An introduction to statistical tests in SPSS
Perry R. Hinton, Isabella McMurray in Presenting Your Data with SPSS Explained, 2017
The chi-square test looks at the pattern of the results in the various categories of nominal or ordinal data to compare the frequencies with what we would expect according to a particular known pattern. Consider tossing a coin. If it is a ‘fair’ coin then we expect heads and tails with equal frequency. We are not surprised if it is not exactly 50% heads and 50% tails over a series of tosses as we know that we are not likely to get exactly equal numbers of heads and tails due to chance factors – but we do expect them to more or less even out over time. If we found that over a large number of tosses we were getting 80% heads and 20% tails we might begin to suspect that the coin was not fair. The chi-square test allows us to make a judgement about whether the frequencies in the categories follow an expected pattern (in this case, equal numbers of heads and tails) or a different pattern (such as mostly heads).
C
Filomena Pereira-Maxwell in Medical Statistics, 2018
and is referred to tables of the χ2distribution with the appropriate number of degrees of freedom (df) for an assessment of statistical significance. Assumptions for the chi- squared test are independence of the observations (i.e. each observation coming from a different individual), at least 80% of the cells with expected frequency >5, and all cells with expected frequency >1. When these assumptions cannot be met, other tests should be used, such as McNemar’s test for paired proportions or Fisher’s exact test. The latter is always a valid test for comparing independent groups. Yates’ continuity correction should be subtracted from the test statistic when the x2 test is applied to 2 x 2 tables. The Mantel-Haenszel χ2test is a special application of the x2 test that may be used in the presence of confounding. The z-test for the difference between two proportions is equivalent to the x2 test on a 2 x 2 table. See also chi-squared test for goodness-of-fit, chi-squared test for heterogeneity, chi-squared test for trend. An illustrative example is given in Box T.1 (p. 359).
New Statistical Designs for Clinical Trials of Immunomodulating Agents
Thomas F. Kresina in Immune Modulating Agents, 2020
If the endpoint for analysis is binary, response or nonresponse, then the appropriate analogue of the Kruskal-Wallis test is Fisher’s exact test for 2 × k contingency tables. A chi-square test should not be used when the sample size is small as it often is in phase I trials of biologicals. Fisher’s exact test is not easy to compute; however, it is included in many statistical packages. The analogue of the Johnckheere test for trend with binary response data is the Cochran-Armitage test [6] for linear trend in response probabilities. Table 2 shows the sample size requirements for this test as a function of the number of dose groups, the difference in response probabilities between the lowest and highest dose groups, and the response probability for the lowest dose group. As for Table 1, the response probabilities for the intermediate doses are assumed to be equally spaced and intermediate between the two extremes [7].
Attitude towards Covid-19 Vaccine: A Cross-Sectional Urban and Rural Community Survey in Punjab, Pakistan
Published in Hospital Topics, 2023
Iqra Mushtaque, Muhammad Riaz Dasti, Misbah Mushtaq, Ahmad Ali
The first step is, the collected data is double-checked for accuracy, and errors are removed. The research is then carried out using descriptive and inferential methods. In the descriptive analysis, the data is tabulated, and frequencies and percentages are measured in Microsoft Excel. Pearson’s chi-square test (a probability test) is used with SPSS to calculate the likelihood ratio of the relationship between public opinion in Pakistan and the covid-19 vaccine. The chi-square test is also used to calculate the chances of observed variables/frequencies matching each other and their significant association. If the p-value is greater than 0.05, there is no relationship between the observed variables/frequencies. If the p-value is less than 0.05, there is a good correlation.
Assessment of plasminogen activator inhibitor-1(PAI1) and thrombin activitable fibrinolysis inhibitor (TAFI) in Egyptian children with hemophilia A
Published in Pediatric Hematology and Oncology, 2022
Mohamed Soliman, Nahla Osman, Somyya Hefnawy, Mahmoud Ahmed El Hawy
Data were fed to the computer and analyzed using IBM SPSS software package version 20.0. (Armonk, NY: IBM Corp) Qualitative data were described using number and percent. The Kolmogorov-Smirnov test was used to verify the normality of distribution. Quantitative data were described using range (minimum and maximum), mean, standard deviation, median and interquartile range (IQR). Significance of the obtained results was judged at the 5% level. Chi-square test is used for categorical variables, to compare between different groups. Fisher’s Exact is used for correction for chi-square when more than 20% of the cells have expected count less than 5 .Student t-test is used for normally distributed quantitative variables, to compare between two studied groups. Mann Whitney test is used for non-normally distributed quantitative variables, to compare between two studied groups. F-test (ANOVA) is used for normally distributed quantitative variables, to compare between more than two groups. Spearman coefficient is used to correlate between two distributed non-normally quantitative variables. Kruskal Wallis test: is used for non-normally distributed quantitative variables, to compare between more than two studied groups.
ST2 and galectin-3 as novel biomarkers for the prediction of future cardiovascular disease risk in preeclampsia
Published in Journal of Obstetrics and Gynaecology, 2022
Nil Atakul, Yıldız Atamer, Şahabettin Selek, Berna Kılıç, Fatmanur Koktasoglu
Power and sample size were calculated with G*Power version 3.1.9.2. The IBM Statistical Package for Social Sciences Version 26.0 was used to analyse all of the data (SPSS for Windows, Chicago, IL). The mean, median, standard deviation, lowest maximum frequency and ratio values have been used as descriptive statistics of the results. The Kolmogorov–Smirnov test was used for the distribution of variables. The quantitative independent data were analysed by the Mann–Whitney U test. The Chi-square test was used to determine whether there is an association between categorical variables. Generalised linear models were used to compare the clinical and metabolic data analysis between PE and healthy pregnant patients. p < .05 value is considered statistically significant.
Related Knowledge Centers
- Statistical Hypothesis Testing
- Validity
- Null Hypothesis
- Pearson'S Chi-Squared Test
- Statistical Significance
- Fisher'S Exact Test
- Sampling Distribution
- Sampling
- Test Statistic
- Cochran–Mantel–Haenszel Statistics