Statistical Analysis Using SPSS

Master All Types of Statistical Analyses

Applied Statistics 4.8(100)9h 52m60 lectures3 sections

What you'll learn

Get to know the SPSS interface and the types of variables
Import and enter data and set up variables
Run descriptive analysis and create charts
Run the chi square test and T tests
Apply ANOVA
Calculate correlation in its types
Run linear and logistic regression
Use nonparametric tests
Handle missing values and multiple response questions

About this course

This course teaches statistical analysis with SPSS from the beginning, one of the best known programs researchers use to analyze their data. You start with the contents of the course, the types of variables, the main menus and the toolbar, then importing data, setting up a new variable and entering data. Next you learn descriptive analysis for categorical and quantitative variables, charts, the normal distribution test, the chi square test, T tests, One way ANOVA and comparing means. The course then covers correlation in its types, linear, multiple, logistic and nonlinear regression, and parametric and nonparametric tests such as Mann Whitney, Kruskal Wallis and Wilcoxon. In the last part you learn commands such as compute, recode, split file and select cases, multiple response questions, handling missing values, and importing data from Excel and Google forms. It suits researchers, graduate students and anyone who analyzes survey data. In the end, you will be able to enter your data, analyze it, choose the right test and read the results.

Expected outcomes

Ability to perform statistical analysis using SPSS confidently.
Understanding how to input and analyze data professionally.
Mastering the use of various tools in SPSS for data analysis.
Handling missing values and importing data from other sources.
Analyzing data using different statistical tests.

Learner reviews

These reviews are from learners who bought the content and completed at least 50% of it — there are no reviews from anyone who hasn't gone through the material.

4.8

★★★★★

100 reviews

5★

4★

3★

2★

1★

★★★★★احمد ج.·منذ 5 شهرشاهد 100٪
دورة جيدة ومُنظمة في التحليل الإحصائي باستخدام SPSS. رغم أن لدي خبرة سابقة في العمل والتدريب على البرنامج، فقد التحقت بها بهدف المراجعة المهنية والاطلاع على أسلوب عرض مختلف. استفدت من تنظيم المحتوى ووضوح الشرح، وكانت تجربة مفيدة لتحديث المعرفة وتطوير المادة التدريبية.

تم عرض كل التقييمات (1)

Course content

Statistical Analysis Using SPSS

57 lectures

Course descriptionOutlines the SPSS course in three parts: variable types, an introduction to the program with data entry and missing data, then statistical tests from descriptive analysis to logistic regression, with hands-on practice.4:16
Types of variablesExplains the types of study variables: variable versus constant, quantitative and categorical, nominal and ordinal, interval and ratio, with examples, plus dependent, independent, confounding and control variables.20:35
Introduction to SPSS Main MenusIntroduces the main SPSS menus and windows such as Data Editor, Output and Syntax, and key commands in the Edit and Data menus like inserting a variable, duplicate cases, splitting a file and selecting cases.10:34
Introduction to SPSS ToolbarIntroduces the SPSS toolbar and its icons such as undo, go to case or variable, find and replace, split file and select cases, and how to customize the toolbar by adding or removing icons.16:13
Importing Data into SPSSExplains ways to bring data into SPSS: opening a saved data file, importing from Excel, from a text file, from the sample datasets bundled with the program, or creating a new dataset.5:43
Creating a New Variable in SPSSExplains creating a new variable in Variable View and the properties of its columns such as type, width, decimals, Label, Values, Missing values and measurement level.17:18
Entering Data into SPSSExplains entering questionnaire data in Data View after defining the variables, numbering each questionnaire so it can be traced back, coding answers, and representing the five-point Likert scale with numbers.9:25
Descriptive analysis of a qualitative variableExplains descriptive analysis of nominal and ordinal categorical variables using Frequencies for counts and percentages, presenting them in a characteristics table, and the need to set the measurement level correctly.14:43
Descriptive analysis of a quantitative variableExplains descriptive analysis of quantitative variables using the mean, standard deviation, minimum and maximum, in three ways in SPSS: Descriptives, the shortcut, and Frequencies.6:12
Graphs of Qualitative VariableExplains charting categorical variables in SPSS with Chart Builder, using a pie chart for a nominal variable and a bar chart for an ordinal one, and formatting colors, fonts and data labels.8:42
Graphs of Quantitative VariableExplains charting quantitative variables in SPSS with a histogram in Chart Builder, showing the normal curve, formatting the chart, and copying it into Word.5:59
Different Graphs - ExercisesGives exercises on various SPSS charts such as pie, bar, stacked and clustered bar, histogram and frequency polygon, chosen according to the type of data and number of variables.21:34
Test of Normal DistributionExplains the normal distribution and bell curve and why parametric tests need it, how to check it in SPSS using Explore with the Kolmogorov-Smirnov and Shapiro-Wilk tests, and when to use each.10:07
Chi-Square TestExplains the chi-square test of independence between two nominal variables using Crosstabs in SPSS, interpreting the output tables and the significance value, and using Fisher's exact test when needed.10:40
Two Sample Independent T-TestExplains the independent samples t-test for comparing the mean of a quantitative variable between two categories, defining groups in SPSS, interpreting the equal variances test and significance value, and reading the direction of the difference from the means.9:52
One way ANOVAExplains One-Way ANOVA for comparing the means of three or more groups, running it in SPSS, post hoc tests such as LSD and Tukey, and presenting the results in a Word table.19:58
One sample t- testExplains the one-sample t-test for comparing a sample mean with a reference population mean, its conditions, running it in SPSS on a hemoglobin example, and interpreting the two output tables and the sign of t.6:14
Paired t- testExplains the paired t-test for comparing two measurements of the same group before and after an intervention, running it in SPSS, interpreting the output tables, and judging whether the educational program was effective.7:54
Compare meansExplains the Compare Means command in SPSS for comparing a dependent variable's means across groups, with the ANOVA table and Eta to judge the significance of differences and the effect size, and interpreting the measures of association.8:55
Pearson correlationExplains bivariate correlation, its strength and direction, and Pearson correlation between two normally distributed quantitative variables, checking normality, running it in SPSS and interpreting the correlation matrix and significance.8:01
Spearman correlationExplains Spearman's correlation as the non-parametric alternative when a variable is ordinal or normality fails, running it in SPSS on age and body mass index, and interpreting its strength, direction and significance.8:32
Kendall's TouExplains Kendall's tau correlation for two variables where one is ordinal, running it in SPSS alongside Spearman, comparing their results, and why Kendall's value comes out smaller and more conservative than Spearman's.6:18
Simple linear regressionExplains simple linear regression as an extension of correlation with one independent variable, running it in SPSS on a reading ability example, interpreting the model summary, ANOVA and coefficients tables, and using it for prediction.8:07
Assumptions of multiple linear regressionExplains the assumptions of multiple linear regression in SPSS, including linearity and multicollinearity among predictors, and reads residual plots and statistics to choose the strongest model.12:09
Multiple linear regressionExplains standard multiple linear regression in SPSS, from the correlation matrix to the ANOVA and Coefficients tables, and how to interpret each independent variable's effect on the dependent variable.8:24
Assumptions of Logistic regressionExplains the six assumptions of binary logistic regression, such as a dichotomous outcome, independent observations and no multicollinearity, and checks goodness of fit with the Hosmer-Lemeshow test.12:00
Logistic regressionExplains running binary logistic regression in SPSS on graduate-school admission data, including coding of the dependent variable, reading the Coefficients table and interpreting the effect of GPA and school prestige.12:44
ODDS ratio in logistic regressionExplains the odds ratio as an effect-size measure in logistic regression, how coding of the dependent variable affects interpretation, and how to interpret Exp(B) for scale and categorical variables.14:59
Multinomial logistic regressionExplains multinomial logistic regression when the dependent variable has three groups, choosing the reference category and interpreting each category's coefficients against it.21:01
Curve estimationExplains curve estimation in SPSS for nonlinear relationships, comparing models such as quadratic and cubic to choose the one closest to the observed data.12:53
Nonlinear regressionExplains nonlinear regression in SPSS, specifying the model expression and starting values for the parameters, and reading the iteration history, parameter estimates and R-squared.16:55
Parametric and nonparametric testsExplains the difference between parametric and nonparametric tests based on normal distribution, the causes of non-normal data and ways to handle it, and matches each parametric test with its nonparametric counterpart.11:27
Mann Whitney U-testExplains the Mann-Whitney U nonparametric test for comparing two independent groups when data are not normal, using two methods in SPSS, and how mean ranks are compared to read significance.10:16
Kruskal Wallis H testExplains the Kruskal-Wallis H test as the nonparametric alternative to ANOVA for three or more groups, reading mean ranks and significance, then pairwise comparisons to locate the differences between groups.9:15
Wilcoxon signed rank testExplains the Wilcoxon Signed Rank nonparametric test, the alternative to the one-sample t-test, for comparing a data median with a hypothesized value, running it in SPSS and reading significance and the decision.4:17
Kolmogorov Semirnov test - test for normalityExplains the Kolmogorov-Smirnov test for checking whether data are normally distributed in SPSS, via nonparametric tests and via Explore, and compares its results with the Shapiro-Wilk test.3:28
Sign testExplains the Sign test as an alternative to the paired t-test when its assumptions are violated, comparing pre- and post-intervention scores and reading positive and negative differences and significance.5:41
Using the compute command to calculate a new variableExplains using the Compute command in SPSS to calculate a new variable from existing ones, such as the difference between two measures, the average and body mass index, with naming rules for variables.9:30
Using important statistics functions from the compute commandExplains using statistical functions in the Compute command in SPSS, such as mean, median, standard deviation, sum, variance and coefficient of variation, to calculate new variables.6:53
Using important Arithmetic functions from the compute commandExplains the Arithmetic function group in the Compute command in SPSS, namely log base 10, square root and absolute value, and when they help transform data or ignore negative signs.6:04
Using the recode into different variable property to recode the variable into a new variableExplains Recode into Different Variable in SPSS to recode a numeric variable into new categories while keeping the original data, such as classifying body mass index with numbers or text.9:51
Using the recode into different variable property to recode reverse variablesExplains recoding reverse-worded items in a Likert scale using Recode into Different Variable, so all questions point the same way before checking the questionnaire's internal consistency and reliability.10:26
Using the recode into different variable property with ifExplains using Recode into Different Variable with an If condition to recode only selected cases, such as splitting scores into two groups for participants below a given age.6:00
Using the recode into same variable propertyExplains Recode into Same Variable, which recodes the variable itself without keeping the original, with a reminder to save a copy of the data, applied to reverse-worded Likert items.8:17
Using the split file propertyExplains the Split File command in SPSS, which divides the file by a variable such as specialty so each analysis runs separately per group, comparing results with and without splitting.7:32
Using the select cases propertyExplains the Select Cases command in SPSS to pick only cases that meet a condition and analyze them while excluding the rest, how it differs from Split File, and restoring All Cases afterward.8:17
Using the sort and rank cases propertiesExplains the difference between Sort Cases, which orders data ascending or descending, and Rank Cases, which creates a new variable giving each value a rank, including how tied scores are handled.7:20
Using the Weight cases propertyExplains the Weight Cases command in SPSS to weight cases by a frequency variable when data are aggregated, applied to a Crosstabs table and the chi-square test.8:26
Entry of multiple response questionsExplains entering multiple-response questions in SPSS, such as symptoms where several can be chosen, by turning each option into its own variable coded 1 or 0 instead of coding every combination.5:42
Multiple response analysisExplains analyzing multiple-response questions in SPSS by defining a variable set, then computing frequencies, response percentages and case percentages for each option.6:55
Pattern of missing dataExplains patterns of missing values in SPSS and checking whether data are missing completely at random, by computing a variable that counts missing values and comparing means between responders and non-responders.10:10
Coding of missing valuesExplains coding missing values in SPSS by assigning out-of-range values such as 999 and declaring them missing, as discrete values or a range, and the conditions for handling them, such as not exceeding a threshold.10:19
Analysis of missing values using EMExplains missing value analysis with the Estimation Maximization method in SPSS, using Little's MCAR test to see whether data are missing completely at random, reading the results and saving imputed values to a new file.8:05
Replacing missing valuesExplains replacing missing values with the Replace Missing Values command in SPSS, and its methods: series mean, mean or median of nearby points, linear interpolation and linear trend at point.9:13
Importing data from Microsoft Excel to SPSS (Part 1)Explains importing data from Excel into SPSS after coding categorical and ordinal variables as numbers within Excel so they are not read as text, then setting each variable's measurement type after import.25:42
Importing Data from Microsoft Excel to SPSS (Part Two)Explains importing data from Excel into SPSS without prior coding, so categorical variables arrive as text, then coding them inside SPSS with Recode into Different Variable while dealing with stray spaces.19:40
Importing Data from Google Forms to SPSS via ExcelExplains importing Google Forms questionnaire responses into SPSS by downloading them as Excel and then coding them, along with the pros and cons of electronic versus paper questionnaires.7:06