Psychology 110, Spring 2012
Homework Assignment 5
1. Consider a study of whether infants born prematurely begin to recognize faces later
than do infants in general. Make a chart of the four possible correct and incorrect
decisions in hypothesis testing fo
Homework Assignment 5
1. Consider a study of whether infants born prematurely begin to recognize faces later than
do infants in general. Make a chart of the four possible correct and incorrect decisions in
hypothesis testing for this study, and explain wh
Population 2
Population 1
We started with two hypothetical distributions of what scores on a variable that we
have measured would look like. Each is a population representing all possible scores
The first, population 1, is what scores would hypothetically
How can we determine if our research
hypothesis is likely to be correct (and conduct
hypothesis testing) if we need to compare our
experimental group to some comparison
group, but we do not know the mean or the
variance of the comparison group?
The main p
X
The normal distribution can be thought of as a probability
distribution: The proportion of cases between any two Z
scores is the same as the probability of selecting a case
between those two Z scores
If X marks the spot where .03% of the scores fall, we
ERRORS IN INFERENCE
Hypothesis 0: A new drug to promote infant walking does not work; it is useless
Hypothesis 1: A new drug to promote infant walking works; infants walk sooner
True State of Affairs
useless)
Hypothesis 0 is True
(the drug works)
Hypothes
An experiment does not involve observing one
person who receives some treatment and
deciding if this person is different from the group of
comparison scores (the population of all
individuals who do not receive treatment). An
experiment involves observing
Descriptive Statistics:
Frequency Tables
Histograms
Distributions
Frequency: Number of cases (people) that responded to
p. 7-9
a particular value for one of the variables how
frequently a given score appears in the sample.
Frequency distribution: The patt
The simplest case: A sample of one person (N=1).
Give some experimental treatment to one person, measure
his/her scores on the variable of interest.
Compare the extremity of his/her score against a comparison
distribution.
The comparison distribution is o
One-way Analysis of Variance (ANOVA)
Our discussion thus far has been limited to experiments that
compare two conditions against each other:
a) scores without a treatment for anxiety versus scores with a
treatment for anxiety
b) one group of infants who r
Limits of Method Just Reviewed:
Recall that when calculating between group variance we
need to use sample size in the formula: Sbetween2 =
(SM2)(N)
This procedure works great for experiments where there are
equal sample sizes, but it is problematic when t
One-Way ANOVA: One independent variable with 2
or more groups/conditions/levels
Using our previous example of whether jurors are affected by
information irrelevant to the trial, we had only one
independent variable (whether jurors had information about
so
An interaction is a joint effect over and above the main effects. In fact,
this language is quite precise. The variance associated with an
interaction is exactly the variance that exists over and above (that is left
over) after we have accounted for a) th
1.
2.
3.
4.
5.
A researcher is interested in an observed phenomenon: The students who suffer from
anxiety seem to sleep less than students not suffering from anxiety. The researcher seeks to
determine whether the mean number of hours slept per night is di
Correlation and Prediction
What does it mean to say that two variables are associated, or
that they are correlated (and that we can quantify this
correlation with a number that tells you the degree of the
relationship)?
If we say Grades in college are cor
The Correlation Coefficient
How do we define high and low? What makes a correlation
strong or weak (a high or low r)?
The correlation coefficient (r) is calculated by considering how
much each individuals score on the 1st variable deviates from the
sample
To date, our dependent variables have been
quantitative variables we can calculate means for.
What do we do if the DV is a category?
Levels of Measurement: Numeric and Nominal
Variables
There are two broad types of variables.
a) Numeric (quantitative): wh
Conducting a One-way Analysis of variance
Once having calculated the Swithin2 and Sbetween2 we can test the H0
If the null hypothesis is correct, Swithin2 = Sbetween2 or,
Sbetween2 / Swithin2 = 1. This ratio is called an F score
If the H0 is correct F = 1
Variance: How uniform are the scores associated with a given
variable? A distribution can be characterized by how much the
scores in it vary from each otherthey can range from being
bunched closely together or very spread out. This is a question
quite sep
Probability of 10 heads in a row:
X X X X X X X X X = .00098
p=.00098 = .098%
Outcomes of coin flips
49.9%
X
Lets say I offer you a million dollars in a bet: I say I will flip 10
tails in a row you say I wont. You cannot know for sure in
advance I wont,
PSYC110, Spring 2010
Assignment 12
1. Make up a scatter diagram with 10 dots for each of the following situations: (a) large
positive linear correlation, (b) small positive linear correlation, (c) strong negative
correlation, (d) no correlation, and (e) c
Homework assignment 6 One sample t test and Dependent means t test
1. In a particular country, it is known that college seniors report falling in love an average
of 2.2 times during their college years. A sample of five seniors, originally from that
count
Homework assignment 10 ANOVAs with two IVs and interaction effects
1. Each of the following tables of means shows the results of a study using a factorial
design. Assuming that any differences are statistically significant, for each table (a) and
(b), mak
Psychology 110, Spring 2012
Homework Assignment 3
1) When a result is significant, explain why it is wrong to say the result proves the
research hypothesis?
2) A researcher wants to test whether a certain sound will make rats do worse on learning
tasks. I
Psychology 110, Spring 2012
Homework Assignment 4
1. What is the distribution of sample means?
2. Explain how you could create a distribution of means by taking a large number of
samples of six individuals each.
(Do not just copy the answer from the book/
Psychology 110, Spring 2012
Homework Assignment 1
1) If you did not finish it in lab, finish the class survey and enter your own data into the
SPSS file you created in lab. Then e-mail your data (1 line of variable names and 1 line
of numbers with your sc
Psychology 110, Spring 2012
Homework Assignment 2
1) 2) If the mean of a test is 13 and its standard deviation is 3, then what is the raw score for a
person with a z score of -2?
2) A personnel psychologist has to decide which of three employees to place
Assignment 11 Chi-Square Tests
1. Carry out a chi-square test of for goodness of fit for each of the following studies (use
the .01 level for each):
2. Stasser and colleagues (1989) conducted a study involving discussions of three
different candidates, wh
Homework assignment 7 t test for independent means
1. For each of the following studies, say whether you would use a t-test for dependent
means or a t-test for independent means.
a). A researcher measures the heights of 40 college students who are the fir