- 在线播放
- 分集下载
- 0.1 Course introduction (14.22)
- 1.1 Experimental research - Example 1 Polio vaccine (11.17)
- 1.2 Experimental research - Example 2 Memory training (16.21)
- 1.3 Experimental research - Example 3 The concept of random (6.27)
- 2.1 Correlational research - Example 1 Personality (9.07)
- 2.2 Correlational research - Example 2 Intelligence (9.09)
- 2.3 Correlational research - Example 3 Sports-related concussion (11.24)
- 3.1 Variables and distributions - Types of variables (14.53)_x264
- 3.2 Variables and distributions - Distributions_Histograms (22_39)_x264
- 3.3 Variables and distributions - Scales of measurement (6.46)_x264
- 4.1 Summary statistics - Measures of central tendency (15.22)_x264
- 4.2 Summary statistics - Measures of variability (17.01)_x264
- 5.1 Correlation - Overview (15.58)_x264
- 5.2 Correlation - Calculation of R (15.29)_x264
- 5.3 Correlation - Assumptions (12.13)_x264
- 6.1 Measurement - Reliability (14.31)
- 6.2 Measurement - Validity (9.50)
- 6.3 Measurement - Sampling (11.03)
- 7.1 Introduction to regression - Overview (19.02)
- 7.2 Introduction to regression - Calculation of regression coefficients (8.22)
- 7.3 Introduction to regression - Assumptions (7.34)
- 8.1 Null Hypothesis Significance Tests (NHST) - Overview (17.05)
- 8.2 Null Hypothesis Significance Tests (NHST) - Problems & remedies (15.55)
- 9.1 Central limit theorem - Sampling distributions (11.51)
- 9.2 Central limit theorem - The central limit theorem (14.16)
- 10.1 Confidence intervals - Confidence intervals for sample means (18.19)
- 10.2 Confidence intervals - Confidence intervals for regression coefficients (10
- 11.1 Multiple regression - Multiple regression (15.28)
- 11.2 Multiple regression - Matrix algebra (14.50)
- 11.3 Multiple regression - Estimation of coefficients (9.34)
- 12.1 Multiple regression continued - The general linear model (7.55)
- 12.2 Multiple regression continued - Dummy coding (12.24)
- 13.1 Moderation - Example 1 (27.13)
- 13.2 Moderation - Centering predictors (15.15)
- 13.3 Moderation - Example 2 (6.44)
- 14.1 Mediation - Standard approach (18.33)
- 14.2 Mediation - Path analysis (14.41)
- 15.1 Group comparisons (t-tests) - Introduction (14.12)
- 15.2 Group comparisons (t-tests) - Dependent t-tests (12.48)
- 15.3 Group comparisons (t-tests) - Independent t-tests (18.50)
- 16.1 Group comparisons (ANOVA) - One-way ANOVA (22.17)
- 16.2 Group comparisons (ANOVA) - Post-hoc tests (7.35)
- 17.1 Factorial ANOVA - Factorial ANOVA (16.37)
- 17.2 Factorial ANOVA - Example (8.43)
- 18.1 Repeated measures ANOVA - Repeated measures_ Pros and cons (21.33)
- 18.2 Repeated measures ANOVA - Repeated measures ANOVA example (11.36)
- 19.1 Chi-square - Chi-square goodness of fit (11.27)
- 19.2 Chi-square - Chi-square test of independence (10.07)
- 20.1 Binary logistic regression - Overview (12.15)
- 20.2 Binary logistic regression - Example (11.57)
- 21.1 Assumptions revisited (correlation and regression) - Assumptions (12.36)
- 21.2 Assumptions revisited (correlation and regression) - Transformations (6.37)
- 22.1 Generalized Linear Model - Parametric vs. non-parametric statistics (10.22)
- 22.2 Generalized Linear Model - Examples (14.28)
- 23.1 Assumptions revisited (t-tests and ANOVA) - Overview (8.32)
- 23.2 Assumptions revisited (t-tests and ANOVA) - Examples (10.21)
- 24.1 Non-parametrics - Research methods and descriptive statistics (5.32)
- 24.2 Non-parametrics - Simple and multiple regression (7.42)
- 24.3 Non-parametrics - Group comparisons t-tests and ANOVA (5.52)
- 24.4 Non-parametrics - Procedures for non-normal distributions and non-linear mo
- 25.1 Lab 1 - Introduction to R (12.03)
- 25.2 Lab 2 - Histograms and summary statistics (37.04)
- 25.3 Lab 3 - Scatterplots and correlations (20.46)
- 25.4 Lab 4 - Regression (28.33)
- 25.5 Lab 5 - Confidence intervals (30.10)
- 25.6 Lab 6 - Multiple regression (21.45)
- 25.7 Lab 7 - Moderation and mediation (15.48)
- 25.8 Lab 8 - Group comparisons (18.18)
- 25.9 Lab 9 - Factorial ANOVA (12.16)
- 25.10 Lab 10 - Binary logistic regression (18_56)
统计学的相关介绍
《统计学》热门公开课 - Statistics One - by Prof. Andrew Conway @ Coursera https://www.youtube.com/playlist?list=PL5F2bE5w-jK1SyQnU4qMu1dWBUxmmhu3b
统计学是一门综合性科学,它主要通过搜索、整理、分析数据等手段来达到推断所测对象的本质的目的。统计学往往对我们研究实际问题有很大的帮助,下面我们就来了解一下。
统计学的中心问题就是如何根据样本去探求有关总体的真实情况。因此,如何从一个总体中抽取一些元素组成样本,什么样的样本最能代表总体,这直接影响着统计的准确性。如果抽取元素的方法是使总体中的元素成分不改,所观测到的数值是互相独立的随机变量,并有着和总体一样的分布,这样的样本是一个简单的随机样本,它是总体的最好代表,而取得简单随机样本的过程叫做简单随机取样。
简单随机取样就是重复进行同一随机试验,也就是指每次试验都在同一组条件下进行,因而每次试验得到什么结果,其可能程度都是固定不变的。对于有限总体,简单随机抽样意味着每次抽出一个元素后,放还再抽,若不放还,总体的成分将有所改变,那么再抽时,出现各种结果的可能程度就相对地改变了。至于无限总体则没有区分“放回”或“不放回”的必要。
除以上述原则外,另一方面,获得样本的具体方法能否保证观察值是独立的,这是问题的关键,因此,一样本的随机与否还取决于获得样本的具体方法。
在具体进行取样时,必须根据研究目的的不同,选择不同的取样方法。
①单纯随机取样法先把每个个体编号,然后用抽签的方式从总体中抽取样本。这种方法适用于个体间差异较小、所需抽选的个体数较少或个体的分布比较集中的研究对象。
②分区随机取样法将总体随机地分成若干部分,然后再从每一部分随机抽选若干个体组成样本。这种抽样法可以更有组织地进行,而且中选的个体在总体的分布比单纯随机取样更均匀。
③系统取样法先有系统地将总体分成若干组,然后随机地从第一组决定一个起点,如每组15个元素,决定从第一组的第13个元素选起,那么以后选定的单位即28,43,58,73等等。
④分层取样法根据对总体特性的了解,把总体分成若干层次或类型组,然后从各个层次中按一定比例随机抽选。这种方法的代表性好,但若层次划分得不正确,也不能获得有高度代表性的样本。