You are on page 1of 3

1. Describe an application of a chi-square analysis to your area of research.

Clearly define
your variables and state the null and alternative hypotheses.

Research Question: Are the proportion of male college students who treat young, middle-
aged, and elderly women with distain the same?
For the purpose of this study, a random sample of 90 students was selected. The data
consists of two variables:
1. Age: It has three levels, Young, Middle-aged and Elderly.
2. Condes stands for condescension which has two levels, not condescending and
condescending.
Contingency Table:
Age
Condes
Total
Not condescending Condescending
Young 21 9 30
Middle-Aged 25 5 30
Elderly 16 14 30
Total 62 28 90
Hypothesis:
H0: In the entire population, there is no significant association between age and
condescension.
H1: In the entire population, there is significant association between age and
condescension.


2. Present the results from your application assignment using APA format in accordance
with the Publication Manual of the American Psychological Association. State a null and
alternative hypothesis and include a measure of effect size. Note: you do not need to
include all 10 questions you did for your application assignment, just the APA write-up
for the chi-square.

A sample of 105 students was evaluated to determine if gender balance was associated
with ethnicity.
Null hypothesis: For the entire population, gender balance and ethnicity are not related
Alternative hypothesis: For the entire population, gender balance and ethnicity are related
The above data was analyzed using chi-square test for significance of association
between attributes. Pearson chi-square and Cramers V tests indicated a similarity in the
observed values and expected values.
2
(4, N = 105) = 1.19, p > .05. Due to the lack of
an identified relationship, the null hypothesis is accepted.

3. Everyones quarterly question is: Please describe and define, in your own words, what
the chi-square analysis is, the conditions under which it is used, and how it compares to
the Pearson Correlation. ALSO, in your own words, describe and define what loglinear
modeling is and the conditions under which it is used. Do not forget the operational
definitions and examples!


Chi-square tests are non-parametric tests used to determine whether there is significant
association between two nominal or categorical variables. An assumption for the chi-
square statistic is that the observations are independent. The chi-square statistic is small
when there is no association and larger when there is an association due to the
relationship between the expected and observed counts. A row/column table would be
used to show this data. The data is presented using expected and observed data
frequencies.
The Pearson correlation is also used to examine relationships; however, the assumptions
are that the data are distributed normally and variables can be continuous.
Log-linear models allow for chi-square tests to function similarly to models of regression.
They rely heavily on categorical data and make use of frequency tables. Log-linear
models make it easier to interpret what would otherwise have been overload for a chi-
square table; however they are not simple for the mathematically challenged. Log
linear models use the natural logarithm (of the frequency of cases in a particular cell of
the table) to produce a linear model and can become complicated to explain without
referring directly to SPSS output. An example for a log-linear model might be looking at
the relationship between what baccalaureate degrees lead to which professional careers.

George, D., & Mallery, P. (2012). IBM SPSS Statistics 19 step by step: A Simple guide
and reference (12th ed.). Boston, MA: Pearson.
Gravetter, F. J., & Wallnau, L. B. (2009). Statistics for the behavioral sciences (8th
edition). Belmont, CA: Wadsworth.

You might also like