Chi-Square with SPSS

State the statistical assumptions for this test.

  1. The level of measurement of all the variables is nominal or ordinal.
  2. The sample sizes of the study groups are unequal; for the χ2the groups may be of equal size or unequal size whereas some parametric tests require groups of equal or approximately equal size.
  3. The original data were measured at an interval or ratio level, but violate one of the following assumptions of a parametric test:

Using the data set you have selected, choose independent and dependent variables.

Independent variable is (Gender)SEX which has two level such as 1 Male and 2 Female

Dependent variable is (Health)

HEALTH

Would you say your own health, in general, is excellent, good, fair, or poor?

0 Not applicable

1 Excellent

2 Good

3 Fair

4 Poor

8 Don’t know

9 No answer

Develop the null hypothesis and the alternative hypothesis.

Null Hypothesis (Ho): There is no statistically significant relationship between gender and condition of health

Alternative Hypothesis (Ha):There is a statistically significant relationship between Gender and condition of health

Use SPSS to calculate a chi-square.
Crosstabs

Case Processing Summary
Cases
Valid / Missing / Total
N / Percent / N / Percent / N / Percent
CONDITION OF HEALTH * RESPONDENTS SEX / 742 / 49.5% / 758 / 50.5% / 1500 / 100.0%
CONDITION OF HEALTH * RESPONDENTS SEX Crosstabulation
RESPONDENTS SEX / Total
MALE / FEMALE
CONDITION OF HEALTH / EXCELLENT / Count / 95 / 119 / 214
Expected Count / 99.2 / 114.8 / 214.0
% within CONDITION OF HEALTH / 44.4% / 55.6% / 100.0%
% within RESPONDENTS SEX / 27.6% / 29.9% / 28.8%
% of Total / 12.8% / 16.0% / 28.8%
Residual / -4.2 / 4.2
Adjusted Residual / -.7 / .7
GOOD / Count / 170 / 191 / 361
Expected Count / 167.4 / 193.6 / 361.0
% within CONDITION OF HEALTH / 47.1% / 52.9% / 100.0%
% within RESPONDENTS SEX / 49.4% / 48.0% / 48.7%
% of Total / 22.9% / 25.7% / 48.7%
Residual / 2.6 / -2.6
Adjusted Residual / .4 / -.4
FAIR / Count / 69 / 65 / 134
Expected Count / 62.1 / 71.9 / 134.0
% within CONDITION OF HEALTH / 51.5% / 48.5% / 100.0%
% within RESPONDENTS SEX / 20.1% / 16.3% / 18.1%
% of Total / 9.3% / 8.8% / 18.1%
Residual / 6.9 / -6.9
Adjusted Residual / 1.3 / -1.3
POOR / Count / 10 / 23 / 33
Expected Count / 15.3 / 17.7 / 33.0
% within CONDITION OF HEALTH / 30.3% / 69.7% / 100.0%
% within RESPONDENTS SEX / 2.9% / 5.8% / 4.4%
% of Total / 1.3% / 3.1% / 4.4%
Residual / -5.3 / 5.3
Adjusted Residual / -1.9 / 1.9
Total / Count / 344 / 398 / 742
Expected Count / 344.0 / 398.0 / 742.0
% within CONDITION OF HEALTH / 46.4% / 53.6% / 100.0%
% within RESPONDENTS SEX / 100.0% / 100.0% / 100.0%
% of Total / 46.4% / 53.6% / 100.0%
Chi-Square Tests
Value / df / Asymp. Sig. (2-sided)
Pearson Chi-Square / 5.252a / 3 / .154
Likelihood Ratio / 5.368 / 3 / .147
Linear-by-Linear Association / .002 / 1 / .964
N of Valid Cases / 742
a. 0 cells (0.0%) have expected count less than 5. The minimum expected count is 15.30.

Decide whether to reject or retain the null hypothesis.
Since the p-value of the chi-square test is 0.154 which is bigger than 0.05 so we will not able to reject the null hypothesis.

Generate syntax and output files in SPSS. You will need to copy and paste these into your Application document.

GET

FILE='C:\Users\Documents\gss04student_corrrected.sav'.

DATASET NAME DataSet1 WINDOW=FRONT.

CROSSTABS

/TABLES=HEALTH BY SEX

/FORMAT=AVALUE TABLES

/STATISTICS=CHISQ PHI

/CELLS=COUNT EXPECTED ROW COLUMN TOTAL RESID ASRESID

/COUNT ROUND CELL

/BARCHART.

Based on your SPSS analysis, report the results using correct APA format. Your report should include the following:SPSS syntax and output files

An analysis using a Chi Square test of Independence (Two-Way Contingency Table Analysis Using Crosstabs) for the following variables Gender (Respondent sex) and Health (Self-assessment of condition. Health condition (excellent, good, fair, poor) was not dependent on Gender, x2(2, N = 742) = 5.25, p = .154, Cramer’s = .084. As presented in Chart 2, the distribution was relatively equal between gender and health specially excellent, good, and fair. Chart 2 also shows a significantly higher percent of female in the category of Poor health. There are far more females consider themselves in poor health than male 69.7% to 30.3% respectively.