SAS Applications in Demography II - MD360P39N
Title: Demografické aplikace SAS II
Czech title: Demografické aplikace SAS II
Guaranteed by: Department of Demography and Geodemography (31-360)
Faculty: Faculty of Science
Actual: from 2018 to 2023
Semester: summer
E-Credits: 3
Examination process: summer s.:combined
Hours per week, examination: summer s.:1/1, Ex [HT]
Capacity: unlimited
Min. number of students: unlimited
4EU+: no
Virtual mobility / capacity: no
State of the course: taught
Language: Czech
Level: specialized
Note: enabled for web enrollment
Guarantor: prof. RNDr. Jitka Rychtaříková, CSc.
Teacher(s): prof. RNDr. Jitka Rychtaříková, CSc.
Opinion survey results   Examination dates   SS schedule   
Annotation -
Last update: prof. RNDr. Jitka Rychtaříková, CSc. (29.06.2021)
The course introduses students to the SAS software with lot of practical examples. In addition, selected procedures from SAS/STAT software are taught in order to use multidimensional statistics in demography.
Literature -
Last update: RNDr. Barbora Janáková Kuprová, Ph.D. (22.12.2019)

Obligatory literature:

Base SAS 9.4 Procedures Guide.

SAS/STAT 9.4 Procedures Guide: Statistical Procedures.

Computing Direct and Indirect Standardized Rates and Risks with the STDRATE Procedure, Paper 423-2013;

The Basics of Creating Graphs with SAS/GRAPH Software;

Applied Survival Analysis by Hosmer, Lemeshow and May;

Modeling Survival Data with Parametric Regression Models;

Using the PHREG Procedure to Analyze Competing-Risks Data;

ŘEHÁKOVÁ, B. (2000): Nebojte se logistické regrese, Sociologický časopis, 36, 4. l Doporučená literatura:

Kleinbaum, D. G., KLEIN, M. (2011): Survival Analysis, A Self-Learning Text, Springer.

Kleinbaum, D. G., KLEIN, M. (2010): Logistic Regression, A Self-Learning Text, Springer.

Hendl, J. (2004): Přehled statistických metod zpracování dat. Praha: Portál.

Wonnacot, T. - Wonnacot, R. (1995): Statistika pro obchod a hospodářství. Praha: Victoria Publishing.

Requirements to the exam -
Last update: prof. RNDr. Jitka Rychtaříková, CSc. (29.06.2021)

Examination: written. Precondition is the final written test (program preparation) and active participation in lessons are required.

Syllabus -
Last update: prof. RNDr. Jitka Rychtaříková, CSc. (29.06.2021)


1.   The STDRATE procedure (SAS/STAT) computes directly standardized rates and risks, indirectly standardized rates and risks, and Mantel-Haenszel estimates, including their confidence limits. For two study populations with the same reference population, PROC STDRATE compares directly standardized rates or risks from these two populations.


2.   SAS/GRAPH. The GPLOT procedure plots the values of two or more variables on a set of coordinate axes (X and Y). It creates line plots, scatters, histograms, area plots, bubble plots, high-low plots, needle plots, plots with simple or spline-interpolated lines. etc.). GCHART procedure produces six types of charts: block charts, horizontal and vertical bar charts, pie and donut charts, and star charts. GBARLINE procedure creates bar-line charts; vertical barcharts with one or more plot overlays.


3.   The LIFETEST procedure (SAS/STAT) computes nonparametric estimates of the survivor functions, compares survival curves, and computes tests for association of the failure time variable with covariates. Censoring. Nonparametric estimates of the survivor function are computed either by the product-limit method (also called the Kaplan-Meier method) or by the life-table method (also called the actuarial method). The survival distribution function (SDF), the cumulative distribution function (CDF), the probability density function (PDF), and the hazard function, including standard errors, are estimated.


4.   The LIFEREG procedure (SAS/STAT) fits parametric models to failure time data that can be uncensored, right censored, left censored, or interval censored. The exponential, Weibull, lognormal, and other distributions are supported. The models are equivalent to accelerated failure time models when the log of the response is the quantity being modeled. The effect of independent variables on an event time distribution is multiplicative. The estimates of parameters are made by maximum likelihood method.


5.   The PHREG procedure (SAS/STAT) performs regression analysis of survival data based on the Cox proportional hazards model known as multiplicative hazard model. Cox's model is used in the analysis of survival data to explain the effect of explanatory variables (including time-dependent variables) on hazard rates. The Cox proportional hazards model (semi-parametric) makes the assumption that the hazards for subgroups are proportional to the baseline hazard. Cox model is fitted by maximizing the partial likelihood. The CLASS statement enables the classification variables to be used, in addition to continuous variables, as explanatory variables in the analysis.


6.   The LOGISTIC procedure fits logistic models, in which the response can be binary or ordinal or nominal. Logistic regression analysis is used to investigate the relationship between these discrete responses and a set of explanatory variables that can be continuous or categorical. Link function is logit function. The model is fitted by the method of maximum likelihood. Odds ratios are displayed along with parameter estimates. 


7.   The GENMOD (SAS/STAT) procedure fits generalized linear models.The generalized linear models are an extension of traditional linear models that allows the mean of a population to depend on a linear predictor through a nonlinear link function and allows the response probability distribution to be any member of an exponential family of distributions. Poisson Regression for Count data and Poisson Regression for Rate data. Poisson regression is used for modeling count or rate data with the assumption that the conditional mean equal the conditional variance.


8.   The QUANTLIFE Procedure(SAS/STAT). Quantile regression analysis  is a type of regression analysis that explores how the conditional quantile of a response variable depends on its covariates. Quantile regression offers a powerful tool in survival analysis, where the lifetimes are skewed and extreme survival times can be of special interest. It accounts for censoring and provide valid estimates. The method is distribution-free and apply to heteroscedastic data.