Introduction to Quantitative Methods in Social Sciences - YBLS021
|
|
|
||
|
This course provides a hands-on introduction to quantitative research methods and statistical analysis in the social sciences. Students will learn the strengths and weaknesses of different research designs, common sources of bias, and strategies to minimize them. The core focus is on describing data, testing hypotheses, selecting appropriate statistical tests based on the research question, study design, and data type, and correctly interpreting and reporting the results. Students will use the free statistical software JASP to perform analyses and answer hypothetical research questions. By the end of the course, students will acquire the conceptual understanding and practical skills needed to conduct their own quantitative research and to critically evaluate published research findings.
Week 1: Lecture 1: Course overview and review of research designs
• Literature: Chapters 1 and 2, Navarro et al., 2019
• Assignment: Homework #1
• Learning objectives:
o Understand the course expectations and ensure that JASP is installed before the next class.
o Compare qualitative and quantitative research methods and explain their relative advantages and disadvantages.
o Describe different types of research methods (experiments, quasi-experiments, observational/correlational research, longitudinal vs. cross-sectional research) and compare the strengths and weakness.
o Distinguish between a sample and a population.
o Distinguish between variables and constants. Describe and identify different types of variables (dependent variables, independent variables, manipulated variables, confounding variables)
o Be able to read a description of a study and identify the type of research, its hypothesis, the variables in the study, and how the constructs were operationalized.
o Explain what validity and reliability are. Specifically, the different types of validity (face validity, construct validity, criterion-related validity
o Understand basic threats to validity in research (confounding variables, expectancy effects, carry-over effects) and how to mitigate against them.
Week 2: Lecture 2: Organizing research data and describing distributions
• Literature: Chapters 3, 4 and 5, Navarro et al., 2019, Instructor handout on skewness and kurtosis (posted on Moodle section for this lecture)
• Homework: Homework #2
• Learning objectives:
o Compare the different levels of measurement (nominal categorical data, ordinal categorical data, ratio data, interval data). Give three examples of each.
o Load data into JASP and set the variables appropriately.
o Export JASP results as a PDF file.
o Explain the objective of descriptive statistics.
o Compare the different measures of central tendency (mean, medium, and mode). Contrast their strengths and weaknesses and the level of measurement they are suitable for. Calculate the mean, medium and mode by and hand, and by using JASP.
o Compare the different measures of variability (sum of squares, standard deviation, variance, interquartile range). Calculate the sum of squares, standard deviation and variance by hand. Calculate the measures of variability in JASP. Explain the relationship between sum of squares, standard deviation and variance.
o Calculate descriptive statistics in JASP for specific groups separately.
o Explain how and why bias correction needs to be applied when calculated
o Explain the importance of normal distributions to statistical analyses in the social sciences.
o Draw a dataset that is normal, positively skewed, negatively skewed, platykurtic, or leptokurtic.
o Calculate and interpret percentiles and quartiles.
o Create and interpret boxplots with JASP. Explain what the components of the boxplot mean.
o In JASP, use histograms, Q-Q plots, the Shapiro-Wilk test, and compute kurtosis and skewness (and their standard errors) to analyze whether data are normally distributed or not.
Week 3: Lecture 3: Probability and estimation of population parameters
• Literature: Chapters 6 and 7, Navarro et al., 2019
• Assignment: Homework #3
• Learning objectives (Probability):
o Know the range of probability (0 to 1).
o Compare the frequentist and Bayesian view on probability.
o Define elementary events and describe how they relate to a sample space.
o Define the law of large numbers.
o Describe the parameters that effect the shape of the binomial distribution (the size parameter N, the random variable X and theta). In an example of a coin experiment or dice experiment, you should be able to identify the appropriate value of N, X and theta, and be able to determine the probability of a specific event based upon a graph of the binomial distribution.
o Give an example of a discrete distribution and four examples of continuous distributions.
o Remember the normal, chi-square, t, and F probability distributions as they will be used to perform hypothesis testing later in the course. Explain how their shapes change depending on the mean, standard deviation (normal distribution) or degrees of freedom.
o Explain the relationship between probability density and continuous probability. Explain the implications for determining probability in continuous probability distributions.
o Describe what p-hacking is, its negative impact on research and how to avoid it.
• Learning objectives (Estimation of population parameters)
o Distinguish the objectives of descriptive statistics from inferential statistics.
o Explain the importance of sampling to inferential statistics and how bad sampling can affect the quality the analysis. Specifically, how sampling impacts the generalizability and validity of a study.
o Define different samplings methods (simple random sampling with and without replacement, stratified random sampling, convenience sampling, and snowball sampling). Compare the advantages and disadvantages.
o Define what a sampling distribution is and the types of values that can have a sampling distribution. Define what sampling error is.
o Describe the central limit theorem and how it relates to the sampling distribution of the mean.
o Use the 3-sigma rule to determine the percentage of normally distributed scores that fall within a certain number of standard deviations of the mean.
o Calculate and interpret the standard error of the mean and confidence intervals. Understand how they relate to errors bars in a graph and interpret what it means when error bars overlap.
Week 4: Lecture 4: Hypothesis testing
• Literature: Chapter 8, Navarro et al., 2019
• Assignment: Homework #4
• Learning objectives:
o Explain what a hypothesis is and identify whether a hypothesis is good or bad (based on its falsifiability and simplicity). Understand the significance of hypothesis testing to the development of scientific theories.
o Describe the process of how hypotheses are generally formed in science.
o Distinguish between a research hypothesis and statistical hypothesis.
o Explain the different types of statistical hypotheses (the null hypothesis vs. the alternate hypothesis). Understand how statistical tests generally provide evidence for our research hypothesis not by confirming the alternate hypothesis but rather by rejecting the null hypothesis.
o Define Type I (alpha) and Type II (beta) error and what the standard acceptable limits are (alpha < .05, beta < .20).
o Explain what statistical significance is, how it is quantified by p-values, and use p-values to decide whether to reject or retain the null hypothesis. Explain how statistical significance does not guarantee importance or clinically significance, and the importance of considering effect size.
o Explain what statistical power is, how it relates to Type II error and statistical significance, and the factors that influence power.
o Explain how test statistics, their samplings distributions under the null are used to test hypotheses.
o Explain the relationship between critical regions and p-values, and how they relate to the shape of the sampling distribution.
o Compare one-sided (one-tailed) tests and two-sided (two-tailed tests).
Week 5: Lecture 5: Categorical data analysis
• Literature: Chapter 9 in Navarro et al., 2019, instructor handout on chi-square tests, video demonstrations of chi-square test of independence and goodness of fit (posted on Moodle section for this lecture)
• Assignment: Homework #5
• Learning objectives:
o Select the appropriate type of Chi-square test (goodness-of-fit test, test of independence) for a given research requestion.
o Use contingency tables to analyze the association between categorical variables
o For both the Chi-square goodness-of-fit test and Chi-square test of independence
Describe the purpose of the specific test, the null hypothesis and whether the test is one or two tailed.
Understand the research designs that support Chi-square tests of independence
Give an example of a study where the specific test is applied.
Explain the relationship between the Chi-square statistic and the difference between the observed and expected frequencies of the different categories.
Using data from mock studies, use JASP to conduct the test and interpret the results (both in terms of the statistical hypothesis and research question).
Calculate the degrees of freedom by hand.
Identify the test statistic and the sampling distribution of the test statistic under the null. Explain how the shape of the distribution (and consequently the critical region) changes depending on the degrees of freedom and how that affects statistical significance.
Name the factors that impact the statistical significance of the tests (magnitude of the test statistics, the number of categories/the number of rows/columns, degrees of freedom)
Calculate and interpret the effect size using JASP.
Name the assumptions of each test, describe the consequence of violating the assumption, and describe steps that can be taken if certain assumptions are violated.
Week 6: Lecture 6: Comparing two means
• Literature: Chapter 10, Navarro et al., 2019.
• Assignment: Homework #6
• Learning objectives:
o For the one-sample z-test, one-sample t-test, independent groups t-test, Welch's t-test, Mann-Whitney U test, dependent (paired-samples) t-test, and Wilcoxon signed-rank test
Describe the purpose of the specific test, the null hypothesis, and describe the difference between a one-tailed and two-tailed test.
Understand which research designs support the different types of tests. Give an example of a study where the specific test is applied.
For the parametric tests, explain how the test statistic (z and t) are calculated. It is unnecessary to memorize formulas, but you should understand the test statistic as a ratio between the magnitude of the difference and the standard error of the difference.
Identify which test to use for a specific circumstance.
For non-parametric tests, understand how they are based on ranks instead of raw values.
Using data from mock studies, use JASP to conduct the test and interpret the results (both in terms of the statistical hypothesis and research question).
Calculate the degrees of freedom by hand (if the test has degrees of freedom)
Identify the test statistic, the sampling distribution of the test statistic under the null. For parametric tests, explain how the shape of the distribution (and consequently the critical region) changes depending on the degrees of freedom and how that affects statistical significance.
Explain how factors impact the significance of test (the standard error, the magnitude of then difference, number of subjects, degrees of freedom)
Calculate and interpret the effect size using JASP.
Identify the type of data (level of measurement) that are suitable for the test. Name the assumptions of each test, explain the consequences of violating those assumptions. Explain how to determine if the assumptions are met and conduct the relevant tests of assumptions in JASP. If certain assumptions are violated, use appropriate alternative test that should be used certain assumptions are violated (e.g. a one sample t-test instead of the z-test, Welch's test, Mann-Whitney U test, Wilcoxon signed-rank test).
Report the results providing the appropriate information.
Week 7: MIDTERM TEST #1 (covers Lectures 1 through 6)
Week 8: Lecture 7: Correlation
• Literature: Chapter 11 (Sections 1.1 and 1.2), Navarro et al., 2019.
• Assignment: Homework #
• Learning objectives:
o Explain how covariance and correlation can be used to determine the magnitude and direction of a relationship between two variables. Describe relationship between variance, covariance, and correlation and compare covariance to correlation.
o Describe either visually or verbally the difference between a linear and non-linear relationship.
o Explain the importance of visualizing associations with scatterplots between variables. Create a scatter plot in JASP.
o Compare Pearson's product-moment correlation, Spearman's rank correlation and Kendall's tau. Identify the level of measurement they are appropriate for and explain under what conditions you would use each test. Name their assumptions, explain the consequences of violating those assumptions. Explain how to determine if the assumptions are met and conduct the relevant tests of assumptions in JASP.
o Understand which research designs support the different types of correlations. Give an example of a study where the specific test is applied.
o Understand that r is its own measure of effect size and determine if r is small, medium or large.
o Test hypotheses about correlation. Specify the null hypothesis, the test statistic and the sampling distribution under the null. Explain how the shape of the distribution (and consequently the critical region) changes depending on the degrees of freedom and how that affects statistical significance.
o Explain how factors impact the significance of test (the standard error, the magnitude of r, number of subjects, degrees of freedom).
o Compute by hand and interpret the coefficient of determination (R2). Understand that the computation and interpretation differ between correlation and regression.
o Using data from mock studies, use JASP to conduct the appropriate correlational analyses and interpret the results (both in terms of the statistical hypothesis and research question). Report the results providing the appropriate information.
Week 9: Lecture 8: Regression
• Literature: Chapter 11 (Sections 1.3 to 1.9), Navarro et al., 2019.
• Assignment: Homework #8
• Learning objectives:
o Explain what a statistical model is and use the mean as an example.
o Explain how linear regression can be used to determine the direction and magnitude of the association between two variables. Explain the difference between the dependent variable and the independent variables in terms of their conceptual relationship and the type of data that they can be.
o Compare multiple regression to simple regression and correlation. Describe the advantages of multiple regression over simple regression and correlation.
o Know the formula of the regression and explain the components (the slope, intercept and residuals). Explain how the residuals are calculated.
o Describe how regression can be used to predict both observed and unobserved data. Explain how to calculate the regression line (line of best fit).
o Explain how variance is partitioned in regression. Compare and relate the sum of squares total, the sum of squares regression and the sum of squares error. Explain how each are calculated. Use this information to calculate the coefficient of determination (R2). Interpret the R2 and what it means for model fit.
o Discuss why one would use the adjusted R2 as opposed to the regular R2.
o Explain how ordinary least squares estimates the regression coefficients.
o Interpret the raw and standardized regression slopes. Using JASP, conduct hypothesis tests on regression slopes. Specify the null hypothesis, the test statistic and the sampling distribution under the null. Explain how the shape of the distribution (and consequently the critical region) changes depending on the degrees of freedom and how that affects statistical significance. Note the similarity with hypothesis tests for correlations.
o Explain how factors impact the significance of test (the standard error of the regression slope, the standard error of the regression, the magnitude of the slope, number of subjects, the number of predictors, multicollinearity, degrees of freedom)
o Describe the assumptions of linear regression, and what happens when they are violated. Explain how to determine if the assumptions are met and conduct the relevant tests of assumptions in JASP.
o Understand what types of research designs are optimal for regression.
o Using data from mock studies, use JASP to conduct multiple linear regressions, and interpret the results (both in terms of the statistical hypothesis and research question). Report the results providing the appropriate information.
Week 10: Lecture 9: One-way analysis of variance
• Literature: Chapter 12, Navarro et al., 2019.
• Assignment: Homework #9
• Learning objectives:
o When one wishes to compare more than two means, using the concept of family wise error, explain the problems of conducting many statistical tests (comparing multiple pairs of means), and why it is better to perform an ANOVA first as an omnibus test.
o Describe the conditions where a one-way ANOVA might be used (i.e. the level of measurement and number of independent variables, the minimum number of groups).
o For both the independent groups (between-subjects) ANOVA, the repeated measures (within-subjects) ANOVA, the Kruskal-Wallis test and Friedman's test:
Identify which test to use for a specific circumstance (e.g., the level of measurement of the dependent variable). Give an example of a study where the specific test is applied.
Describe the purpose of the specific test, the null hypothesis, and whether the test is one-tailed and two-tailed test.
For parametric tests, explain how the ANOVA partitions the variance (sum of squares) in the dependent variable in terms of different sources (e.g., between groups/conditions, between subjects, unexplained variance) Understand the logic for how the different types of sum of squares are calculated.
• Calculate the degrees of freedom for each source of variance by hand. Use the sum of squares and degrees of freedom to calculate the mean square.
• Calculate the F-ratio. Interpret the F-ratio in terms of the variance explained between groups (or between conditions) relative to the error variance.
• Identify the test statistic (F-ratio) and the sampling distribution of the test statistic under the null. Define the null hypothesis and whether the hypothesis is one or two tailed. explain how the shape of the distribution (and consequently the critical region) changes depending on the degrees of freedom and how that affects statistical significance.
• Explain how factors impact the significance of test (the magnitude of difference between the groups, the variability within groups, the degrees of freedom, the number of subjects, the number of groups/conditions)
For non-parametric tests, understand how they are based on ranks instead of raw values.
Using data from mock studies, use JASP to conduct the test and interpret the results (both in terms of the statistical hypothesis and research question).
Calculate and interpret the effect size using JASP.
Name the assumptions of each test, explain the consequences of violating those assumptions. Explain how to determine if the assumptions are met and conduct the relevant tests of assumptions in JASP. If certain assumptions are violated, use appropriate alternative test that should be used certain assumptions are violated (Kruskal-Wallis test, Friedman's test, Welch or Brown-Forsythe correction).
Explain the function of post-hoc pairwise comparisons and when they are performed.
Correct for family wise error when doing post-hoc comparisons. Compare the different types of corrections (Tukey's, Bonferroni, Holm, Conover and Dunn) in terms of their conservativeness and when they might be performed. Conduct the tests in JASP, and interpret and report the results.
Report the results providing the appropriate information.
Week 11: Lecture 10: Factorial n-way analysis of variance
• Literature: Chapter 13, Navarro et al., 2019.
• Assignment: Homework #10
• Learning objectives:
o Compare a one-way ANOVA with factorial n-way ANOVA. Explain the advantages of a factorial n-way ANOVA.
o Explain the basic components of a factorial design (e.g., factors cross-one another, minimum number of levels per factor)
o Determine if a design is balanced or not and explain the implications.
o Explain the difference between independent groups, repeated measures, and mixed designs. Give an example of each (think of hypothetical studies).
o Identify whether a factor is fixed or random, and whether it is a treatment or classification factor.
o Distinguish between rows, columns and cells. Define marginal mean and grand mean and explain how they are calculated.
o Explain the different types of interactions (moderation). Determine whether two variables interact graphically.
o Explain how variance is partitioned in an n-way factorial ANOVA. Understand the difference between the main effects and an interaction and that they each have their own F-ratio. Determine the number of main effects and interactions based upon a description of the research design.
o Describe the null hypothesis when testing for significant main effects and interactions (it is not necessary to know the formula for interactions).
o Using data from mock studies, use JASP to conduct an n-way factorial ANOVA and relevant post hoc tests and interpret the results (both in terms of the statistical hypothesis and research question).
o Based on the results of the ANOVA, determine which groups to perform pairwise post-hoc tests (with the appropriate adjustment for family wise error)
o Interpret and calculate the effect sizes for terms in a factorial n-way ANOVA. Compare eta-squared and partial eta-squared.
o Name the assumptions of factorial n-way ANOVA explain the consequences of violating those assumptions. Explain how to determine if the assumptions are met and conduct the relevant tests of assumptions in JASP.
o Conduct and interpret the results of a test of simple main effects. Explain when you would use this test and the benefits.
o Create plots of marginal means and cell means to visualize group differences.
o Using data from mock studies, use JASP to conduct the ANOVA and the suitable follow-up tests and interpret the results (both in terms of the statistical hypothesis and research question).
Extension of introduction to research methods for AAU
• Required reading: instructor handout
• Assignment: Homework 11
• Learning objectives:
o Understand what it means to conduct ethical research in psychology (approval from research ethics boards, informed consent, confidentiality and data security, balancing risks with benefits, debriefing, adjustments for special populations)
o Identify common bad research practices (e.g., p-hacking, post-hoc theorizing) and how they relate to the replication crisis in psychological research
o Explain ways of avoiding bad research practices and maximizing transparency (e.g., pre-registration of hypotheses, publishing data and analysis codes to open science platforms)
Last update: Zakreski Ellen, Ph.D. (01.09.2026)
|
|
||
|
All course materials, homework instructions, datasets, grades, and feedback are available on Moodle. 1) Attendance (5%)
2) Students must submit 10 weekly homework assignments (20%)
3) Two midterm tests and one final test will be held during regular class time.
Grading:
AI Policy: The use of large language models (e.g., ChatGPT, Grok, or similar) is prohibited for completing homework assignments. During tests, no electronic devices, notes, or books are allowed. Use of general large language models is not recommended for study purposes as the information may be inaccurate. The textbook, lecture slides, and Moodle materials contain all required information. Students are encouraged to contact the instructor for study support. Last update: Horáčková Karolína, Mgr. (25.08.2026)
|
|
||
|
1) Course Overview and Review of Research Designs
2) Organizing Research Data and Describing Distributions
3) Probability and Estimation of Population Parameters
4) Hypothesis Testing
5) Categorical Data Analysis
6) Comparing Two Means
7) Midterm Test #1 (covers Lectures 1–6) 8) Correlation
9) Regression
10) One-Way Analysis of Variance
11) Factorial (n-way) Analysis of Variance
12) Final Test (covers the entire course) Last update: Horáčková Karolína, Mgr. (25.08.2026)
|
|
||
|
Navarro, D., Foxcroft, D., & Faulkenberry, T. J. (2019). Learning Statistics with JASP:A Tutorial for Psychology Students and Other Beginners Moodle: https://dl1.cuni.cz/course/view.php?id=18294 Last update: Horáčková Karolína, Mgr. (25.08.2026)
|
|
||
|
Students must have access to a computer where they can install and run the latest version of JASP (free at https://jasp-stats.org/download/). Completion of an Introduction to Research Methods course is strongly recommended. Last update: Horáčková Karolína, Mgr. (25.08.2026)
|