Parametrische und nichtparametrische Methoden der Einzelfallstatistik

  • C. Möbus
  • G. Göricke
  • P. Kröh

Zusammenfassung

Die Auswertung von zeitbezogenen Daten macht i.allg. die Anwendung spezieller statistischer Verfahren notwendig. Die Begründung hierfür liegt in der sog. „Abhängigkeit“ der Daten: Man nimmt im Gegensatz zur Querschnittuntersuchung an, daß die Daten eine gewisse „Trägheit“ oder ein „Beharrungsvermögen“ aufweisen. Diesen Effekt kann man auf physiologische Prozesse oder psychologische Ursachen wie „Erinnerungs“- und „Gewöhnungseffekte“ oder auch regelmäßig wiederkehrende äußere Einflüsse (wie z.B. regelmäßige Berufstätigkeit) zurückführen. Diese zeitliche Abhängigkeit der Daten wird auch Autokorreliertheit genannt. Die Verwendung „normaler“ statistischer Verfahren zur Analyse autokorrelierter Daten liefert verzerrte Prüfgrößen, die zu falschen Interpretationen führen.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literatur

  1. Anderson OD (1975) Time series analysis and forecasting: The Box-Jenkins approach. Butterworths, LondonGoogle Scholar
  2. Anderson TV (1978) Repeated measurements in autoregressive processes. J An Statist Assoc 73: 371–378CrossRefGoogle Scholar
  3. Aström KJ, Bohlin T (1966) Numerical identification of linear dynamic systems from normal operating records. In: Hammond PH (ed) Theory of self-adaptive control systems. Plenum, New YorkGoogle Scholar
  4. Bartlett MS (1946) On the theoretical specifications of the sampling properties of autocorrelated time series. J R Statist Soc B. 8: 27–41Google Scholar
  5. Box GEP, Pierce DA (1970) Distribution of residual autocorrelations in ARIMA time series models. J Am Statist Assoc. 64: 1509–1526CrossRefGoogle Scholar
  6. Box GEP, Tiao GC (1965) A change in level of a non-stationary time-series. Biometrika. 52: 181–192Google Scholar
  7. Box GEP, Tiao GC (1975) Intervention analysis with applications to economic and environmental problems. J Am Statist Assoc. 70: 70–79CrossRefGoogle Scholar
  8. Chatfield C (1975) The analysis of time-series: Theory and practice. Chapman & Hall, LondonGoogle Scholar
  9. Cook TD, Campbell DT (1979) Quasi-experiments: Nonequivalent control groups designs. In: Cook TD, Campbell TD (eds) Quasi-experimentation: Design and analysis issues for field settings. McNally, Chicago, pp 95–146Google Scholar
  10. Cooley WW, Lohnes PR (1971) Multivariate data analysis. Wiley & Sons, New YorkGoogle Scholar
  11. Edgington ES (1967) Statistical inference from N = 1 experiments. J Psychol. 65: 195–199Google Scholar
  12. Edgington ES (1969a) Statistical inference: The distribution free approach. McGraw-Hill, New YorkGoogle Scholar
  13. Edgington ES (1969b) Approximate randomization tests. J Psychol. 72: 143–149Google Scholar
  14. Edgington ES (1971) Randomization tests with statistical control over concomitant variables. J Psychol. 79: 13–19CrossRefGoogle Scholar
  15. Edgington ES (1973) Randomization tests: Computer time requirements. J Psychol. 85: 89–95CrossRefGoogle Scholar
  16. Edgington ES (1975a) Randomization tests for one-subject operant experiments. J Psychol. 90: 57–68CrossRefGoogle Scholar
  17. Edgington ES (1975b) Randomization for predicted trends. Can Psychol Rev. 16: 49–53Google Scholar
  18. Edgington ES (1980) Randomization tests. Dekker, New York Fisher RA ( 1951 ) The design of experiments. Hafner, LondonGoogle Scholar
  19. Glass GV, Willson UL, Gottman JM (1975) Design and analysis of time-series experiments. Colorado Associated University Press, BoulderGoogle Scholar
  20. Gottman JM (1981) Time-series analysis. Cambridge University Press, CambridgeGoogle Scholar
  21. Gottman JM, Glass GV (1978) Analysis of interrupted time-series experiments. In: Kratochwill TR (ed) Single subject research: Stra-tegies for evaluating change. Academic Press, New York, pp 197–235Google Scholar
  22. Hibbs DA (1977) On analyzing the effects of policy interventions: BOX-JENKINS and BOX-TIAO vs. structural equation models. In: Heise DR (ed) Sociological methodology. Jossey-Bass, New York, pp 137–179Google Scholar
  23. Holtzman WH (1963) Statistical models for the study of change in the single case. In Harris C (ed) Problems in measuring change. University of Wisconsin Press, Madison WisconsinGoogle Scholar
  24. Jenkins GM (1979) Practical experiences with modelling and fore-casting time series. GJP Ltd., Channel IslandGoogle Scholar
  25. Lehman EL (1975) Nonparametrics: Statistical methods based on ranks. Holden-Day, San FranciscoGoogle Scholar
  26. Levin JR,. Marascuilo LA, Hubert LJ (1978) N = 1–Nonparametric randomization tests. In: Kratochwill TR (ed) Single subject research. Academic Press, New York, pp 167–196Google Scholar
  27. Makridakis S, Wheelwright SC (1978a) Forecasting - methods and applications. Wiley & Sons, New YorkGoogle Scholar
  28. Makridakis S, Wheelwright SC (1978b) Interactive forecasting.Holden-Day, San FranciscoGoogle Scholar
  29. McCain LJ, McCleary R (1979) The statistical analysis of the simple interrupted time-series quasi-experiment. In: Cook TDGoogle Scholar
  30. Campbell DT (eds) Quasi-experimentation: Design and analysis for field settings. McNally, Chicago, pp 233–293Google Scholar
  31. McCleary R, Hay RA (1980) Applied time-series analysis for the social sciences. Sage, Beverly HillsGoogle Scholar
  32. Möbus C, Nagl W (1983) Messung, Analyse und Prognose von Veränderun-gen. In: Bredenkamp J, Feger H (Hrsg) Hypothesenprüfung, Bd 5 der Serie Forschungsmethoden der Psychologie der Enzyklopädie der Psychologie. Verlag für Psychologie, Göttingen, S 239–470Google Scholar
  33. Möbus C, Göricke G, Kröh PA (1983) Statistical analysis of single-case experimental designs: Conditional equivalence of the general-linear-model approach of Glass, Willson and Gottman with the intervention model of Box and Tiao. EDV in Med Biol. 14: 98–108Google Scholar
  34. Nelson CR (1973) Applied time-series analysis. Holden-Day, San FranciscoGoogle Scholar
  35. Quenouille MH (1949) Approximate tests of correlation in time series. J R Statist Soc B. 11: 68–74Google Scholar
  36. Revenstorf D (1979) Zeitreihenanalyse für klinische Daten: Methodik und Anwendungen. Beltz, WeinheimGoogle Scholar
  37. Revenstorf D, Keeser W (1979) Zeitreihenanalyse von Therapieverläu-fen. In: Petermann F, Hehl FJ (Hrsg) Einzelfallanalyse. Urban & Schwarzenberg, München, S 183–228Google Scholar
  38. Schneeweiß H (1974) Ökonometrie, 2. Aufl. Physica, Würzburg WienGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1985

Authors and Affiliations

  • C. Möbus
  • G. Göricke
  • P. Kröh

There are no affiliations available

Personalised recommendations