# Basics of data science and statistics

## Aims

This course is intended to provide the basic and PRACTICAL knowledge of statistics for those who are involved in managing, analysing and presenting quantitative information.

Its intent is to cover, using a simplified but rigorous approach, the lack of knowledge that usually have those that have not attended a proper academic training during university but, nevertheless, require to manage, analyse and present quantitative information.

During the course, some statistical tools will be used to show how to translate into immediate practical application the concepts presented.

## Participants

CFOs, R&D, financial analysts, and anyone who need to analyse measures and KPI.

## Options

This training is also available as Tailored Training 1:1

## Program

Descriptive statistics

Categorical data (nominal, ordinal)

Describing and summarizing

• Bar Chart
• Pie Chart
• Contingency Table

Scale (interval, ratio, continuous)

Summarizing continuous data

Central Tendency

• Mode
• Median
• Mean

Dispersion

• Range
• Inter-quantile
• Standard deviation

The Likert Scale

Inferential statistics

Basics

Sample and population

• Representative sample
• Probability sample
• Non-probability sample

Independent (predictor) vs. dependent (outcome) variable

Operationalization – How to measure a concept or construct

Sample-statistic: estimating mean and standard deviation

• Confidence interval
• Confidence intervals for categorical data

Statistical Significance and Significance Testing

Research hypothesis

Test-statistic (estimate significance p<0.05)

Type of Errors

• Type I error (false positive)
• Type II error (false negative)

Measuring Effect Size

Concept of Power

Generalization, confidence and causality

The mechanic of inferential statistics

The normal distribution and the confidence interval

The SAMPLING DISTRIBUTION OF MEANS and the CENTRAL LIMIT THEOREM

Use of Test Statistic to compute the Significance Test

How big is the sample for a test-statistic?

Analysing differences

Differences In the proportion of cases that fall into 2 different categories

Differences in the mean of two continuous variable

Analysing correlations

When to use

How a variable can predict another and how much of the variation of the variable can be explained by another

Identifying a small number of core theoretical variable

Correlation between 2 continuous variable or 1 continuous variable and 1 categorical dichotomous variable (Correlation and Simple Regression)

Moderation variables

Hierarchical analysis

Logistic regression

Using graphs to analyse data

• Histogram
• Pie chart
• Bar chart
• Frequency polygon
• Skewed and Bimodal distribution
• Scatter plot
• Box and Whiskers

## Information

• Duration: 2 days (9:30-17:30)
• Calendar
• Price information: 1.200 CHF + VAT (1.000 CHF + VAT each for more than one subscriber from the same company)

## Booking your training is easy

1. Send us your request by filling the following form
2. You will receive all the information needed to complete the application procedure