Comparison between NXG Logic Explorer and other software for running a single t-test

	Other software			NXG Logic Explorer
Task/assumptions	Description	Time required	Remarks	Description	Time required	Remarks
Import data	If data not clean, get back to provider	Minutes to 2,3 days	May result in long delays	Automatic data cleaning	N/A
Run summary statistics on variable	Evaluate average, s.d., min, max, median, quartiles, separately from skewness, kurtosis	<1 hour, need to develop syntax language for command line usage, manually run	Results are in separate output	Each run automatically includes avg, s.d., min. max range, quartiles, skewness, kurtosis, and p-value for normality	5-10 seconds, automatically run	Can run multiple variables, no syntax needed
Test normality assumption, evaluate distribution	Run separate test of normality (Lilliefors, Shapiro-Wilk)	Few minutes, manually run	Can’t make single run on multiple variables, Results are in separate output	N/A	N/A	Performed during summary statistics run
Test equality of variance	Run separate Levene’s or Bartlett’s test	Few minutes, manually run	Can’t make single run on multiple variables; Results are in separate output	N/A	N/A	Performed during testing
Run t-test on single variable		Few seconds, manually run	Results are in separate output	Automatically runs Bartlett’s test, t-test, and Mann-Whitney	Few seconds, automatically run	Results for multiple variables in single output
Association tests for single categorical variable	Need to make additional runs	< 1 hour, but need to set up runs separately, manually run	Must transpose results from individual runs into useable table or format	Automatically runs chi-squared tests for multiple variables	Few seconds, automatically run	Chi-squared tests run on categorical variables during parametric, non-parametric testing
Use output		<1 hour, depending of format	Must transpose results from individual runs into useable table or format	N/A	N/A	Readily publishable/presentable format
	Total time	Several minutes (e.g. 10-20) for one variable (parametric)	Hundreds of keystrokes & debugging, loss of productivity, not ergonomic		< 1 minute for multiple variables (parametric, non-parametric, categorical)	Few mouse clicks

Step 1: Start Explorer, and input the Retinol dataset (5 seconds).

Step 2: Select independence tests, unpaired 2-sample (2 seconds).

Step 3: Select SEX as the 2-group variable, and the remaining continuous and categorical variables (5 seconds).

Step 4: Select the Grouped analysis icon and view the output table (5 seconds). Notice the adjustment to the d.f. of the t-test when Bartlett's test is significant. This implies that the Welch t-test for unequal variances was used. The categorical tests for vitamin use and smoking provide the asymptotic p-values along with the Fisher exact test based on a set limit of 10,000 iterations. This can be increased to 100,000 if necessary, but 10,000 has shown to converge on results from 100,000 iterations.

Chi-squared tests are run the same time parametric and non-parametric tests are run on the continuous variables.

Step 5: A 3-group ANOVA (Kruskal-Wallis) set of tests along with chi-squared tests for SEX and SMOKING can be quickly run by simply selecting the 3-group VITUSE (vitamin use) variable as the grouping variable, with all remaining variables as the test variables (5 seconds).

Step 6: Select the Grouped analysis icon and view the output table (5 seconds). Note that Welch ANOVA is used when Bartlett's test is significant, due to heteroscedasticity (unequal variances). This can be noticed by a change in the denominator d.f. of the F-ratio test - shown in the table. Again, you can see the asymptotic p-value for the chi-squared tests along with the Fisher exact test (10,000) iterations.

In summary, the total time required to run the 6 steps was less than a minute, and the results included a dozen variables and dozens of tests, while all the necessary tests concerning equality of variances were ran behind the scenes, with Welch tests employed if heteroscedasticity was present. The chi-squared tests were also performed on the categorical variables which happened to be included in the 2-group and k-group tests.

The above runs are ideal for generating demographic tables for intervention studies, case-control, cohort and prospective, and baseline variables for randomized clinical trials and longitudinal studies with k-treatment groups. Group labels can be easily input using the label editor or by input of text files containing categorical group labels.

The analyses presented above are also available in the free Standard edition of Explorer.   Once you become accustomed to the time-savings offered by using Explorer, you will begin to realize how much time you have wasted with your current software. We also use Explorer whenever possible, since we can't afford to waste time and lose the productivity associated with use of so many other platforms.