Universitat Internacional de Catalunya - Barcelona

Biostatistics 2

• code 12186
• course 1
• term Semester 1
• type OB
• credits 3

Main language of instruction: Catalan

Other languages of instruction: English, Spanish

Head instructor

Dr. Juan Carlos MARTÍN - jcmartin@uic.es

Office hours

Head instructor: PhD Juan Carlos Martín Sánchez (jcmartin@uic.es)

This subject is guided to training the students with the necessary bioestatisics tools to critically assess the methodology of the research articles in Health Sciences. As well as, provide students biostatistics techniques so they can develop and carry out research projects in Health Sciences.

In the area of Health Sciences, human populations are heterogeneous with respect to certain characteristics that may predispose a given disease. In this sense, the study of this variability with regression models has become a useful tool to study the relationship between disease and population characteristics. The purpose of this subject is to present the regression models commonly used to research in Health Sciences.

The student should have taken and passed the Biostatistic I subject.

1. To present the most useful regression models depending on the purpose of the study and the variable of interest
2. To estimate, form, and validate the classical regression statistical programs
3. To interpret the results of the regression models provided by the software
4. To encourage the critical interpretation of scientific literature in which regression models are applied

• CE1 - To know how to apply scientific methods, experimental design and biostatistics to answer a question or corroborate a hypothesis in a clinical setting.
• CE6 - To know how to describe and apply the most common techniques for exploring and analysing data, the relationship between variables or categories and/or corroborating hypotheses in both quantitative and qualitative research.
• CE9 - To know how to apply specific theoretical and practical knowledge to health science research.
• CG2 - The ability to critically analyse and discuss research results and transmit the relevant outcomes.

Students will be able to determine the statistical methods needed to answer scientific questions arising when conducting a research study. They will learn to formulate statistical hypotheses from a scientific question and answer from a statistical standpoint. You will learn to make models of multiple linear regression, logistic regression and Cox regression, and selecting the regression model according to the purpose of the study and the data available.

The students will develop skills to read critically the statistical methodology and the results of a scientific article and they will also be able to interpret and communicate the results of the regression models. Additionally, the student will be familiar with the use of statistical software that allows you to perform the analysis of the data generated in your research, knowing estimate, form and validate regression models using such statistical software.

Block 1. Review Advanced Statically I subject

Block 2. Introduction to linear regression model and ANOVA

Block 3. Logistic regression model

• Epidemiology review: Measures of frequency and measures of association

Block 4. Introduction to survival analysis

• Kaplan-Meier and log-rank
• Cox regression model
• Advanced concepts in survival analysis

Activities will be conducted in and outside the classroom. In the classroom will be taught lectures and tutored practical exercises and oral presentations. Outside the classroom work will be individual.  

The methodology used in this subject will consist of theoretical presentations (30%) and case methods and computer practice (70%).

It will be carried a mixed evaluation which will have three components:

1. Continuous evaluation of students (20%) base on the following criteria:

• Assistance to the theorical sessions, case methods and laboratory practices
• Participation in the methods of the case and laboratory practice
• Oral and written communication of the results

2. Evaluation of different works of the subject (50%):

• Works of different methods of case (25%)
• Laboratories practices (25%)

3. Final test (30%)

• Multiple-choice test between 20 and 40 questions, with  4 answers and only one correct

To pass the course the student must obtain a minimum score of 5 in each of the three components of the evaluation of the subject.

General references

Martínez-González MA, Sánchez-Villegas, Faulín Fajardos FJ. Bioestadística amigable. 2ª Edición. Ediciones Díaz de Santos, 2006. 

Katz MH. Multivariable Analysis: A Practical Guide for Clinicians. Cambridge University Press, 2006.

Szklo M, Nieto J (traducción Luis Carlos Silva y Rosa Jiménez). Epidemiologia intermedia. Diaz de Santos. 2003.

Alan Grafen, Rosie Hails. Modern statistics for the life sciences.OxfordUniversityPress, 2002.

Martin Bland. An Introduction to medical statistics.OxfordUniversityPress, 1990.

Hosmer, DW, Lemeshow S. Applied logistic regression.New York. John Wiley & Sons. 2000.

Hosmer, DW, Lemeshow S. Applied survival analysis: regression modeling of time to event data.New York. John Wiley & Sons. 1999.

Rabe-Hesketh S. Everitt B. A Handbook of Statistical Analyses Using Stata, 4th Edition. Chapman & Hall/CRC. 2007.

Hilbe JM. Logistic Regression Models.Boca Raton: Chapman & Hall/CRC, 2009.

ClevesM, Gould WW, Gutierrez RB, Marchenko Y. An Introduction to survival analysis using stata. College Station, Texas : Stata Press, 2010.

Silva LC. Excursión a la regresión logística en ciencias de la salud. Madrid: Díaz de Santos, cop.1995.

Papers recommended

Lineal regression

Cozzi-Lepri A, Prosperi MC, Kjær J, Dunn D, Paredes R, Sabin CA et al. Can linear regression modeling help clinicians in the interpretation of genotypic resistance data? An application to derive a lopinavir-score. PLoS One. 2011; 6(11): e25665.

Hart J. Association between heart rate variability and manual pulse rate. J Can Chiropr Assoc. 2013; 57(3):243-50.

Marconi VC, Grandits G, Okulicz JF, Wortmann G, Ganesan A, Crum-Cianflone N et al. Cumulative viral load and virologic decay patterns after antiretroviral therapy in HIV-infected subjects influence CD4 recovery and AIDS. PLoS One. 2011; 6(5): e17956.

Phillips AN, Sabin CA, Elford J, Bofill M, Janossy G, Lee CA. Use of CD4 lymphocyte count to predict long-term survival free of AIDS after HIV infection. BMJ. 1994; 309(6950): 309-13.

Perrier E et al. Relation between urinary hydration biomarkers and total fluid intake in healthy adults. Eur J Clin Nutr. 2013; 67(9):939-43.

Rudge MV. et al. The safe motherhood referral system to reduce cesarean sections and perinatal mortality - a cross-sectional study [1995-2006]. Reprod Health. 2011; 8:34.

Silva LC, Barroso IM. Selección algorítmica de modelos en las aplicaciones biomédicas de la regresión múltiple. Med Clin (Barc) 2001; 116(19): 741-745.

Taylor R. Interpretation of the correlation coefficient: a basic review. J Diagn Med Sonogr 1990; 1:35-39.

Thorsteinsson K, Ladelund S, Jensen-Fangel S, Johansen IS, Katzenstein TL, Pedersen G et al. Impact of gender on response to highly active antiretroviral therapy in HIV-1 infected patients: a nationwide population-based cohort study. BMC Infect Dis. 2012; 12: 293.

Xu X, Hu H,DaileyAB,KearneyG, Talbott EO, Cook RL. Potential health impacts of heavy metals on HIV-infected population inUSA. PLoS One. 2013; 8(9): e74288.

Logistic regression

Bland JM, Altman DG. The odds ratio. BMJ. 2000; 320 (7247): 1468.

Cortès I, et al. Desigualdades en la salud mental de la población ocupada. Gac Sanit. 2004: 18 (5): 351-9.

Silva LC. Una ceremonia estadística para identificar factores de riesgo. Salud Colect. 2005; 1(3): 309-22.

Survival analysis

Bland JM, Altman DG. Survival probabilities (the Kaplan-Meier method). BMJ. 1998; 317(7172): 1572.

Bland JM, Altman DG. The logrank test. BMJ. 2004; 328(7447): 1073.

Bull K, Spiegelhalter DJ. Survival analysis in observational studies: tutorial in biostatistics. Statistics in Medicine. 1997; 16(9): 1041-74.

ClarkTG, Bradburn MJ, Love SB, Altman DG. Survival analysis Part I: Basic concepts and first analyses. Br J Cancer 2003; 89(2): 232-8.

Cologne J, Hsu WL,Abbott RD, Ohishi W, Grant EJ, Fujiwara S et al. Proportional hazards regression in epidemiologic follow-up studies : an intuitive consideration of primary time scale. Epidemiology. 2012; 23(4): 565-73.

Fisher LD, Lin DY. Time-dependent covariates in the Cox proportional-hazards regression model. Annu. Rev. Public Health. 1999. 20:145-57.

Holmes MD,Chen WY, Feskanich D, Korenke CH, Coldits GA. Physical activity and survival after breast cancer diagnosis. JAMA. 2005; 293: 2479-86.

Lee WS, Yun SH, Chun HK, Lee WY, Yun HR, Kim J et al. Pulmonary resection for metastases from colorectal cancer: prognostic factors and survival. Int J Colorectal Dis. 2007; 22(6):699-704.