Chapter 1

Statistical Methods for Social Sciences

Detecting errors,
mistakes,exaggerations
• Researcher may feel strongly about a
cause.
• Lack of information
• Fabricated numbers
Checking the math
• Check to be sure everything adds up.
• Look for a total sample size- ignore results
based on tiny samples.
• Examine whether the projections are
reasonable.
• Converting numbers to % (better than
counting data)
Scale
• Looking at the scale of a graph or chart can
really help you keep the reported results in
proper perspective.
• Stretching the scale out or starting the y-axis
at the highest possible number makes
differences appear larger; squeezing down
the scale or starting the y-axis at a much
lower value than needed makes differences
appear smaller than they really are. (lottery)
Scale
Sample size
• sample size is an important factor in
determining the accuracy and repeatability of
the results.
• time and money
Wording
• Even small differences in a survey can create
big differences in results.
• »»Should the veto right be available to the
president to eliminate waste (yes/no/no
opinion)?
• »»Does the veto right give the president too
much individual power (yes/no/no opinion)?
• »»What is your opinion on the presidential
veto right? Choose 1–5, with 1 = strongly
opposed and 5 = strongly support.
Statistics: More than numbers
• Involved every aspect of scientific
method-
– formulating good questions, (who will win
the next election)
– setting up studies, (determine population
and sample)
– collecting good data, analyzing the data
properly,
– and making appropriate conclusions.(100%
confident?)-Every study has limits.
Statistics: More than numbers
• The results may lead to more questions.
• Statistics is the business of using
scientific methods to answer research
questions about the World.
• It is a process- series of stages
• Set of methods for collecting/ analyzing
data
 Statistical Jargon
• Data - Information collected from individuals and/or
organizations to gain knowledge regarding a field or
question of interest. (Information that you collect
through your study)
– Numerical data: Quantitative- These data have
meaning as a measurement, such as a person’s height,
weight, IQ, or blood pressure; or they’re a count, such as
the number of stock shares a person owns, how many
teeth a dog has, or how many pages you can read of your
favorite book before you fall asleep.
• Discrete Data: finite data-fixed (Number of Heads in 100 coin
flips)
• Continuous Data: interval (10 lt of bottle)
• Number of pets, age, weight, number of siblings
Data
– Categorical data: Qualitative- represent
characteristics such as a person’s gender,
marital status, hometown, or the types of
movies they like.
– can take on numerical values (such as “1”
indicating male and 2” indicating female),
but those numbers don’t have meaning.
– You couldn’t add them together,
Data
• Data Sources:
– Surveys (Mail, Telephone, Internet)
– Content Analysis (Newspaper, Magazine,
Television)
– Natural Experiments/Field Studies
– Controlled Experiments
– Data Base: existing archived collections of
data
Data
• Data Set: collection of all the data taken from
the sample.
– how many pets they own, and the data they gave
me are the following: 0, 2, 1, 4, 18.
– the gender of each of my friends, giving me the
following data: male, male, female, male, female.
• Variable: Any characteristic or numerical
value that varies from individual to individual.
(number of pets, gender)
Data
• Let’s go to the website
https://sda.berkeley.edu/GSS/
• Click on GSS—with NOWEIGHT
VARIABLES predefined.
• The GSS name for the question about
number of good friends is NUMFREND.
• Type NUMFREND in the Row box.
Click on Run the table.
Population
• Full set of subjects of interest to researcher
• The group of individuals you want to study in
order to answer your research question
• center your attention on a particular group of
individuals (population of interest)
– Broad population: a college professor wants to study
how TV ads persuade consumers to buy products.
Her study is based on a group of her own students
her results can’t be generalized to any population
beyond her own students, because no other
population was represented in her study.
Sample
• Subset of population that is observed
and measured in a data collection study
– Ex: a pot of Pasta
• Selecting sample in a way that avoid
bias- RANDOM. (random number
generators-soft ware)
• No matter how large a sample is, if it is
based on non-random methods the
results will not represent the population.
Statistic
• A number calculated from data
• A number that summarizes the data
collected from a sample.
– Percentage- categorical
– Average(mean), median, standard
deviation- numerical
• Descriptive statistics: numerical
summary of sample
• (statistics: methods analyzing data)
 Parameters and Statistics
• Census – Data for population. (If you collect data
from entire population-missing part then census
numbers can only be estimates)
• Statistic - Numeric summary of a sample (descriptive
statistics)
• Parameter - Numeric summary of a population
– Population Mean - Average of a numeric
measure
– Population Proportion - Fraction having a
particular characteristic
• Inferential statistics: provide predictions about
population based on data from a sample of that
population
Description and Inference
• Descriptive Statistics - Summary of
the information in a sample of data
• Inferential Statistics - Statements
regarding a population, based on a
sample
 Uses of Statistical Methods
• Design - Planning/Implementing a study
– Constructing a survey and deciding who to
sample
– Determining methods to be compared
– Deciding which groups of units to be analyzed
• Description - Summarizing data
– Typical outcomes and distributions of outcomes
– Tables and/or Graphs
• Inference - Using sample data to predict or make
statements regarding unobserved data
 Statistical Computing
• Statistical computer packages have
become widespread over recent years,
and their methods and ease of use have
improved drastically in recent years (R,
Gretl, SPSS, STATA, EViews, etc.)
• Data must be entered into a data file:
– Rows typically represent individuals
– Columns typically represent variables
Application
• R
– Used in:
• Data science
• Statistical research
• Documentation production
• Academic research
Application
• R
– Open source- everybody is writing
packages for specific data analytic
problems
– Created in 1993-implementation of S(1976)
– A lot of packages-libraries
– Vectorized language (easy to perform
analysis)
– Using program language-codes
• Reproducable-repeatable
Application
• IDE (Integrated Development Environment)
all in one- (R studio)
– Software creation can be complicated thing even
for professionals.
– involving numerous tools for code creation,
building and testing.
– Like software development toolbelt consolidating
many of these functions together in a single
framework, application or service.
– Text editors, code libraries, compilers and test
platforms.
Application
• R and R studio
• http://www.r-project.org/

• https://www.rstudio.com/products/rstudi
o/download/
Application
• R studio
• For the appearance
– Tools
– Global options
– Appearance
• Dracula
Application
• File- New file- R script
– Hello World----Run
– print("Hello World")----Run
There are lots of packages to perform
analysis in R.
– install.packages("Rcmdr") for the use of
command
You also need the library.
– library(Rcmdr)
Application
To load data file from text website
Crime <-
read.table("http://www.stat.ufl.edu/~aa/smss/data/
Crime.dat",header=TRUE)
–header=TRUE #variable names are at the
top of the file#

–import data from excel

• Under environment or under file
Application
• Gretl
– http://gretl.sourceforge.net/win32/
– File- new data set-cross-sectional 5-
forward-start entering data values-apply
– data frame
– import data