APPLIED STATISTICS

Prof. Joaquim Carvalho

Classes:

Monday: 07:30–2 classes

Thursday: 10:50–1 class

February 3

General Guidelines: Evaluation

First test: 04/18/11

Second test: 06/13/11

Second test: 27/06/11

The exams are worth 8 points (each) and the exercise lists provided are worth 2.
points, each. The minimum average for approval is 6.

The exams have 06 questions, all with a weight of 1.6. The student can choose to answer
just 05 or answer all. In this case, the teacher will disregard the lowest question.
performance.

A prova do segundo bimestre (N2B) pode ser substituída por trabalho de pesquisa. O trabalho
it can be done by teams of up to 3 members. The written part will be worth 3 points and
presentation 5. The exercise list (2 points) will complete the grade.

Calculation of the Average:

Average = (N1B x 4 + N2B x 6) / 10

Substitute exam: if the minimum average is not reached, the student will take a substitute exam.
with all the content, which will be worth 10 points and will replace the lowest bimonthly grade for
calculation of the average.
 February 7th

Menu

1. Fundamental Concepts
2. Construction of tables and graphs (a)
3. Frequency distribution of data (b)
4. Measures of central tendency: mean, mode, median (c)
5. Separating measures

Observations:

Scientific notation: coefficient between 0<x<10 multiplied by a power of 10. Ex.: 2.5 x 105

(a) Tables: The rules of ABNT - Brazilian Association of Technical Standards must be observed.
Techniques. Example: in the tables, the sides are not closed, as happens in frames. In
the body of the tables does not mark lines; these are only allowed in the header.
Note: charts and tables are different things: charts are used to present
data that has not been measured. Example: class schedule. The data in a frame
are set by criteria of convenience.

(b) Variables: discrete (counting object) or continuous (measurement object).

(c) Means: they can be arithmetic, geometric, and harmonic.

Example: (2, 4, 8, 16) - set of 4 elements
Arithmetic mean: Xa = (2+4+8+16)/4 = 7.5
Geometric mean: Xg = = 5.6...
Harmonic mean: Xh = 4 / (1/2 + 1/4 + 1/8 + 1/16) = 4.27...

Median: represents the 'center of the interval'

Moda: indica a frequência de repetição de elementos. Ex.: (2, 2, 6, 8, 8, 10, 12). Moda = (2, 8)
 February 10

Agenda - Continuation

6. Measures of dispersion (a) verifies the behavior of the data

Total amplitude
Mean absolute deviation
Variance
Standard deviation
Coefficient of variation
7. Measures of skewness and kurtosis
8. Notions of probability
Probability calculation
Probability distribution (Binomial, Normal and Student)
9. Confidence interval (for estimation)
Media
Proportion
Variance
Standard deviation
10. Determination of sample size
Media
Proportion
11. Hypothesis testing
Media
Proportion
Variance
Standard deviation
12. Concepts of regression and correlation (how to determine a mathematical model, its
representativeness and accuracy
13. (Construction of) Index numbers (b)

Observations:

(a) The measures of dispersion verify the behavior of the data. Example 1: three students
from a classroom they get grades 2, 7, and 10. By calculating the arithmetic mean, we will have 6.3, that is,
The class average is above the minimum passing grade. However, we see that 1/3 of the
the class is doing poorly, despite this good average. Example 2: the per capita income of Brazilians revolves around

around R$ 1,200.00/month. However, we know that in reality, more than 30 million

Millions of Brazilians live in extreme poverty.

there is no inflation rate, but rather a price rate.

 February 14th

OVERVIEW

1. GENERAL CONSIDERATIONS

1.1 Definition
Statistics is the area of Mathematics applied to the study of collective phenomena, of wide
coverage in both applied sciences and market inferences.
It is the collection of methods for planning experiments, obtaining and organizing data, summarizing them,
analyze them, interpret them and draw conclusions from them (Triola, 1999)1.
The word statistics is associated with status: from Latin, state.

1.2 Method
It is the set of means organized in a way to achieve the desired end.
It is the most effective way to achieve a certain goal.
The methods are classified as: empirical or scientific.

1.2.1 Empirical method

It is based on experiences accumulated by communities over time, without
necessarily requires proof.

1.2.2 Scientific method

It is based on lived observations, or not, by the communities; and these are assessed by
starting from hypothetical procedures using mathematical methodology. The
The scientific method can be: experimental or statistical.
The main difference between these is that the experimental method is used in research.
of phenomena in which it is allowed to vary only one of the causes that has influence
on the phenomenon, while the other causes remain constant; as for the method
statistics is used when it is not allowed to make constant causes that have
influences on the phenomenon and it becomes necessary to study the phenomenon in its entirety
its causes varying simultaneously.
This method, or statistical, is based on the description and inference of the phenomenon.
description includes the stages of collecting, organizing, and presenting the data; however the
inference involves the analysis and interpretation of data.

Statistics is divided into:

Descriptive Statistics: it is the part of statistics responsible for describing the data.
It includes the collection, organization, description of data, the calculation and the

1
The excerpts in blue are from the booklet 'Basic Statistics in Excel' by Bertolo or from the book.
Easy Statistics by Antônio Arnot Crespo.
 interpretation of coefficients. This part is associated with average calculations,
variances, study of graphs, tables, etc.. It is the most well-known part.
Inductive or Inferential Statistics: corresponds to the analysis and interpretation of the
data, associated with a margin of uncertainty, whose methods that are
are based on probability theory. In it, we find the Estimation of
Parameters, Hypothesis Testing, Modeling, etc. Or still, it is the part of
statistics that aim to obtain and generalize conclusions for a
population based on a sample, through probability calculation.

1.3 Phases of the Statistical Method

1.3.1 Collection
Defined in the work planning what phenomenon is to be measured and its
causes of influences, measurement instruments are set up to quantify it.
This part of the research involves data collection that can be direct or indirect.
a) Direct: made on various records (births, marriages, imports,
school records, etc.). It is classified according to the time factor as: continuous,
periodic (censuses) or occasional.
b) Indirect: made based on information already measured through direct collection or by
knowledge of causes related to the phenomenon. Ex.: infant mortality.

1.3.2 Critique
Optional application stage, it encompasses the process of screening the instruments.
from the research in search of possible errors in its preparation, or still, in the verification of
tabulated data. It can be classified as internal or external, depending on the
purpose: errors in the instruments or in the data, respectively.
It aims to seek flaws and imperfections in order to avoid errors in the results.
Some common mistakes: leading questions, preservation of self-image (the
interviewed mind, thinking about self-protection), more samples, more questions (which
writing makes it difficult for the interviewee to fully understand.

1.3.3 (Investigation, Reduction or) Organization

Corresponds to the stage of summing and processing the data, manually or
electronics.

February 17

OVERVIEW
1. GENERAL CONSIDERATIONS - continuation

1.3.4 Presentation or Exhibition

It is the way of presenting the processed data, and this can be done through
tables or graphs. It aims to make your examination and application easier in a
statistical calculation.
1.3.5 Analysis
Understand the final stage that is the discussion and conclusion of the results. If the
the research was conducted through sampling, so we can measure the
parameters based on these estimated results.

Through methods of inductive or inferential statistics, conclusions are drawn and

predictions of a whole through the examination of just a part of that whole. The errors and
inconsistencies that occurred in data collection must be corrected. The samples of
data must be grouped in a way that facilitates handling, visualization, and understanding
may be simplified.

Summarizing

tables
Critique of Analysis
Collection Organization Presentation
Data
graphics

One of the objectives of data analysis and interpretation is to seek a model for the
observations. These models can be essentially deterministic or non-deterministic
(probabilistic or stochastic).
In determinism, the conditions under which an experiment is conducted determine
the result of the experiment. Ex.: The current i can be determined by U/R (Ohm's Law)
Ohm) in an elementary resistive electrical circuit.
In non-deterministic models, a Probability Distribution is used. Ex.:
Parts are manufactured up to perfect pieces; the total number of
manufactured parts are counted. A distribution is used, in this case, the Geometric.
decision making.

2. FUNDAMENTAL CONCEPTS

2.1 Variables
It is commonly defined as the set of possible outcomes of a phenomenon. And
this can be classified as: qualitative or quantitative and also as parametric or non-parametric
parametric.

It is the set of possible outcomes of a phenomenon.

Examples: a) determination of the phenomenon sex: two possible outcomes, male and
feminino; b) determinação do fenômeno número de alunos na sala: resultados possíveis, os
natural numbers {0,1,2,3,4,...}.

The variable may be classified as parametric or non-parametric; this classification is made

based on the finding that the estimator is representative of the parameter in the population, if
If the answer is affirmative, then the variable will be parametric; otherwise, it will be non-parametric.
 Parametric

Variable
Non-parametric

2.1.1 Qualitative variable

When your values are expressed by attributes, for example: gender, manufacturer brand of
computers, professional specialty, characteristics of software, etc.

2.1.2 Quantitative variable

When your values are expressed in numbers, for example: employees' salaries,
processing time of a computer, lifespan of machines, etc.

This type of variable, quantitative, can be classified as: discrete or continuous.

Discrete: if the values are expressed in a pointwise manner.
Continues: if the values are expressed within limits

Nominal
Qualitative
Ordinal
Variable
Discrete
Quantitative
Continuous

Variable Type
Estado: Perfeita ou defeituosa Nominal Qualitative
Quality: 1st, 2nd or 3rd category Ordinal Qualitative
Number of defective parts Discrete Quantitative
Diameter of the pieces Continuous Quantitative

The quantitative variable can be continuous when it takes any value between two limits (e.g.: weight,
height, measurements), or it can be discrete, when it can only take values belonging to a set
enumerable (e.g., number of children, counting in general). We denote the variables by the Latin letters, x, y, z,
etc. For example, let there be a population (or sample) {2,3,4,5,9}, denoting by x the variable related to
phenomenon that gave rise to the population of results above, we have: x∈ {2,3,4,5,9}
In general, measurements give rise to continuous variables and counts to discrete variables.

2.1 Population and Sample

The study of any phenomenon, whether natural, social, or economic, requires the collection and analysis.
of statistical data. Data collection is, therefore, the initial phase of any research.
2.2.1 Population
It is the set of all items (people, things, objects) of interest in the study of the phenomenon.
of the object.

The population is the collection of all potential observations about a certain phenomenon or
about a set of individuals (having at least one common characteristic). The
Population is the entire set Universe, which can be finite or infinite.
Finite presents a limited number of observations, which can be counted.
Infinite - presents an unlimited number of observations that is impossible to count and
it is generally associated with processes.

February 21

OVERVIEW

2. FUNDAMENTAL CONCEPTS - continuation

2.2.2 Sample
It is a non-empty and finite subset, representative of the population.
Sampled population is the set of data that has been effectively observed or extracted. About the data from
a sample is that it develops studies, with the aim of making inferences about the population.
They must be chosen through appropriate processes that ensure randomness in the selection. It is called
we are demonstrating the process of collecting samples.

2.2.3 Parameter
It is a numerical characteristic obtained, that is, measured from all the elements of the
population.

2.2.4 Estimator
It is a numerical characteristic obtained, that is, measured from the sampled elements.

2.2.5 Raw data

It is a sequence of unorganized numerical values, obtained directly from observation.
of a phenomenon.
It is the set of numerical data obtained that has not yet been organized.

2.2.6 Role
It is an ordered sequence of raw data, and it can be either ascending or descending.
It is the arrangement of raw data in ascending (or descending) order.

3. STATISTICAL APPROACH PROCESSES

The measurement of the causes that influence the phenomenon under study can be done
through estimation or census.
3.1 Census
Understand the evaluation of the phenomenon using all the elements that make up the
population.

3.2 Estimation
Understand the evaluation of the phenomenon from an estimator using for that calculation of
probabilities.[Related terms: margin of error, confidence level, etc.]

Through the table below we can verify the properties of these procedures.
survey.

Process of
Advantages Disadvantages
Survey
It's expensive, slow, almost always
Accepts zero procedural error
Census outdated and not always is
and has 100% reliability
viable.
Accepts positive procedural error
It is cheap, fast, updated and (greater than zero) and has
Estimation
always viable.
reliability lower than 100%

Notes:
Statistically, the precision of a numerical value is assessed through the binomial:
trust and procedural error.
Surveying is the scientific study of a part of a population with the aim of
to study attitudes, habits, and preferences of the population regarding events
circumstances and matters of common interest.

4. SAMPLING TECHNIQUES
When research is done by estimation, it is necessary to use some procedures in the
selection of the elements from the population that will make up the sample; these procedures
They are called Sampling Techniques.
Sampling is the starting point (in practice) for an entire Statistical Study. This technique
especially for sampling ensures, as much as possible, randomness in the choice of
elements that will compose the sample. Thus, each element of the population comes to have the
mesma chance de ser escolhido, o que garante à amostra o caráter de representatividade e
this is very important since the conclusions regarding the population will be based
in the results obtained from the samples of this population.

4.1 Main Techniques Used in the Evaluation of Parametric Variables

4.1.1 Casual or Simple Random Sampling

It is the one in which the same sampling probability is assigned to the groups. In this, the selection
Two elements are equivalent to a lottery draw.
4.1.2 Stratified Proportional Sampling
It is used when the population is distributed across distinct strata, but each of them
homogeneous. In this case, a random quantity of elements is selected from each
group to form the sample, proportionally to the size of this group.
It is common to have populations that split into sub-populations (strata) and, as each
stratum may behave differently from another; the sample must take into account the existence
of these strata and their proportion in relation to the population.

4.1.3 Cluster Sampling

It is mainly used when the population is distributed over a large
surface, and it is observed in this one an extract with similar characteristics. Therefore, they may
select some of these extracts to obtain the elements that will make up the sample.

4.1.4 Systematic Sampling

It is used in cases where the population is already ordered.
In order to select the elements that will compose the sample, the following steps are followed:
steps:
a) The period is determined (which is the ratio between the size of the population and the sample);
b) In the population, in the first interval corresponding to the period obtained in the above item,
one element is selected;
c) From this selected element, the others that will compose the
sample, followed by the period.

4.2 Sampling Techniques Used in the Evaluation of Non-Parametric Variables

The choice of a non-probabilistic method will generally always encounter disadvantages.
against the probabilistic method. However, in some cases, it is necessary to opt for
this method. Fonseca (1996) warns that there is no way to generalize the obtained results
in the sample for the entire population when this sampling method is chosen.

Accidental (or convenience) sampling: indicated for exploratory studies.

Frequentemente utilizados em supermercados para testar produtos.

Intentional sampling: in it, the interviewer approaches a specific group to

to know your opinion. For example, when conducting a study on automobiles, the
researcher looks for workshops only.

Quota sampling: in reality, it is a variation of sampling

intentional. It is necessary to have prior knowledge of the population and its
proportionality. For example, one wishes to interview only individuals from class A,
which represents 12% of the population. This will be the quota for work. Commonly
a share is also sub-stratified following a second proportionality.

Disproportional: widely used when the sample selection is disproportionate to

population. We assign weights to the data, and this way we obtain weighted results
representatives for the study.
 Accidental or convenience

Intentional
Non-Probabilistic
Quotas or proportional

Disproportionate
Types of Sampling

Simple Random

Probabilistic Stratified Random

Conglomerate

5. STATISTICAL SERIES
It is the name given to the tables that present the distribution of the observed data of
phenomenon in function: of the time, of the place or of the species. And this is called,
respectively, historical, geographical or specific series.
One of the objectives of Statistics is to summarize the values that one or more variables can take.
to assume, so that we have a global view of the variation of this or these variables. And this
she can, initially, present these values in tables and graphs.

5.1 Table
It is a framework that summarizes a set of observations.
A table consists of:

Title: A set of information, as complete as possible, responding to

Questions: 'What? When? Where?'. It is located at the top of the table.
Header: the top part of the table that specifies the set of columns (indicates its
content and nature);
Body: a set of rows and columns that contain information about the variable in
study
Indicator column: part of the table that specifies the content of the rows;
Imaginary straight lines that facilitate the horizontal reading of data that
they are recorded in their intersections with the columns;
House or cell: space destined for a single number.

There are still the complementary elements of the table to consider, which are the source and the notes.
and the calls, preferably placed in your footer.

The footer contains the source and any captions:

 Source refers to the entity that organized the table or provided the displayed data;
the notes present general information intended to conceptualize or clarify the
table content and indicating the methodology adopted in the collection and preparation of data. Each
note should be indicated in its own line, possibly numbered or identified by
graphic symbols;
specific notes that serve to clarify details regarding the houses,
columns or rows. They are indicated in Arabic numerals or graphic symbols.

A table is a small board or frame made up of rows and columns, summarizing a set of
observations. The construction of a table depends on the collected data that will be summarized and
arranged in tabular form, which means they are placed in series and presented in
charts or tables. A table is the graphical arrangement of series according to a specific order.
classification.

Table 1 - Coffee Production

Brazil 1991-1995 { Title
Years Production
{ Header

{
(1,000 t)
1991 2.535
1992 2.666 { célula
1993 2.122
Body 1994 3.750 {linha
1995 2007
Source: IBGEfooter
_____________________________

Notes on the various series

Geographical, spatial, territorial or locational series - whose data is arranged in correspondence

with the geographical region, that is, they vary with the location.

Specific or categorical series, whose data are arranged according to specific items or categories,
at a certain time and place.

Time Series or Chronological - describe the values of the variable, at a certain location, detailed
according to variable time intervals.
 March 3rd

OVERVIEW

6. GRAPH CONSTRUCTION

They are resources used to present statistical series quickly and dynamically, without loss.
of scientific rigor.

The chart must adhere to certain requirements to be useful:

a)simplicity: it should be devoid of details of secondary importance, as well as

unnecessary traces that may lead the observer to a lengthy or...
errors;
b) clarity: should allow for a correct interpretation of the representative values of
phenomenon under study;
c) veracity: the graph must express the truth about the phenomenon under study.

The main types of charts are diagrams, cartograms, and pictograms. Next
we will see the main diagrams.

6.1 Line or Curve Chart

This type of graph uses a polygonal line to represent the statistical series. The graph
in line constitutes an application of the process of representing functions in a system of
Cartesian coordinates. As we know, in this system we make use of the two lines.
perpendicular: the lines are the coordinate axes and the intersection point, the origin. The axis
the horizontal is called the x-axis (or abscissa) and the vertical, the y-axis (or ordinate)
y).

Example:

Table 1–Brazilian Production

from Dende oil
1987-92
Years Quantity
(1.000 t)
1987 39.3
1988 39.1
1989 53.9
1990 65.1
1991 69.1
1992 59.5
Source: Agropalma
Line Chart

80.0

70,0

60.0

50.0

40.0

30.0

20.0

10.0

0,0
1987 1988 1989 1990 1991 1992

Figure 1: Brazilian Palm Oil Production–1987-92

Source: Agropalma

6.2 Column or Bar Chart

It is the representation of a series through rectangles, arranged vertically (in columns)

or horizontally (in bars). And it is mainly indicated for geographical series or
specific, when the idea of complementation is not conveyed.

Example:

Table 2–Brazilian Exports

May - 1995
States Values
(US$ Millions)
São Paulo 1.344
Minas Gerais 542
Rio Grande do Sul 332
Holy Spirit 285
Paraná 250
Santa Catarina 202
Source: SECEX
Column Chart

1.500
1.250
1.000
750
500
250
0
SP MG RS ES PR SC
STATES

Figure 2: Brazilian Exports - May 1995

Source: SECEX

Bar Chart

SC

PR

ES

RS

MG

SP

0 250 500 750 1,000 1.250 1.500

Values (US$ Millions)

Figure 2: Brazilian Exports - May 1995

Source: SECEX

6.3 Pie Chart

This chart is built based on a circle, and it is used whenever we want to
highlight the participation of the data in the total. The total is represented by the circle, which is divided.
in so many sectors how many are the parts.
The sectors are such that their areas are respectively proportional to the given series data.
We obtain each sector through a simple and direct rule of three, remembering that the total area
corresponds to 360o.
 Example:

Table 3 - Swine Herd of

Southeast of Brazil
1992
States Quantity
(a million heads)
Minas Gerais 3,363.7
Holy Spirit 430.4
Rio de Janeiro 308.5
São Paulo 2,035.9
TOTAL 6.138,9
Source: IBGE

Sector Chart

119,39o
Minas Gerais
197,27o
Holy Spirit
18,09o Rio de Janeiro
25,24o
São Paulo

Figure 3: Pig Herd in the Southeast of Brazil - 1992

Source: IBGE
EXERCISES

Exercises extracted from the book Easy Statistics by the author Antônio Arnot Crespo.

1. Complete: The experimental method is the most used by sciences such as:...

2. Human and social sciences, to obtain the data they seek, resort to what
method?

3. What is Statistics?

4. Cite the phases of the statistical method.

5. What does it mean to you to collect data?

6. What is the purpose of data criticism?

What is data collection?

8. How can the data be presented or displayed?

9. Conclusions and inferences belong to which part of Statistics?

10. Cite three or more activities in business planning where Statistics is used.
necessary.

11. The statistical method has as one of its aims:

a. study statistical phenomena.
b. study the concrete qualities of individuals that form groups.
c. determine abstract qualities of groups of individuals.
d. study numerical phenomena.

_______________________

Answers

1. Complete: The experimental method is the most used by sciences such as: Chemistry, Physics,
Biology, etc.

2. The human and social sciences, in order to obtain the data they seek, make use of what
method?
Although more difficult and less accurate, the statistical method.

3. What is Statistics?
Statistics is a part of Applied Mathematics that studies methods for collecting,
organization, description, analysis and interpretation of data. All of your study aims, among
others, the decision-making.
Statistics is a set of quantitative methods and processes used to study and
measure collective phenomena.
4. Cite the phases of the statistical method.
Data Collection, Data Critique, Data Compilation, Exposure or Presentation of
Data and Analysis of Results.
5. What does it mean to collect data for you?
Collecting data is obtaining information from the studied population related to the phenomenon that
if you want to verify.

The collection is direct when carried out on mandatory record information elements.
(births, marriages, and deaths, import and export of goods), elements
pertinentes aos prontuários dos alunos de uma faculdade ou, ainda, quando os dados são
 collected by the researcher themselves through surveys and questionnaires, as is the case
of verification and examination notes, from the demographic census, etc.

The data collection can be classified in relation to the time factor as:
a. continuous (record) – when done continuously, such as that of births and deaths and the
student attendance in classes;
b. periodic - when done at constant time intervals, like censuses (every 10 years)
10 years) and the periodic evaluations of the students;

c. occasional - when done extemporaneously, in order to meet a situation or a

an emergency, as in the case of epidemics that ravage or decimate entire herds.
The collection is said to be indirect when it is inferred from known elements (direct collection) and/or from
knowledge of other phenomena related to the phenomenon studied. As
for example, we can mention the research on infant mortality, which is conducted through
data gathered through direct collection.

6. What is the purpose of data criticism?

Once the data is obtained, it should be carefully reviewed in search of possible flaws.
and imperfections, in order not to incur gross or significant errors, that could
to significantly influence the results.
The criticism is external when it targets the causes of mistakes made by the informant, due to distraction.
or your interpretation of the questions that were asked of you; it is internal when it aims to observe the
original elements of the data collection.

7. What is data collection?

It is nothing more than the sum and processing of the obtained data and the arrangement thereof.
classification criteria. It can be manual, electromechanical, or electronic.

8. How can the data be presented or displayed?

No matter how diverse the purpose may be, the data must be
presented in an appropriate format (tables or graphs), making examination easier
from that which is being the subject of statistical treatment and subsequent acquisition of measures
typical.

9. Conclusions and inferences belong to which part of Statistics?

Inductive or Inferential Statistics, which is based on induction or inference, and we derive
of these results conclusions and predictions.

10. Cite three or more activities of business planning in which Statistics is involved.
necessary.
We can know the geographical and social reality, the natural and human resources, and
available finances, the community's expectations about the company, and establish
your goals, your objectives with a greater likelihood of being achieved in the short, medium or long term.
long term. In the selection and organization of the strategy to be adopted in the venture,
still, in the choice of techniques for verifying and evaluating the quantity and quality of
product and even of possible profits and/or losses.

11. The statistical method has as one of its purposes:

a. study statistical phenomena.

____________________________
Proposed Exercises
1. Classify the variables as qualitative or quantitative (continuous or discrete)
a. População (ou Universo): alunos de uma escola. Variável: cor dos cabelos
b. População: casais residentes em uma cidade Variável: nº de filhos
c. População: as jogadas de um dado Variável: o ponto obtido em cada jogada
d. Population: pieces produced by a certain machine. Variable: number of pieces produced by
hour
e. População: peças produzidas por certa máquina. Variável: diâmetro externo

2. Diga quais das variáveis abaixo são discretas e quais são contínuas:
a. População (ou Universo): crianças de uma cidade. Variável: cor dos olhos
b. População: dados de uma estação meteorológica de uma cidade. Variável: precipitação
rainfall, during the year
c. Population: data from the São Paulo Stock Exchange - IBOVESPA. Variable: number of
traded shares
d. População: funcionários de uma empresa. Variável: salários
e. População: pregos produzidos por uma máquina. Variável: comprimento
f. População: casais residentes numa cidade. Variável: sexo dos filhos
g. População: propriedades agrícolas do Brasil. Variável: produção de soja
h. População: segmentos de reta. Variável: comprimento
i. População: bibliotecas de Catanduva. Variável: nº de volumes
j. Population: devices produced on an assembly line. Variable: number of defects per
unit
k. População: indústrias de uma cidade. Variável: retorno sobre o capital próprio empregado

______________________________

Answers
1. Classify the variables as qualitative or quantitative (continuous or discrete)
a. População (ou Universo): alunos de uma escola. Variável: cor dos cabelos -qualitativa
b. População: casais residentes em uma cidade Variável: nº de filhos -quantitativa discreta
c. População: as jogadas de um dado Variável: o ponto obtido em cada jogada- quantitativa
discrete
d. Population: pieces produced by a certain machine. Variable: number of pieces produced by
hour - discrete quantitative
e. População: peças produzidas por certa máquina. Variável: diâmetro externo -quantitativa
continuous

2. Diga quais das variáveis abaixo são discretas e quais são contínuas:
a. População (ou Universo): crianças de uma cidade. Variável: cor dos olhos- contínua
b. População: dados de uma estação meteorológica de uma cidade. Variável: precipitação
rainfall, throughout the year - continuous
c. Population: data from the São Paulo Stock Exchange - IBOVESPA. Variable: number of
traded actions - discreet
d. População: funcionários de uma empresa. Variável: salários- discreta
e. População: pregos produzidos por uma máquina. Variável: comprimento- contínua
 f. População: casais residentes numa cidade. Variável: sexo dos filhos- discreta
g. População: propriedades agrícolas do Brasil. Variável: produção de soja- discreta
h. População: segmentos de reta. Variável: comprimento- contínua
i. População: bibliotecas de Catanduva. Variável: nº de volumes- discreta
j. Population: devices produced on an assembly line. Variable: number of defects per
discrete unit
k. População: indústrias de uma cidade. Variável: retorno sobre o capital próprio empregado
continuous

____________________________

Proposed Exercises
{"population":"What is population? And sample?"}

Population is the set of entities that share at least one common characteristic.
A sample is a finite, non-null, and representative subset of a population.
2. What is the difference between parameter and estimator?

3. What is a statistical data?

4. What is the difference between raw data and a list?

5. Define two statistical approaches. Draw a parallel between them.

addressing its advantages and disadvantages.

_______________________________
Answers
1. What is a population? And a sample?

Population is the set of entities (people, things, objects) bearing at least

a common characteristic. A sample is a finite, non-null, and representative subset
of a population.
2. What is the difference between a parameter and an estimator?

In the parameter, the numerical characteristic is obtained from all the elements of the
population, while in the estimator, only elements of the sample are used.
3. What is the difference between raw data and a list?

Raw data is the set of unorganized numerical data obtained directly from
observation of a collective phenomenon. Roll is the arrangement of raw data in ascending order or
decreasing.

6. What is the difference between raw data and a list?

7. Define two statistical approaches. Draw a parallel between them.

addressing its advantages and disadvantages.