Learning outcomes of the course unit
The course is divided into two parts.
In the first part the tools of descriptive exploratory statistics are described. THE FUNDAMENTAL GOAL IS TO
ALLOW THE STUDENT TO BECOME COMFORTABLE WITH THE QUANTITATIVE ANALYSIS
OF COMPANY AND ECONOMIC DATA SO THAT HE/SHE WILL BE ABLE TO
INDEPENDENTLY AND CORRECTLY PROCESS AND ANALYSE PROCESSING RESULTS. TO
ATTAIN THIS GOAL, ATTENTION IS FOCUSED ON A NARROW RANGE OF TECHNIQUES,
BUT THOSE WHICH ARE WIDELY USED IN A PRACTICAL CONTEXT. IN PARTICULAR,
THE METHODS EXAMINED INCLUDE SYNTHESIS OF A SINGLE VARIABLE (FREQUENCY
DISTRIBUTION, MEANS, VARIABILITY INDICES), CALCULATION OF SIMPLE AND
COMPOUND INDEX NUMBERS, STUDY OF THE CORRELATION BETWEEN TWO
QUANTITATIVE VARIABLES AND FITTING OF A REGRESSION LINE. FOR EACH
TECHNIQUE, THE LOGICAL BASES AND COGNITIVE GOALS WILL BE EXPLAINED,
WHILE THE TECHNICAL DETAILS AND MATHEMATICAL DERIVATIONS ARE GIVEN
SECONDARY IMPORTANCE. FROM THIS STANDPOINT, EACH TECHNIQUE IS INTRODUCED
IN REFERENCE TO THE BUSINESS AND ECONOMIC PROBLEMS THAT THE TECHNIQUE
COULD CONTRIBUTE TO SOLVING (WITH SIMPLIFIED EXAMPLES THAT CAN BE
PERFORMED IN DETAIL IN THE CLASSROOM) AND EXTENSIVE TIME DEDICATED TO
CRITICAL INTERPRETATION OF THE RESULTS.
The second part of the course deals with inferential statistics and basic concepts linked to probability calculus. In particular, methods of estimation and hypothesis testing are considered. The logical foundations and knowledge purposes of each technique are illustrated, while technical details and mathematical derivations take second place. Each technique is introduced with reference to the business and economic problems that it can help to solve, and include statistical quality control, study of market shares and analysis of relations between economic variables.
Basic knowledge of maths
Course contents summary
DATA COLLECTION AND STATISTICAL SOURCES.
DATA MATRIX, GRAPHIC REPRESENTATION, USE OF A SPREADSHEET.
FREQUENCY DISTRIBUTION AND CONTINGENCY TABLES.
MEANS (ARITHMETIC, MEDIAN AND QUARTILES, MODE).
INDICES OF ABSOLUTE VARIABILITY (VARIANCE, STANDARD DEVIATION, RANGE) AND RELATIVE VARIABILITY (VARIATION COEFFICIENT).
FORM OF DISTRIBUTION.
SIMPLE INDEX NUMBERS.
LINKING OF SERIES WITH DIFFERENT BASES; AVERAGE ANNUAL RATE OF
COMPOUND PRICE INDEX NUMBERS AND DEFLATION OF VALUES AT CURRENT PRICES.
COVARIANCE AND LINEAR CORRELATION COEFFICIENT.
COVARIANCE MATRIX AND CORRELATION MATRIX.
REGRESSION LINE: LEAST SQUARES; PARAMETER INTERPRETATION;
GOODNESS OF FIT.
LINEAR INTERPOLATION OF A TIME SERIES.
Concepts of probability
Random variables: general aspects and applications
Sampling distributions of statistical indices
Point estimate of the mean and of relative frequency
Interval estimate of the mean in large and small samples
Interval estimate of relative frequency in large samples
Introduction to statistical hypothesis testing; observed significance value (P-value)
Mean hypothesis testing in large and small samples
Hypothesis testing for relative frequency in large samples
Hypothesis testing for two universes in large samples
Model significance and relations with the regression line
Problems of estimation and hypothesis testing on model parameters
Testing the good fit of the model; analysis of variance.
M.A. MILIOLI, M. RIANI, S. ZANI, Introduzione all’analisi dei dati statistici, III edizione ampliata, Pitagora, Bologna, 2016.
A. Cerioli, M. A. Milioli, Introduzione all’inferenza statistica senza (troppo) sforzo, II edizione, Uni.nova, Parma, 2007.
A. Cerioli, M. A. Milioli, M. Riani, Esercizi di statistica, V edizione, Uninova, Parma, 2016.
Lectures and tutorials
Assessment methods and criteria