
- Subjects: Medicine -- Research -- Statistical methods , Eye -- Diseases -- Statistics , Incidence functions , Regression analysis -- Data processing , Regression analysis -- Mathematical models -- Evaluation , Medical statistics
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11776 , http://hdl.handle.net/10353/464 , Medicine -- Research -- Statistical methods , Eye -- Diseases -- Statistics , Incidence functions , Regression analysis -- Data processing , Regression analysis -- Mathematical models -- Evaluation , Medical statistics
- Description: This study presents the methodology for estimating the incidence rate from the age specific prevalence data of three different eye diseases. We consider both situations where the mortality may differ from one person to another, with and without the disease. The method used was developed by Marvin J. Podgor for estimating incidence rate from prevalence data. It delves into the application of logistic regression to obtain the smoothed prevalence rates that helps in obtaining incidence rate. The study concluded that the use of logistic regression can produce a meaningful model, and the incidence rates of these diseases were not affected by the assumption of differential mortality.
- Full Text:
- Date Issued: 2011
Randomization in a two armed clinical trial: an overview of different randomization techniques
- Authors: Batidzirai, Jesca Mercy
- Date: 2011
- Subjects: Clinical trials -- Statistical methods , Biometry , Sampling (Statistics)
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11781 , http://hdl.handle.net/10353/395 , Clinical trials -- Statistical methods , Biometry , Sampling (Statistics)
- Description: Randomization is the key element of any sensible clinical trial. It is the only way we can be sure that the patients have been allocated into the treatment groups without bias and that the treatment groups are almost similar before the start of the trial. The randomization schemes used to allocate patients into the treatment groups play a role in achieving this goal. This study uses SAS simulations to do categorical data analysis and comparison of differences between two main randomization schemes namely unrestricted and restricted randomization in dental studies where there are small samples, i.e. simple randomization and the minimization method respectively. Results show that minimization produces almost equally sized treatment groups, but simple randomization is weak in balancing prognostic factors. Nevertheless, simple randomization can also produce balanced groups even in small samples, by chance. Statistical power is also improved when minimization is used than in simple randomization, but bigger samples might be needed to boost the power.
- Full Text:
- Date Issued: 2011
- Authors: Batidzirai, Jesca Mercy
- Date: 2011
- Subjects: Clinical trials -- Statistical methods , Biometry , Sampling (Statistics)
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11781 , http://hdl.handle.net/10353/395 , Clinical trials -- Statistical methods , Biometry , Sampling (Statistics)
- Description: Randomization is the key element of any sensible clinical trial. It is the only way we can be sure that the patients have been allocated into the treatment groups without bias and that the treatment groups are almost similar before the start of the trial. The randomization schemes used to allocate patients into the treatment groups play a role in achieving this goal. This study uses SAS simulations to do categorical data analysis and comparison of differences between two main randomization schemes namely unrestricted and restricted randomization in dental studies where there are small samples, i.e. simple randomization and the minimization method respectively. Results show that minimization produces almost equally sized treatment groups, but simple randomization is weak in balancing prognostic factors. Nevertheless, simple randomization can also produce balanced groups even in small samples, by chance. Statistical power is also improved when minimization is used than in simple randomization, but bigger samples might be needed to boost the power.
- Full Text:
- Date Issued: 2011
Maximization of power in randomized clinical trials using the minimization treatment allocation technique
- Authors: Marange, Chioneso Show
- Date: 2010
- Subjects: Clinical trials -- Statistical methods , Statistical hypothesis testing , Regression analysis , Logistic distribution , Estimation theory
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11777 , http://hdl.handle.net/10353/399 , Clinical trials -- Statistical methods , Statistical hypothesis testing , Regression analysis , Logistic distribution , Estimation theory
- Description: Generally the primary goal of randomized clinical trials (RCT) is to make comparisons among two or more treatments hence clinical investigators require the most appropriate treatment allocation procedure to yield reliable results regardless of whether the ultimate data suggest a clinically important difference between the treatments being studied. Although recommended by many researchers, the utilization of minimization has been seldom reported in randomized trials mainly because of the controversy surrounding the statistical efficiency in detecting treatment effect and its complexity in implementation. Methods: A SAS simulation code was designed for allocating patients into two different treatment groups. Categorical prognostic factors were used together with multi-level response variables and demonstration of how simulation of data can help to determine the power of the minimization technique was carried out using ordinal logistic regression models. Results: Several scenarios were simulated in this study. Within the selected scenarios, increasing the sample size significantly increased the power of detecting the treatment effect. This was contrary to the case when the probability of allocation was decreased. Power did not change when the probability of allocation given that the treatment groups are balanced was increased. The probability of allocation { } k P was seen to be the only one with a significant effect on treatment balance. Conclusion: Maximum power can be achieved with a sample of size 300 although a small sample of size 200 can be adequate to attain at least 80% power. In order to have maximum power, the probability of allocation should be fixed at 0.75 and set to 0.5 if the treatment groups are equally balanced.
- Full Text:
- Date Issued: 2010
- Authors: Marange, Chioneso Show
- Date: 2010
- Subjects: Clinical trials -- Statistical methods , Statistical hypothesis testing , Regression analysis , Logistic distribution , Estimation theory
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11777 , http://hdl.handle.net/10353/399 , Clinical trials -- Statistical methods , Statistical hypothesis testing , Regression analysis , Logistic distribution , Estimation theory
- Description: Generally the primary goal of randomized clinical trials (RCT) is to make comparisons among two or more treatments hence clinical investigators require the most appropriate treatment allocation procedure to yield reliable results regardless of whether the ultimate data suggest a clinically important difference between the treatments being studied. Although recommended by many researchers, the utilization of minimization has been seldom reported in randomized trials mainly because of the controversy surrounding the statistical efficiency in detecting treatment effect and its complexity in implementation. Methods: A SAS simulation code was designed for allocating patients into two different treatment groups. Categorical prognostic factors were used together with multi-level response variables and demonstration of how simulation of data can help to determine the power of the minimization technique was carried out using ordinal logistic regression models. Results: Several scenarios were simulated in this study. Within the selected scenarios, increasing the sample size significantly increased the power of detecting the treatment effect. This was contrary to the case when the probability of allocation was decreased. Power did not change when the probability of allocation given that the treatment groups are balanced was increased. The probability of allocation { } k P was seen to be the only one with a significant effect on treatment balance. Conclusion: Maximum power can be achieved with a sample of size 300 although a small sample of size 200 can be adequate to attain at least 80% power. In order to have maximum power, the probability of allocation should be fixed at 0.75 and set to 0.5 if the treatment groups are equally balanced.
- Full Text:
- Date Issued: 2010
Statistical methods to model the influence of age and gender on the behavioral risk factors of HIV/AIDS
- Authors: Tlou, Boikhutso
- Date: 2010
- Subjects: AIDS (Disease) -- Statistics , HIV infections -- Statistics , AIDS (Disease) -- South Africa , Health risk assessment , HIV infections -- South Africa , AIDS (Disease) -- Social aspects
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11779 , http://hdl.handle.net/10353/400 , AIDS (Disease) -- Statistics , HIV infections -- Statistics , AIDS (Disease) -- South Africa , Health risk assessment , HIV infections -- South Africa , AIDS (Disease) -- Social aspects
- Description: The effects of gender and age on the behavioral risk of HIV/AIDS are not clearly understood as previous distinct studies which have been carried out, have given disputable and contradictory outcomes. This study therefore, discusses the statistical methods which can be used to model the influence of age and gender on the behavioral risk factors of HIV/AIDS. In general, generalized linear models are the main methods which can be applied to depict the impact of age and gender on the behavioral risk of becoming infected with HIV/AIDS virus. In this study, the main methods used were logistic regression, log-linear regression and multiple regressions. Behavioral risk was taken as the dependent variable while age, gender, number of sexual partners, religious beliefs and alcohol and drug abuse were fitted as predictor variables. The three statistical methods gave significant results for gender and insignificant results for age. Furthermore, comparisons were made on the three regression methods and the logistic regression gave the best results. It was therefore concluded that gender plays a significant role on the behavioral risk of HIV/AIDS. The results of the study showed that gender of the student and number of sexual partners had a significant effect on the risk behavior of the university students. In future, it may be very important to find out why age is not a significant factor on risk behavior of HIV/AIDS among university students.
- Full Text:
- Date Issued: 2010
- Authors: Tlou, Boikhutso
- Date: 2010
- Subjects: AIDS (Disease) -- Statistics , HIV infections -- Statistics , AIDS (Disease) -- South Africa , Health risk assessment , HIV infections -- South Africa , AIDS (Disease) -- Social aspects
- Language: English
- Type: Thesis , Masters , MSc (Biostatistics and Epidemiology)
- Identifier: vital:11779 , http://hdl.handle.net/10353/400 , AIDS (Disease) -- Statistics , HIV infections -- Statistics , AIDS (Disease) -- South Africa , Health risk assessment , HIV infections -- South Africa , AIDS (Disease) -- Social aspects
- Description: The effects of gender and age on the behavioral risk of HIV/AIDS are not clearly understood as previous distinct studies which have been carried out, have given disputable and contradictory outcomes. This study therefore, discusses the statistical methods which can be used to model the influence of age and gender on the behavioral risk factors of HIV/AIDS. In general, generalized linear models are the main methods which can be applied to depict the impact of age and gender on the behavioral risk of becoming infected with HIV/AIDS virus. In this study, the main methods used were logistic regression, log-linear regression and multiple regressions. Behavioral risk was taken as the dependent variable while age, gender, number of sexual partners, religious beliefs and alcohol and drug abuse were fitted as predictor variables. The three statistical methods gave significant results for gender and insignificant results for age. Furthermore, comparisons were made on the three regression methods and the logistic regression gave the best results. It was therefore concluded that gender plays a significant role on the behavioral risk of HIV/AIDS. The results of the study showed that gender of the student and number of sexual partners had a significant effect on the risk behavior of the university students. In future, it may be very important to find out why age is not a significant factor on risk behavior of HIV/AIDS among university students.
- Full Text:
- Date Issued: 2010
- «
- ‹
- 1
- ›
- »