Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
56 views

MAS113X Fundamentals of Statistics I Lecture Notes

This document provides an introduction to statistics and statistical modeling. It discusses how statistics is used to extract meaningful patterns from data and quantify uncertainty. It lists common fields that use statistical methods and the types of questions asked. The document then discusses statistical modeling, noting models take the form of observed data equaling a function of variables plus error. It emphasizes modeling is an iterative process. The document also defines populations as the collection of items under study and samples as subsets of populations used to make inferences. It provides examples of defining populations and variables and methods for collecting sample data.

Uploaded by

shantanuril
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
56 views

MAS113X Fundamentals of Statistics I Lecture Notes

This document provides an introduction to statistics and statistical modeling. It discusses how statistics is used to extract meaningful patterns from data and quantify uncertainty. It lists common fields that use statistical methods and the types of questions asked. The document then discusses statistical modeling, noting models take the form of observed data equaling a function of variables plus error. It emphasizes modeling is an iterative process. The document also defines populations as the collection of items under study and samples as subsets of populations used to make inferences. It provides examples of defining populations and variables and methods for collecting sample data.

Uploaded by

shantanuril
Copyright
© Attribution Non-Commercial (BY-NC)
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 8

MAS113X Fundamentals of Statistics I

Lecture Notes

Professor S. G. Gilmour
School of Mathematical Sciences
Queen Mary, University of London
(modified version of MAS113 notes of Dr L. Pettit)

September 27, 2007

1
1 Introduction

1.1 What is Statistics?

Statistics is concerned with the process of finding out about


real phenomena by collecting and making sense of data. Its
focus is on extracting meaningful patterns from the variation
which is always present in the data. An important feature is the
quantification of uncertainty so that we can make firm decisions
and yet know how likely we are to be right.

1.1.1 Problems and Questions

Statistical methods are applied in an enormous diversity of prob-


lems in such fields as:

• Agriculture (which varieties grow best?)

• Genetics, Biology (selecting new varieties, species)

• Economics (how are the living standards changing?)

• Market Research (comparison of advertising campaigns)

• Education (what is the best way to teach small children


reading?)

• Environmental Studies (do strong electric or magnetic fields


induce higher cancer rates?)

2
• Meteorology (is global warming a reality?)

• Medicine (which drug is best?)

• Psychology (how are shyness and loneliness related?)

• Social Science (comparison of people’s reaction to different


stimuli)

Questions which arise in an investigation should be posed in non-


statistical terms to keep subject matter priorities first; ”trans-
lating” these questions into the language of statistics usually
means to answer the following:
- What should I measure?
- How should I measure it?

1.2 Ideas of Statistical modelling

In this section we are going to discuss some of the ideas of Sta-


tistical Modelling. We start with a real life problem. We think
about what to measure and how to measure it. We decide how
to collect some data. This may be via a survey, an experi-
ment or carrying out an observational study. We have to design
the method of data collection. For example by thinking care-
fully about questionnaire wording or in what way we decide ex-
perimental units receive different treatments or deciding which

3
variables to measure. We should also think of an appropriate
statistical model for our data. This will often be of the form

Observed data = f (x, θ) + error,

where x are variables we have measured and θ are parameters of


our model. Data often exhibit great variability. The relationship
we are assuming here is NOT deterministic. That is why the
“error” term is there. We usually make some assumptions about
the error term but we should use our data to check if those
assumptions seem justified. If not we should go back and revise
our model.
Statistical model building is an iterative process. we entertain
a tentative model but we are ready to revise it if necessary. Only
when we are happy with our model should we stop. We can then
use our model, sometimes to understand our current set of data,
sometimes to help us predict what may happen in the future.
We must be ready to translate what the model is telling us
statistically to the client with the real life problem.

1.3 Populations and Samples

When we carry out a statistical investigation we want to find


out about a population.

4
Definition 1 A population is the collection of items under dis-
cussion. It may be finite or infinite; it may be real or hypothet-
ical.

Sometimes although we have a target population in mind the


study population we can actually find out information about may
be different.
We are interested in measuring one or more variables for the
members of the population but to record observations for every-
one would be costly. The government carries out such a census
of the population every ten years but also carries out regular
surveys based on samples of a few thousand.

Definition 2 A sample is a subset of a population.

The sample should be chosen to be representative of the pop-


ulation because we usually want to draw conclusions or infer-
ences about the population based on the sample. Samples will
vary and the question of whether our sample is compatible with
hypotheses we may have about the population will be a large
concern in this course.
We will not concern ourselves much with the mechanics of
how the sample is chosen, this is a topic for the course Samples,
Surveys and Simulation which some of you may be doing or may

5
do next year. But the following examples give you some idea of
the sorts of problems:

1. A city engineer wants to estimate the average weekly water


consumption for single-family dwellings in the city.

The population is single-family dwellings in the city. The


variable we want to measure is water consumption. To col-
lect a sample if the dwellings have water meters it might be
best to get lists of dwellings and annual usage directly from
the water company. If not then the local authority should
have lists of addresses which can be sampled from. Note we
should collect data through the year as water consumption
will be seasonal.

2. A political scientist wants to determine if a majority of


voters favour an elected House of Lords.

The population is voters in the UK. Electoral rolls provide


a list of those eligible to vote. What we want to measure
is their opinion on this issue using a neutral question. (It
would be easy to bias the response by asking a leading
question.) We could choose a sample using the electoral
roll and then ask the question by post, on the telephone or
face to face but all these methods have problems of non-

6
response and/or cost.

3. A medical scientist wants to estimate the average length of


time until the recurrence of a certain disease.

The population is people who are suffering from this disease


or have done in the past. What we want to measure are
the dates of the last bout of disease and the new bout of
disease. We could take a sample of patients suffering the
disease now and follow them until they have another bout.
This may be too slow if the disease doesn’t recur often.
Alternatively we could use medical records of people who
suffered the disease in one or more hospitals but records
can be wrong and there may be biases introduced.

4. An electrical engineer wants to determine if the average


length of life of transistors of a certain type is greater than
5000 hours.

The population is transistors of this type. We want to


record the length of time to failure by putting a sample of
transistors on test and recording when they fail. Note that
for such experiments where the items under test are very
reliable it may be necessary to use an “accelerated” test
where we subject the items to higher currents than usual.

7
In other parts of the course we may not emphasize the un-
derlying population or exactly how we collect a sample but re-
member these questions have had to be considered.

You might also like