Search JIM Advanced Search

Journal of Chinese Integrative Medicine ›› 2007, Vol. 5 ›› Issue (1): 101-105.doi: 10.3736/jcim20070121

• Medical Statistics • Previous Articles     Next Articles

Analysis of variance of repeated data measured by water maze with SPSS

Hong Qiu1, Guo-qin Jin2, Ru-feng Jin1, Wei-kang Zhao3   

  1. 1. Department of Preventive Medicine and Medical Statistics, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China
    2. Department of of Biochemistry, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China
    3. Institute of Geriatrics, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China
  • Online:2007-01-31 Published:2007-01-21

Objective: To introduce the method of analyzing repeated data measured by water maze with SPSS 11.0, and offer a reference statistical method to clinical and basic medicine researchers who take the design of repeated measures. 

Methods: Using repeated measures and multivariate analysis of variance (ANOVA) process of the general linear model in SPSS and giving comparison among different groups and different measure time pairwise. 

Results: Firstly, Mauchly's test of sphericity should be used to judge whether there were relations among the repeatedly measured data. If any (P≤0.05), multivariate ANOVA should be taken next, or Greenhouse-Geisser corrected results should be taken. Treated effect could be evaluated by estimating between-subject variance. Repeated measurement effect or its interactive effect with treated group could be evaluated by estimating within-subject variance. The method of Bonferroni should be used to do pairwise comparisons of the repeatedly measured data in different measurement time of each treated group. With multivariate ANOVA, data in different treated group of each measurement time could be compared pairwise. 

Conclusion: The repeated measures process of the general linear model is suitable for variance analysis of repeatedly measured data. SPSS statistical package is available to fulfil this process.

Key words: analysis of variance, statistics, SPSS, linear models

CLC Number: 

  • R573

Table 1

Mauchly's test of sphericity Measure: MEASURE_1"

Within Mauchly's W Approx. df Sig. Epsilon
subject effect Chi-Square Greenhouse-Geisser Huynh-Feldt Lower-bound
Day 0.44 67.7 9 0 0.769 0.84 0.25

Table 2

Tests of within-subject effects Measure: MEASURE_1"

Source Type Ⅲ sum of squares df Mean square F Sig.
Day
Sphericity assumed 18 904.952 4 4 726.238 46 0
Greenhouse-Geisser 18 904.952 3.08 6 147.179 46 0
Huynh-Feldt 18 904.952 3.36 5 624.645 46 0
Lower-bound 18 904.952 1 18 904.952 46 0
Day×group
Sphericity assumed 1 143.810 16 71 0.7 0.792
Greenhouse-Geisser 1 143.810 12.3 93 0.7 0.753
Huynh-Feldt 1 143.810 13.4 85 0.7 0.766
Lower-bound 1 143.810 4 ## 0.7 0.593
Error (Day)
Sphericity assumed 33 826.378 332 ##
Greenhouse-Geisser 33 826.378 255 ##
Huynh-Feldt 33 826.378 279 ##
Lower-bound 33 826.378 83 ##

Table 3

Tests of between-subject effects Measure: MEASURE_1. Transformed variable: average"

Source Type Ⅲ sum of squares df Mean square F Sig.
Intercept 159 748.892 1 1 159 748.892 250 0
Group 17 446.070 4 4 361.517 6.8 0
Error 53 016.075 83 ##

Figure 1

The trend for average latency of each group during 5 days"

Table 4

Effects of Tiaoxin Recipe on spatial memory of deleterious network of oxidative damaged AD rats ($\bar{x}±S$ ,s)"

Group n Latency at different time
Day 1 Day 2 Day 3 Day 4 Day 5
Normal control 16 20.8±8.3 17.3±8.5 14.1±9.3 10.3±5.8 9.9±6.7
Sham-operation 12 30.1±12.9 19.0±7.1 16.4±8.9 10.9±5.7 8.3±5.5
Untreated 20 43.9±17.9* 33.1±23.4* 31.8±25.1* 25.9±24.3* 22.2±24.9*
Tiaoxin Recipe-treated 20 27.6±14.1 18.4±15.5 15.9±9.1 11.4±5.4 11.3±10.2
Aricept-treated 20 31.8±16.8 21.5±17.0 17.2±13.6 10.0±7.1 8.4±3.6
[1] 邱宏, 金国琴, 赵伟康 , 等. 氧化损伤类阿尔茨海默病大鼠模型的建立及调心方的作用[J]. 中国中西医结合杂志, 2003,23(8):603-605
Qiu H, Jin GQ, Zhao WK , et al. Establishment of analogous oxidative damaged Alzheimer's disease rat model and effect of Tiaoxin Recipe on it[J]. Zhongguo Zhong Xi Yi Jie He Za Zhi, 2003,23(8):603-605
[2] 胡良平 . 如何比较重复测量结果[J]. 中华预防医学杂志, 2003,37(4):293-294
Hu LP . Data analysis of repeated measurements[J]. Zhonghua Yu Fang Yi Xue Za Zhi, 2003,37(4):293-294
[3] 张文彤 . SPSS 11统计分析教程(高级篇)(第1版)[M]. 北京: 北京希望电子出版社, 2002,( 第1版):32-63
Zhang WT. Textbook of statistical analysis with SPSS 11(1st ed)[M]. Beijing: Beijing Hope Electronic Press, 2002,( 1st ed):32-63
[4] 余松林, 向惠云 . 重复测量资料分析方法与SAS程序(第1版)[M]. 北京: 科学出版社, 2004,( 第1版):1-48
Yu SL, Xiang HY. Methods of data analysis of repeated measurements and SAS(1st ed)[M]. Beijing: Science Press, 2004,( 1st ed):1-48
[1] Bellavite Paolo, Marzotto Marta, Bonafini Clara. Arnica montana experimental studies: Confounders and biases?. Journal of Integrative Medicine, 2018, 16(2): 72-76.
[2] Salvatore Chirumbolo, Geir Bjørklund. Homeopathic potencies of Arnica montana L. change gene expression in a Tamm-Horsfall protein-1 cell line in vitro model: The role of ethanol as a possible confounder and statistical bias. Journal of Integrative Medicine, 2017, 15(4): 255-264.
[3] Arthur Yin Fan. The methodology flaws in Hinman’s acupuncture clinical trial, Part II: Zelen design and effectiveness dilutions. Journal of Integrative Medicine, 2015, 13(3): 136-139.
[4] Arthur Yin Fan. The methodology flaws in Hinman’s acupuncture clinical trial, Part I: Design and results interpretation. Journal of Integrative Medicine, 2015, 13(2): 65-68.
[5] Liang-ping Hu, Xiao-lei Bao, Chen-long Lv. Two-factor designs unable to examine the interactions (Part 2). Journal of Chinese Integrative Medicine, 2012, 10(9): 966-969.
[6] Ming T. Tan , Jian-ping Liu , Lixing Lao. Adequate application of quantitative and qualitative statistic analytic methods in acupuncture clinical trials. Journal of Chinese Integrative Medicine, 2012, 10(8): 847-852.
[7] Liang-ping Hu, Xiao-lei Bao, Chen-yi Guo . Two-factor designs unable to examine the interactions (Part 1). Journal of Chinese Integrative Medicine, 2012, 10(8): 853-857.
[8] Liang-ping Hu , Xiao-lei Bao, Chen-long Lü . How to choose an appropriate experimental design type (Part 2). Journal of Chinese Integrative Medicine, 2012, 10(7): 738-742.
[9] Liang-ping Hu, Xiao-lei Bao. How to choose an appropriate experimental design type (Part 1). Journal of Chinese Integrative Medicine, 2012, 10(6): 615-618.
[10] Liang-ping Hu, Xiao-lei Bao, Qi Wang . The balance principle in scientific research. Journal of Chinese Integrative Medicine, 2012, 10(5): 504-507.
[11] Liang-ping Hu, Xiao-lei Bao, Xue Guan . Estimation of sample size and testing power (Part 7). Journal of Chinese Integrative Medicine, 2012, 10(4): 380-383.
[12] Hu Liang-ping, Bao Xiao-lei, Guan Xue, Zhou Shi-guo. Estimation of sample size and testing power (Part 6). Journal of Chinese Integrative Medicine, 2012, 10(3): 298-302.
[13] Hu Liang-ping, Bao Xiao-lei, Guan Xue, Zhou Shi-guo. Estimation of sample size and testing power (Part 5). Journal of Chinese Integrative Medicine, 2012, 10(2): 154-159.
[14] Xiao-lei Bao, Liang-ping Hu. Multifactor designs able to examine the interactions. Journal of Chinese Integrative Medicine, 2012, 10(12): 1371-1374.
[15] Liang-ping Hu, Xiao-lei Bao. Three-factor designs unable to examine the interactions (Part 2). Journal of Chinese Integrative Medicine, 2012, 10(11): 1229-1232.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] Jin-zhou Tian, Jing Shi, Xin-qing Zhang, Qi Bi, Xin Ma, Zhi-liang Wang, Xiao-bin Li, Shu-li Shen, Lin Li, Zhen-yun Wu, Li-yan Fang, Xiao-dong Zhao, Ying-chun Miao, Peng-wen Wang, Ying Ren, Jun-xiang Yin, Yong-yan Wang, Beijing United Study Group on MCI of the Capital Foundation of Medical Developments. An explanation on "guiding principles of clinical research on mild cognitive impairment (protocol)". Journal of Chinese Integrative Medicine, 2008, 6(1): 15-21
[2] Jun Hu, Jian-ping Liu. Non-invasive physical treatments for chronic/recurrent headache. Journal of Chinese Integrative Medicine, 2008, 6(1): 31
[3] Yi-ting He, Qing-lin Zha, Jian-ping Yu, Yong Tan, Cheng Lu, Ai-ping Lv. Principal factor analysis of symptoms of rheumatoid arthritis and their correlations with efficacy of traditional Chinese medicine and Western medicine. Journal of Chinese Integrative Medicine, 2008, 6(1): 32-36
[4] Jun Cai, Hua Wang, Sheng Zhou, Bin Wu, Hua-rong Song, Zheng-rong Xuan. Effect of Sijunzi Decoction and enteral nutrition on T-cell subsets and nutritional status in patients with gastric cancer after operation: A randomized controlled trial. Journal of Chinese Integrative Medicine, 2008, 6(1): 37-40
[5] Dong Yang, Yong-ping Du, Qing Shen, Wei Chen, Yan Yu, Guang-lei Chen. Expression of alpha-smooth muscle actin in renal tubulointerstitium in patients with kidney collateral stasis. Journal of Chinese Integrative Medicine, 2008, 6(1): 41-44
[6] Xue-mei Liu, Qi-fu Huang, Yun-ling Zhang, Jin-li Lou, Hong-sheng Liu, Hong Zheng. Effects of Tribulus terrestris L. saponion on apoptosis of cortical neurons induced by hypoxia-reoxygenation in rats. Journal of Chinese Integrative Medicine, 2008, 6(1): 45-50
[7] Zhi-chun Jin. Problems in establishing clinical guideline for integrated traditional Chinese and Western medicine. Journal of Chinese Integrative Medicine, 2008, 6(1): 5-8
[8] Xi Lin, Jian-ping Liu. Tai chi for treating rheumatoid arthritis. Journal of Chinese Integrative Medicine, 2008, 6(1): 82
[9] Guo-hong Yuan, Xiao-jing Pang, He-chao Ma. Synergic effects of Danggui Buxue Decoction in reducing toxicity of cytoxan in tumor-bearing mice. Journal of Chinese Integrative Medicine, 2008, 6(1): 83-88
[10] Jin-zhou Tian, Jing Shi, Xin-qing Zhang, Qi Bi, Xin Ma, Zhi-liang Wang, Xiao-bin Li, Shu-li Shen, Lin Li, Zhen-yun Wu, Li-yan Fang, Xiao-dong Zhao, Ying-chun Miao, Peng-wen Wang, Ying Ren, Jun-xiang Yin, Yong-yan Wang, Beijing United Study Group on MCI of the Capital Foundation of Medical Developments. Guiding principles of clinical research on mild cognitive impairment (protocol). Journal of Chinese Integrative Medicine, 2008, 6(1): 9-14