No, Intellectus Statistics™ is for quantitative analysis only. For assistance with qualitative analysis, please call Statistics Solutions to schedule a free consult: 877-437-8622.
Nominal: In this level of measurement, numbers are used to categorize the data. For example, if gender is your variable, the responses will be male or female. A dichotomous nominal variable has only two categories.
Ordinal: Ordinal level variables have a meaningful order to them such as rank. For example there is an order to “drink size” (small, medium, large), however there is not a consistent distance between sizes.
Scale: Numeric variables that have equal intervals between each value, for example age.
The application will accept data in .csv format.
When uploading a .csv file to the application all variables with text data will be default to nominal and all variables with numeric data will default to scale. Level of measurement can be adjusted after upload if necessary.
Video Tutorial: Preparing your data for Intellectus Statistics™
When your data is uploaded to the Intellectus Statistics™ application you should confirm your levels of measurement are as follows for each analysis:
Pearson Correlation: All variables are scale level of measurement
One way ANOVA: Independent variable is nominal level of measurement; dependent variable is scale
Independent samples t-test: Independent variable is a dichotomous nominal; dependent variable is scale
Dependent samples t-test: both variables are scale
Chi-square: x variable (factor) is nominal; Y variable (factor) is nominal
Linear regression: Dependent variable is scale; predictor(s) scale or nominal
Mediation: Continuous or dichotomous categorical variable
Moderation: Continuous or dichotomous categorical variable
Reliability: All variables should be the same level of measurement with themselves (e.g., only ordinal variables used together)
Logistic regression: Independent variables are nominal or scale; dependent variable is dichotomous
Wilcoxon signed rank: Both variables are ordinal (or scale)
Mann Whitney U: Independent variable is dichotomous; dependent variable is ordinal (or scale)
Kruskal Wallis: Independent variable is nominal with three or more levels; dependent variable is ordinal (or scale)
Friedman Test: All variables are ordinal (or scale)
Repeated measures ANOVA: All variables are scale
One-within One between ANOVA: Independent variable is nominal; dependent variables are scale
ANCOVA: Independent variable is nominal; covariates are scale; dependent variable is scale
Two-Between ANOVA: Dependent variable is scale; independent variables are nominal
Currently the available analyses are:
DESCRIPTIVE STATISTICS
Descriptive Statistics: Examines frequencies and percentages for nominal and ordinal level variables, and means and standard deviations for scale level variables (e.g., frequency and percent of males and females, means and standard deviations for age)
Cronbach Reliability: Examines the extent to which a set of scale level variables are consistently scored (e.g., for a highly reliable construct, participants consistently endorse a similar level of agreement on a set of items)
ASSOCIATIONS
Chi-Square Test of Independence: Compares the observed frequencies to expected frequencies of two nominal-level variables (e.g., gender and political affiliation)
Smart Correlation: Appropriate correlations between the variables are conducted based on the level of measurement of the variable (dichotomous, ordinal, or scale). Examines the strength of the relationships and ranges from -1 to +1.
Pearson Correlation: Examines the relationship between two or more scale-level variables (e.g., math scores related to study time)
Spearman Correlation: Examines the relationship between two ordinal or scale-level variables (e.g., study time in minutes related to grade letter A-F)
Partial Correlation: Conducts a partial correlation between two scale-level variables while controlling for scale-level covariates.
DIFFERENCES
One Sample t-test: Used to assess if the values of a single variable are significantly different from a tested value.
Dependent Sample t-test: Examines the mean difference between two paired scale-level variables (e.g., differences between math scores pretest vs. posttest)
Independent Sample t-test: Examines mean differences on a scale-level dependent variable by a dichotomous nominal level independent variable (e.g., differences in math scores by gender)
One-Way ANOVA: Examines mean differences on a scale level dependent variable by a nominal level independent variable (e.g., differences on math scores by ethnicity)
ANCOVA: Examines mean differences on a scale level dependent variable by a nominal level independent variable controlling for a scale level covariate variable (e.g., differences on math scores by gender controlling for family income)
Two-Between ANOVA: Examines differences on a scale level dependent variable by two nominal level variables (e.g., differences on math scores by gender and ethnicity)
Repeated Measures ANOVA: Examines mean differences among two or more scale level variables (e.g., differences among pretest vs. posttest vs. follow-up math scores)
One-Between One-Within ANOVA: Examines mean differences both on a scale level dependent variable measured multiple times (Within component) and on a nominal level independent variable (Between component) (e.g., differences on pretest and posttest math scores by gender)
MANOVA: Examines simultaneous mean differences on two or more scale level dependent variables by a nominal level independent variable (e.g., differences on math, science, and reading scores by gender)
MANCOVA: Conducts a multivariate analysis of covariance to assess differences in multiple scale dependent variables by one or more nominal independent variables with the ability to control for a set of scale covariates.
REGRESSION ANALYSES
(Multiple) Linear Regression: Examines if one or more scale, ordinal, or nominal level independent variables predict a scale level dependent variable (e.g., Does age and political affiliation predict income?)
Binary Logistic Regression: Examines if one or more scale, ordinal, or nominal level variables predict a dichotomous nominal level variable. (e.g., Does time studying and gender predict test pass or fail?)
Ordinal Logistic Regression: Examines if one or more scale, ordinal or nominal level variables predict an ordinal or scale level variable (e.g., Does time studying and gender predict letter grade A-F?)
Multinomial Logistic Regression: Examines if one or more scale, ordinal, or nominal level variables predicts a nominal level variable. (e.g., Does time studying and gender predicting pass course, fail course, drop course?)
NON-PARAMETRIC ANALYSES
Chi-Square Goodness of Fit: Examines if a nominal variable is equally distributed across all groups (e.g., testing the distribution of favorite colors)
McNemar’s test: Examines the relationship between two dichotomous variables that can be matched together (such as by time). Both variables must have the same groups for the analysis to run properly.
Wilcoxon Signed-Rank Test: Examines the difference in two paired ordinal or scale level dependent variables (e.g., letter grade pretest vs. posttest
Friedman ANOVA: Examines differences among two or more scale or ordinal level variables (e.g., differences among pretest vs. posttest vs. follow-up letter grade)
Mann-Whitney U: Examines the difference in an ordinal level dependent variable by a dichotomous nominal level variable (e.g., differences on letter grade A-F by gender)
Kruskal-Wallis ANOVA: Examines the difference in an ordinal or scale level dependent variable by a nominal level variable (e.g., differences in letter grade A-F by ethnicity)
ADVANCED STATISTICAL ANALYSES
Mediation Analysis: Examines if one scale level mediator variable explains the relationship between a scale level independent variable and a scale level dependent variable (e.g., Does years of education mediates relationship between income and job satisfaction?)
Moderation Analysis: Examines if one scale level moderator variable strengthens or weakens the relationship between a scale level independent variable and a scale level dependent variable. (e.g., Does age moderates the relationship between income and marital satisfaction?)
Exploratory Factor Analysis: Uses a set of ordinal or scale level variables to assess the number of constructs, and which variables load on each construct
Hierarchical Linear Modeling (HLM)/Multilevel Models: Examines if a set of scale or nominal level independent variables predict a scale level dependent variable after the data has been nested by a nominal level variable (e.g., socio-economic status and time studying predicts GPA after nesting participants within teacher)
Many small samples will not allow you to conduct inferential statistics such as ANOVA’s. A better choice would be to select non-parametric statistics or just keep it a descriptive study.
Topic selection is important, but not if it takes to 6 months to do it. Find something that’s interesting, that a committee can agree with, and begin. The key to a doable project are clear research questions written in statistical language, having instruments that measure the constructs of interest, having access to participants, and that you have a procedure to administer the instruments to those participants. (Remember too: while you wait for the perfect topic, you are spending your precious time and tuition money).
Motivation is an inside job. It’s important to remember that we are 100% responsible for what happens (good and bad), that it’s our job to create and maintain the vision of us completing the thesis or dissertation, and that how we prioritize our time is key. Also, get the support (e.g., emotional, time, money, etc.) that you need.
The time to complete a dissertation can realistically range from 1-2 years. Your focus, your committee, whether you use primary or secondary data, IRB, and the number of revisions, all play a role in the length of time. A key is to find out from other students how it was to work with a particular chair, how timely is their feedback, and did the chair seem to want to get you through.
For data anlaysis plans our typical turnaround time is 1-2 weeks, for quantitative results our typical turnaround time is 2-3 weeks.