Scribd
Upload
33 views

Quantitative Methods Notes

This document contains information about quantitative methods and statistical indicators. It discusses topics like: 1) Definitions of statistics as the science of collecting and interpreting numerical data. 2) Different types of variables (quantitative, qualitative, nominal, ordinal, interval, ratio) and statistical indicators (mean, median, mode, variance, standard deviation). 3) Methods for collecting sample data randomly or through stratified sampling. 4) Examples of calculating basic statistical values like the mean, variance, and standard deviation for a sample data set.

Uploaded by

Davide Rossetti
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
33 views

Quantitative Methods Notes

This document contains information about quantitative methods and statistical indicators. It discusses topics like: 1) Definitions of statistics as the science of collecting and interpreting numerical data. 2) Different types of variables (quantitative, qualitative, nominal, ordinal, interval, ratio) and statistical indicators (mean, median, mode, variance, standard deviation). 3) Methods for collecting sample data randomly or through stratified sampling. 4) Examples of calculating basic statistical values like the mean, variance, and standard deviation for a sample data set.

Uploaded by

Davide Rossetti
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Quantitative methods

Book (statistics): Introduction to basic statistics, 7th edition- Brase&Brase


()
Exam: December
Moodle: Yes

1. INTRODUCTION
Some starting definitions of the term statistics:

1) Statistic is an empirical science that studies how to collect, organize and interpret
numerical information on data, where data is something you observe. The data have
not to be necessarily numbers but could also be genders, colors.
2) Both the science of uncertainty and the technology of extracting information
from data.

1.2 WORDING
- Individuals: Things, people, animals,.. which we are observing.
- Variable: Characteristics of the individuals

When we are using programs like excel to analyse the individuals we will use a
spreadsheet, where the variables are in the columns, and the individuals in the lines.

Variables can be distinguished in different categories and with different methods.


One way of doing is distinguishing them in quantitative and qualitative, where
quantitative ones can be stored in numbers, while the second are genders,
colors,ecc.. , so the opposite, no possibility to store them in numbers.
Another way is distinguish them in nominal, ordinal, interval, ratio:
Nominal (qualitative)
Ordinal means that you can bring the datas in order but there is no difference
between the variables
Interval= order, difference, no ratio.
Ratio: order, difference, ratio
- Population data: the entirety of the population
- Sample data: subset of population
- Population parameters: varians, average, in general indicators based on the
population
- Sample statistics: varians, average, in general indicators based on the samples.
Sample statistic as estimator for population parameter.

(pag 11-12) 5-6-8-12

Sample Techniques.
How to choose the individual for the sample?

- Random sampling: Each individual of the population has the same probability of
being selected to be part of the sample.
- Stratified sampling: (Strata= groups) You try to keep some proportions in reference
to the variable we are considering (for example, we know that 20% people of Austria
are tirolians, so if we get a 100 people sample we will select 20 tirolians).

Study Design
- Observational study
- Experiments:
1. treatment group(s)
2. control group (no treatment)

One rule for the experimental study is not to tell people in which group they are (
placebo group/ actual pill group) and second is to create groups with people that are
as equal as possible.

2. STATISTICAL INDICATORS

- Counting:
1. Absolute frequencies: numbers 300 women
200 men
-----------------
500 people in total
2. Relative frequencies: absolute frequencies divided by the total number of individuals
r.f. of woman= 300/500= 0,6= 60%
r.f. of men= 200/500= 0,4= 40%
I.E. :

0
1000
Variable: salary 1050
QUANTITATIVE VARIABLE 1051
| 10000
|
V

a.f. r.f. cumulated relative frequency


0 50 50%
1-1000 10 10% 60%
1000-3000 15 15 % 75%
3000-5000 15 15% 90%
>5000 10 10% 100%

Then we can draw a histogram (on paper)

Then another one with cumulated relative frequencies (on paper).

12/10/17

3. Basical Statistical indicators


3.1 Indicator of position.
Averages:
- (Arithmetic) mean: If you have a variable where several entries are, like the heights
or weights of a group of people, we can use this mean. It is the sum of all values
divided by the number of all values. Outliers are a big problem when it comes to this
average, because it gives us an unrealistic average, whose unattendability is given by
the fact that the outlier is just a number that stands out of the other datas, that
differ from each other but not in such a big way.
- Weighted average: Example: We want to know what is the average income taking
in consideration three different countries: Austria, Germany, Switzerland. We could
operate with a arithmetic mean but it would give us an incorrect estimation of the
average income, so it is convenient to multiply the income for the population size.
With a mathematical equation: Weighted average= sum values weight/ Sum of
weights
- Mode: It is the most frequent value. No calculation, just observation.
- Median: To find it we have to sort the values from low to high, then we have to
take the value in the middle. The median is not affected by outliers.
- Quartiles: 1st 25% lower and 75% higher, 2nd quartile 50% lower 50% higher, 3rd
quartile 75% lower 25% higher.
- Percentile: 1st, 2nd, 3rd,, 99th
1st percentile 1% of observation is lower und 99% higher.

3.2 Indicators of dispersion

S2= Variance in the sample


S= Standard deviation in the sample
(sigma) = standard deviation in the population
(sigma)2= Variance in the population

body height of 5 people

180,185, 165,170,160

to measure the range we can go highest value- lowest value= 185-160= 25

(formula della varianza)

First we calculate the mean:

(180-172)2 + (185-172)2 + (165-172)2 + (179-172)2 + (160-172)2


S2 = ----------------------------------------------------------------------------------------
number of observations - 1

S2= 107,5 cm2

Standard deviation = sqrt(variance)= 10,36 cm

08/11/17

Correlation
_
mean = Sum of all values/ number of values = Variable x = x/ N = x
Variance and standard deviation
_
Variance: Sum of squared distances from mean / N-1 => 2= (Xi x) 2/ N-1

Standard deviation= = sqrt(2)

Quicker way to calculate variance:


_ _ _ _ _ _
2= (Xi x) (Xi x)= (Xi2- XXi- Xxi+ X2) = Xi2- 2Xxi+ X2
_ _
= Xi2 2xnx =
_ _
= Xi 2nx2+ nx2
2

_
xi2- nx2
Finally 2= -------------
N-1

Example

1. Mean: (2+5+1+3+6+8)/6= 25/6= 4,16


_ _
x | x- x (x-x)2
2 |2 - 4,16 4,66
5 |5 - 4,16 0,71
1 |1 - 4,16 9,98
3 |3 - 4,16
6 | 6 - 4,16
8 |8 - 4,16

fast method:
mean: 4,16 x2= 4+25+1+9+36=139

2= (139-6 x 4,162)/ 6-1 = 7,03 (different from the result of the first formula due
to rounding)

You might also like