THE BIG PICTURE OF STATISTICS

Theory
Question to answer / Hypothesis to test
Design Research Study
Collect Data
(measurements, observations)

Organize and make sense of the #s

USING STATISTICS!
Depends on our goal:
Describe characteristics Test hypothesis, Make conclusions,
organize, summarize, condense data interpret data, understand relations
DESCRIPTIVE STATISTICS INFERENTIAL STATISTICS
 Some Definitions:
Construct: Intelligence
abstract, theoretical, hypothetical
can’t observe/measure directly

IQ Vocabulary Achievement
Variable: reflects
construct, but is directly measurable and can differ from subject to subject
(not a constant). Variables can be Discrete or Continuous.

Operational SAT Vocab

WISC Grades
Definition: Test
concrete, measurable
Defines variable by specific operations used to measure it
 Types of Variables
 Quantitative  Qualitative
 Measured in amounts  Measured in categories
 Ht, Wt, Test score  Gender, race, diagnosis

Discrete: Continuous:
 separate categories  infinite values in between
 Letter grade  GPA
 Scales of Measurement
 Nominal Scale: Categories, labels, data carry no numerical
value

 Ordinal Scale: Rank ordered data, but no information about

distance between ranks

 Interval Scale: Degree of distance between scores can be

assessed with standard sized intervals

 Ratio Scale: Same as interval scale with an absolute zero

point.
 Errors in Hypothesis Testing
 Type I Errors
 You reject a null hypothesis when you
shouldn’t
 You conclude that you have an effect when
you really do not
 The alpha level determines the probability of
a Type I Error (hence, called an “alpha error”)
 Type II Errors
 Failure to reject a false null hypothesis
 Sometimes called a “Beta” Error.
 Statistical Power
 How sensitive is a test to detecting real
effects?
 A powerful test decreases the chances of
making a Type II Error
 Ways of Increasing Power:
 Increase sample size
 Make alpha level less conservative
 Use one-tailed versus a two-tailed test
 Assumptions of Parametric
Hypothesis Tests (z, t, anova)
 Random sampling or random assignment
was used
 Independent Observations
 Variability is not changed by experimental
treatment (homogeneity of variance)
 Distribution of Sample Means is normal
 Measuring Effect Size
 Statistical significance alone does not imply a substantial
effect; just one larger than chance
 Cohen’s d is the most common technique for assessing
effect size
 Cohen’s d = Difference between the means divided by
the population standard deviation.
 d > .8 means a large effect!
 Introduction to the t Statistic
 Since we usually do not know the population variance,
we must use the sample variance to estimate the
standard error
 Remember? S2 = SS/n-1 = SS/df
 Estimated Standard Error = SM = √S2/n
 t = M – μ0/SM
 Differences between the distribution of
the t statistic and the normal curve
 t is only normally distributed when n is very
large. Why?
 The more statistics you have in a formula, the more sources of
sampling fluctuation you will have.
 M is the only statistic in the z formula, so z will be normal
whenever the distribution of sample means is normal
 In “t” you have things fluctuating in both the numerator and the
denominator
 Thus, there are as many different t distributions as there are
possible sample sizes. You have to know the degrees of
freedom (df) to know which distribution of t to use in a problem.
 All t distributions are unimodal and symmetrical around zero.
 Comparing Differences between
Means with t Tests
 There are two kinds of t tests:
 t Tests for Independent Samples
 Also known as a “Between-Subjects” Design
 Two totally different groups of subjects are compared;
randomly assigned if an experiment
 t Tests for related Samples
 Also known as a “Repeated Measures” or “Within-Subjects”
or “Paired Samples” or “Matched Groups” Design
 A group of subjects is compared to themselves in a different
condition
 Each individual in one sample is matched to a specific
individual in the other sample
Paired Sample T-Test

• The paired sample t-test, sometimes called the dependent

sample t-test, is a statistical procedure used to determine
whether the mean difference between two sets of observations
is zero. In a paired sample t-test, each subject or entity is
measured twice, resulting in pairs of observations. Common
applications of the paired sample t-test include case-control
studies or repeated-measures designs. Suppose you are
interested in evaluating the effectiveness of a company training
program. One approach you might consider would be to
measure the performance of a sample of employees before and
after completing the program, and analyze the differences using
a paired sample t-test.
Paired Sample T-Test

• The paired sample t-test, sometimes called the dependent

sample t-test, is a statistical procedure used to determine
whether the mean difference between two sets of observations
is zero. In a paired sample t-test, each subject or entity is
measured twice, resulting in pairs of observations. Common
applications of the paired sample t-test include case-control
studies or repeated-measures designs. Suppose you are
interested in evaluating the effectiveness of a company training
program. One approach you might consider would be to
measure the performance of a sample of employees before and
after completing the program, and analyze the differences using
a paired sample t-test.
Independent T-Test
•The Independent Samples t
Test compares the means of
two independent groups in order to
determine whether there is statistical
evidence that the associated
population means are significantly
different. The Independent Samples t
Test is a parametric test.
•When using a two-tailed test, regardless
of the direction of the relationship you
hypothesize, you are testing for the
possibility of the relationship in both
directions. For example, we may wish to
compare the mean of a sample to a
given value x using a t-test. Our null
hypothesis is that the mean is equal to
x. A two-tailed test will test both if the
mean is significantly greater than x and
if the mean significantly less than x.
A one-tailed test will test
either if the mean is
significantly greater than x
or if the mean is
significantly less than x, but
not both.
Advantages of Independent Sample
Designs
 Independent Designs have no carryover effects
 Independent designs do not suffer from fatigue or
practice effects
 You do not have to worry about getting people to
show up more than once
 Demand characteristics may be stronger in repeated
measure studies than in independent designs
 Since more individuals participate in independent
design studies, the results may be more
generalizeable
 Disadvantages of Independent
Sample Designs
 Usually requires more subjects (larger n)
 The effect of a variable cannot be assessed for each
individual, but only for groups as a whole
 There will be more individual differences between
groups, resulting in more variability
 Advantages of Paired-Sample
Designs
 Requires fewer subjects
 Reduces variability/more statistically efficient
 Good for measuring changes over time
 Eliminates problems caused by individual
differences
 Effects of variables can be assessed for each
individual
 Disadvantages of Paired Sample
Designs
 Carryover effects (2nd measure influenced by 1st
measure)
 Progressive Error (Fatigue, practice effects)
 Counterbalancing is a way of controlling carryover and practice
effects
 Getting people to show up more than once
 Demand characteristics may be stronger
What is really going on with t Tests?

 Essentially the difference between the means of the two

groups is being compared to the estimated standard
error.
 t = difference between group means/estimated standard
error
 t = variability due to chance + independent
variable/variability due to chance alone
 The t distribution is the sampling distribution of
differences between sample means. (comparing
obtained difference to standard error of differences)
 Assumptions underlying t Tests
 Observations are independent of each other (except
between paired scores in paired designs)
 Homogeneity of Variance
 Samples drawn from a normally distributed
population
 At least interval level numerical data
 Analysis of Variance (anova)
 Use when comparing the differences between means
from more than two groups
 The independent variable is known as a “Factor”
 The different conditions of this variable are known as
“levels”
 Can be used with independent groups
 Completely randomized single factor anova
 Can be used with paired groups
 Repeated measures anova
 The F Ratio (anova)
 F = variance between groups/variance within groups
 F = Treatment Effect + Differences due to
chance/Differences due to chance
 F = Variance among sample means/variance due to
chance or error
 The denominator of the F Ratio is known as the “error
term”
 Evaluation of the F Ratio
 Obtained F is compared with a critical value
 If you get a significant F, all it tells you is that at
least one of the means is different from one of
the others
 To figure out exactly where the differences are,
you must use Multiple Comparison Tests
 Multiple Comparison Tests
 The issue of “Experimentwise Error”
 Results from an accumulation of “per comparison
errors”
 Planned Comparisons
 Can be done with t tests (must be few in number)
 Unplanned Comparisons (Post Hoc tests)
 Protect against experimentwise error
 Examples:
 Tukey’s HSD Test
 The Scheffe Test
 Fisher’s LSD Test
 Newman-Keuls Test
 Measuring Effect Size in Anova
 Most common technique is “r2”
 Tells you what percent of the variance is due
to the treatment
 r2 = SS between groups/SS total
 Single Factor Anova
(One-Way Anova)
 Can be Independent Measures
 Can be Repeated Measures
 Do you know
population SD?

Yes
No

Use Z
Test Are there only
2 groups to
Compare?

No -
Yes - More than
Only 2 2
 No -
Yes - More than
Only 2 2 Groups
Groups

Use
Do you have ANOVA
Independent data?

If F not If F is
Yes No Significant, Significant,
Retain Null Reject Null
 Do you have If F not If F is
Independent data? Significant, Significant,
Retain Null Reject Null

Yes No

Compare Means
With Multiple
Use Comparison Tests
Use Paired
Independent
Sample
Sample
T test
T test
 Use
Use Paired
Independent
Sample
Sample
T test
T test

Is t test
Significant?

Yes No

Compare Reject Retain

means Null Null
Hypothesis Hypothesis
 Correlational Method
 No manipulation: just observe 2+
variables, then measure relationship
 Also called:
 Descriptive Non-experimental
 Naturalistic Observational
 Survey design
 Advantages & Disadvantages of
Correlational Methods
 ADVANTAGE: Efficient for collecting lots of data in a
short time
 ADVANTAGE: Can study problems you cannot study
experimentally
 DISADVANTAGE: Leaves Cause-Effect Relationship
Ambiguous
 DISADVANTAGE: No control over extraneous variables
 The Uses of Correlation
 Predicting one variable from another
 Validation of Tests
 Are test scores correlated with what they say
they measure?
 Assessing Reliability
 Consistency over time, across raters, etc
 Hypothesis Testing
 Correlation Coefficients
 Can range from -1.0 to +1.0
 The DIRECTION of a relationship is indicated by the sign
of the coefficient (i.e., positive vs. negative)
 The STRENGTH of the relationship is indicated by how
closely the number approaches -1.0 or +1.0
 The size of the correlation coefficient indicates the
degree to which the points on a scatterplot approximate
a straight line
 As correlations increase, standard error of estimate gets smaller
& prediction becomes more accurate
 The closer the correlation coefficient is to zero, the
weaker the relationship between the variables.
 Types of Correlation Coefficients
 The Pearson r
 Most common correlation
 Use with scale data (interval & ratio)
 Only detects linear relationships
 The coefficient of determination (r2) measures proportion of
variability in one variable accounted for by the other variable.
 Used to measure “effect size” in ANOVA
 The Spearman Correlation
 Use with ordinal level data
 Can assess correlations that are not linear
 The Point-Biserial Correlation
 Use when one variable is scale data but other variable is
nominal/categorical
 Problems with Interpreting Pearson’s r

 Cannot draw cause-effect conclusions

 Restriction of range
 Correlations can be misleading if you do not
have the full range of scores
 The problem of outliers
 Extreme outliers can disrupt correlations,
especially with a small n.
 Introduction to Regression
 In any scatterplot, there is a line that provides the “best
fit” for the data
 This line identifies the “central tendency” of the data and it can
be used to make predictions in the following form:
 Y = bx + a
 “b” is the slope of the line, and a is the Y intercept (the value of Y when X =
0)

 The statistical technique for finding the best fitting line is

called “linear regression,” or “regression”
 What defines whether a line is the best fit or not?
 The “least squares solution” (finding the line with the smallest
summed squared deviations between the line and data points)
 The Standard Error of Estimate
 Measure of “average error;” tells you the precision of your
predictions
 As correlations increase, standard error of estimate gets smaller
 Simple Regression
 Discovers the regression line that provides
the best possible prediction (line of best fit)
 Tells you if the predictor variable is a
significant predictor
 Tells you exactly how much of the
variance the predictor variable accounts
for
 Multiple Regression
 Gives you an equation that tells you how
well multiple variables predict a target
variable in combination with each other.
 Nonparametric Statistics
 Used when the assumptions for a
parametric test have not been met:
 Data not on an interval or ratio scale
 Observations not drawn from a normally
distributed population
 Variance in groups being compared is not
homogeneous
 Chi-Square test is the most commonly used
when nominal level data is collected