Statistical software medical research

These two estimates of variances are compared using the F-test. However, a repeated measure ANOVA is used when all variables of a sample are measured under different conditions or at different points in time. As the variables are measured from a sample at different points of time, the measurement of the dependent variable is repeated. When the assumptions of normality are not met, and the sample means are not normally, distributed parametric tests can lead to erroneous results.

Non-parametric tests distribution-free test are used in such situation as they do not require the normality assumption. That is, they usually have less power. As is done for the parametric tests, the test statistic is compared with known values for the sampling distribution of that statistic and the null hypothesis is accepted or rejected.

The types of non-parametric analysis techniques and the corresponding parametric analysis techniques are delineated in Table 5. Median test for one sample: The sign test and Wilcoxon's signed rank test.

The sign test and Wilcoxon's signed rank test are used for median tests of one sample. These tests examine whether one instance of sample data is greater or smaller than the median reference value. Therefore, it is useful when it is difficult to measure the values. Wilcoxon's rank sum test ranks all data points in order, calculates the rank sum of each sample and compares the difference in the rank sums.

It is used to test the null hypothesis that two samples have the same median or, alternatively, whether observations in one sample tend to be larger than observations in the other. The two-sample Kolmogorov-Smirnov KS test was designed as a generic method to test whether two random samples are drawn from the same distribution.

The null hypothesis of the KS test is that both distributions are identical. The statistic of the KS test is a distance between the two empirical distributions, computed as the maximum absolute difference between their cumulative curves. The Kruskal—Wallis test is a non-parametric test to analyse the variance. The data values are ranked in an increasing order, and the rank sums calculated followed by calculation of the test statistic.

In contrast to Kruskal—Wallis test, in Jonckheere test, there is an a priori ordering that gives it a more statistical power than the Kruskal—Wallis test. The Friedman test is a non-parametric test for testing the difference between several related samples. The Friedman test is an alternative for repeated measures ANOVAs which is used when the same parameter has been measured under different conditions on the same subjects. Chi-square test, Fischer's exact test and McNemar's test are used to analyse the categorical or nominal variables.

The Chi-square test compares the frequencies and tests whether the observed data differ significantly from that of the expected data if there were no differences between groups i. It is calculated by the sum of the squared difference between observed O and the expected E data or the deviation, d divided by the expected data by the following formula:.

A Yates correction factor is used when the sample size is small. Fischer's exact test is used to determine if there are non-random associations between two categorical variables.

It does not assume random sampling, and instead of referring a calculated statistic to a sampling distribution, it calculates an exact probability. McNemar's test is used for paired nominal data. The null hypothesis is that the paired proportions are equal. The Mantel-Haenszel Chi-square test is a multivariate test as it analyses multiple grouping variables. It stratifies according to the nominated confounding variables and identifies any that affects the primary outcome variable.

If the outcome variable is dichotomous, then logistic regression is used. Numerous statistical software systems are available currently. There are a number of web resources which are related to statistical power analyses. A few are:. It gives an output of a complete report on the computer screen which can be cut and paste into another document. It is important that a researcher knows the concepts of the basic statistical methods used for conduct of a research study.

This will help to conduct an appropriately well-designed study leading to valid and reliable results. Inappropriate use of statistical techniques may lead to faulty conclusions, inducing errors and undermining the significance of the article. Bad statistics may lead to bad research, and bad research may lead to unethical practice. Hence, an adequate knowledge of statistics and the appropriate use of statistical tests are important. An appropriate knowledge about the basic statistical methods will go a long way in improving the research designs and producing quality medical research which can be utilised for formulating the evidence-based guidelines.

National Center for Biotechnology Information , U. Journal List Indian J Anaesth v. Indian J Anaesth. Zulfiqar Ali and S Bala Bhaskar 1.

Author information Copyright and License information Disclaimer. Address for correspondence: Dr. E-mail: moc. This article has been corrected.

See Indian J Anaesth. This article has been cited by other articles in PMC. Abstract Statistical methods involved in carrying out a study include planning, designing, collecting data, analysing, drawing meaningful interpretation and reporting of the research findings.

Key words: Basic statistical tools, degree of dispersion, measures of central tendency, parametric tests and non-parametric tests, variables, variance.

Open in a separate window. Figure 1. Quantitative variables Quantitative or numerical data are subdivided into discrete and continuous measurements. Table 1 Example of descriptive and inferential statistics. Descriptive statistics The extent to which the observations cluster around a central location is described by the central tendency and the spread towards the extremes is described by the degree of dispersion.

Measures of central tendency The measures of central tendency are mean, median and mode. The variance of a sample is defined by slightly different formula: where s 2 is the sample variance, x is the sample mean, x i is the i th element from the sample and n is the number of elements in the sample.

The SD of a sample is defined by slightly different formula: where s is the sample SD, x is the sample mean, x i is the i th element from the sample and n is the number of elements in the sample. Table 2 Example of mean, variance, standard deviation. Normal distribution or Gaussian distribution Most of the biological variables usually cluster around a central value, with symmetrical positive and negative deviations about this point.

Figure 2. Skewed distribution It is a distribution with an asymmetry of the variables about its mean. Figure 3. Curves showing negatively skewed and positively skewed distribution. Inferential statistics In inferential statistics, data are analysed from a sample to make inferences in the larger collection of the population.

Table 3 P values with interpretation. Table 4 Illustration for null hypothesis. For example, Stata was used in Use of SAS was somewhat more common in non-U. There is little information available about what kind of statistical software is used in the HSR field or, for that matter, in other academic disciplines.

A variety of articles have been published comparing the features of various statistical software applications and identifying their relative benefits for use in research studies. But virtually no information is publically available about which types of statistical software are most commonly used for data analysis purposes. A few investigators have attempted to offer some insight on this question.

For example, a survey conducted by Scotch et al. However, that survey was based on a small group of 36 participants. Robert Muenchen has analyzed data on the number of Google Scholar hits for various statistical software packages from through [ 7 ]. Muenchen's analysis for covering articles from all disciplines found that Stata was the most commonly cited statistical software application, with about 24, Google Scholar hits, followed by SPSS about 19, and SAS about 17, The present study is the first to provide detailed information on statistical software usage in HSR studies.

Moreover, between and , the use of SAS increased considerably, while the use of other software applications stayed the same or fell. Our simple stratification of the data revealed that use of SPSS was disproportionately greater in non-U. Variations based on country of authorship may be the result of various factors, including marketing strategies by the software vendors, researchers' background and training, and the specific types of HSR research conducted in the U.

However, since this study was primarily focused on articles from U. HSR journals, we were unable to collect sufficient information to determine software usage trends in other countries or to make comprehensive international comparisons.

Further studies based on a selection of non-U. Given that we restricted our attention only to original research articles rather than reviews, meta-analyses, editorials, etc , it was surprising that only HSR journals identified the specific software used in the data analysis.

The proportion of articles mentioning specific analytical software was similar among articles with U. In most cases, there was no way of knowing from the information contained in the articles why the specific type of software used in the data analysis was not identified. We suspect that in some cases the use of statistical software was unnecessary, and in other cases researchers conducted computerized analyses, but without identifying explicitly which particular software application was used.

Additionally, some researchers may have written their own computer program to perform an analysis rather than relying on a general-use software application. It should be noted that journals have varying editorial policies concerning the identification of particular software products. Some journals, such as the Journal of Preventive Medicine and the Journal of the American Dietetic Association , require authors to specify the name and version number of statistical software utilized.

However, some journals specifically instruct authors not to identify the software used for data analysis. For example, instructions for the Journal of Bone and Joint Surgery dictate that authors "do not identify any statistical software unless some aspect of the analysis was uniquely dependent on a particular software package.

These guidelines generally advise authors to identify the statistical software and version used, when applicable. Interestingly, none of the three journals used in this study contained specific instructions for authors as to whether or not to identify the specific statistical software employed in their studies. A primary reason to be concerned about identifying the precise statistical software used in studies is because different software packages can produce varying results, owing to differences in the estimation methods and algorithms used to perform a specific statistical analysis.

Indeed, several recent studies have documented numerous inconsistencies in output among commercial software programs based on each program's underlying methodological assumptions [ 12 , 13 ]. To ensure reliability of analytical results across studies and reasons for any observed inconsistencies , it would be helpful for investigators to identify not only the general software package and version number, but also the specific software procedures used in the analysis.

The intention of this brief report is to provide health services researchers with general information about the most common types of statistical software used in HSR, describe recent trends in software usage, identify variations in use of software among researchers in the U.

We hope that this information will help researchers during the software selection process and motivate them to provide complete information about specific software employed in HSR studies. The information should be used with the recognition that our study had certain methodological limitations. For example, some articles contained insufficient information to determine whether or not statistical software was used or which software application was employed.

In addition, our analysis did not attempt to qualitatively assess the merits of particular software applications relative to one another or to evaluate their suitability for different analytical uses. Because we used only three HSR journals for the study, results might not be entirely representative of the software usage patterns throughout the entire United States or in specific HSR sub-disciplines, such as health economics. Nevertheless, this study represents perhaps the nation's first attempt to systematically identify the most commonly used statistical software in HSR and provides unique baseline data with which to potentially inform similar attempts to understand software usage practices in other fields.

The authors have no financial or other competing interests relating to the conduct of this study or its publication. AD was responsible for the overall design and conduct of this study and was the principal manuscript author.

JP oversaw all data collection, was primarily responsible for the data analysis, and participated in the review and authoring of the manuscript. LG collected data, input the data into an analytic data base, and helped to review the manuscript. All authors read and approved the final manuscript. In his experience supervising doctoral students and other health services researchers, he has frequently fielded inquiries from investigators about which statistical software packages are typically used, or ought to be used, in the health services research field.

Funds for this study were obtained from internal institutional sources. Tom Wickizer provided suggestions and helped review portions of this study. National Center for Biotechnology Information , U. Published online Oct 6. Author information Article notes Copyright and License information Disclaimer. Corresponding author. Allard E Dembe: ude. Received Dec 7; Accepted Oct 6. This article has been cited by other articles in PMC. It also supports direct code execution, seeing the history of data analysis, debugging as well as workspace management.

OriginPro free statistical software online is used not only by businesses but also by students, researchers, and scientists. It is considered a friendly tool for beginners as they can opt for advanced customization as and when they become familiar with the application. TIMi Suite is a popular name in the field of predictive analytics. The Statistical Lab aims to not only carry out analysis of large streams of data. It is also capable of educating your employees in basic and advanced statistical concepts.

The free statistical software for data analysis can connect and display data frames, frequency tables, matrices, etc. Develve is a powerful free statistical software for medical research as it is capable of performing high-speed data interpretation. It also has specialized features such as Response Surface Methodology which enables it to minimize fake assumptions.

DataMelt is perfect for organisations to conduct data interpretation, data visualization, and mathematical computation. SciPy best free statistical analysis software is a python-based ecosystem that provides data interpretation and visualisation capability for scientific, mathematical, and engineering fields.

SciPy comes loaded with a Matplotlib package that is useful for quickly plotting 2-D plots. Zelig is one of the most potent tools for utilizing statistical concepts for intuitive visualization of data. Zelig free statistical software for students uses R from a number of researchers. OpenStat can be used effectively by students, researchers, teachers, and businesses. The software offers a number of options when it comes to saving and opening data files.

IBM Planning Analytics. Customer Analysis Solution. Qnvert Marktech Marketing Analytics Solution. IBM Datacap. KeyStocks Lite. Zoho Analytics. Qnvert Marktech Marketing Analyt Spine HRMS. PeoplesHR Turbo. Vyapar Billing Software. Singularity complete.