A comparative simulation study of AR(1) estimators in short time series
Open accessAbstract
Various estimators of the autoregressive model exist. We compare their performance in estimating the autocorrelation in short time series. In Study 1, under correct model specification, we compare the frequentist r 1 estimator, C-statistic, ordinary least squares estimator (OLS) and maximum likelihood estimator (MLE), and a Bayesian method, considering flat (Bf) and symmetrized reference (Bsr) priors. In a completely crossed experimental design we vary lengths of time series (i.e., T = 10, 25, 40, 50 and 100) and autocorrelation (from −0.90 to 0.90 with steps of 0.10). The results show a lowest bias for the Bsr, and a lowest variability for r 1. The power in different conditions is highest for Bsr and OLS. For T = 10, the absolute performance of all measurements is poor, as expected. In Study 2, we study robustness of the methods through misspecification by generating the data according to an ARMA(1,1) model, but still analysing the data with an AR(1) model. We use the two methods with the lowest bias for this study, i.e., Bsr and MLE. The bias gets larger when the non-modelled moving average parameter becomes larger. Both the variability and power show dependency on the non-modelled parameter. The differences between the two estimation methods are negligible for all measurements.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The data collection reached a saturation point after the eighth interview of each man and each woman in the three religious groups, as no new shared themes were generated.
“after the eighth interview (of each man and each woman in the three religious groups) no new shared themes were generated from the interviews. Therefore, it was deemed that the data collection had reached a saturation point”
From The gendered experience with respect to health-seeking behaviour in an urban slum of Kolkata, India (2018) · cites this paper as [38]
The Research design and Discussion passages describe simulations of AR(1) estimators, not qualitative interviews. Searches for the eighth interview, religious groups, shared themes, and data saturation found no passage addressing the claim. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
No references could be resolved yet.
Research works printed but not linked: 22
- Arnau J Bono R Autocorrelation and bias in short time series: an alternative estimator Qual. Quant. 2001 35 4 365 387 10.1023/A:1012223430234 · DOI
- Berger JO Yang RY Noninformative priors and Bayesian testing for the AR(1) model Econ. Theory 1994 10 461 482 10.1017/S026646660000863X · DOI
- Byrd RH Lu P Nocedal J Zhu C A limited memory algorithm for bound constrained optimization SIAM J. Sci. Comput. 1995 16 5 1190 1208 10.1137/0916069 · DOI
- Cox DD Llatas I Maximum likelihood type estimation for nearly nonstationary autoregressive time series Ann. Stat. 1991 19 3 1109 1128 10.1214/aos/1176348240 · DOI
- DeCarlo LT Tryon WW Estimating and testing autocorrelation with small samples: a comparison of the C-statistic to a modified estimator Behav. Res. Ther. 1993 31 8 781 788 10.1016/0005-7967(93)90009-J 8257410 · DOI
- Durbin J Koopman S Time Series Analysis by State Space Models 2012 Oxford Oxford University Press
- Garcia-Hiernaux A Casals J Jerez M Fast estimation methods for time-series models in state-space form J. Stat. Comput. Simul. 2009 79 2 121 134 10.1080/00949650701617249 · DOI
- Gelman A Rubin DB Inference from iterative simulation using multiple sequences Stat. Sci. 1992 7 4 457 472 10.1214/ss/1177011136 · DOI · Paper page
- Huitema BE McKean JW Autocorrelation estimation and inference with small samples Psychol. Bull. 1991 110 2 291 304 10.1037/0033-2909.110.2.291 · DOI
- Huitema BE McKean JW Reduced bias autocorrelation estimation: three jackknife methods Educ. Psychol. Meas. 1994 54 3 654 10.1177/0013164494054003008 · DOI
- Kunitomo N Yamamoto T Properties of predictors in misspecified autoregressive time series models J. Am. Stat. Assoc. 1985 80 392 941 10.1080/01621459.1985.10478208 · DOI
- Lütkepohl H Introduction to Multiple Time Series Analysis 1991 Berlin Springer Verlag
- Pantula SG Fuller WA Mean estimation bias in least squares estimation of autoregressive processes J. Econ. 1985 77 1 99 121 10.1016/0304-4076(85)90046-6 · DOI
- Price LR Small sample properties of bayesian multivariate autoregressive time series models Struct. Equ. Model. 2012 19 1 51 64 10.1080/10705511.2012.634712 · DOI
- Stoica P Friedlander B Söderström T Least-squares, yule-walker, and overdetermined walker estimation of ar parameters: a Monte Carlo analysis of finite-sample properties Int. J. Control 1986 43 1 13 27 10.1080/00207178608933446 · DOI
- Tanaka K (1984) An asymptotic expansion associated with the maximum likelihood estimators in ARMA models. J. R. Stat. Soc. Ser. B Methodol. 46(1):58–67. URL http://www.jstor.org/stable/2345462
- Tanaka K Maekawa K The sampling distributions of the predictor for an autoregressive model under misspecifications J. Econ. 1984 25 3 327 351 10.1016/0304-4076(84)90005-8 · DOI
- Walker G On periodicity in series of related terms Proc. R. Soc. Lon. Ser. A Contain. Pap. Math. Phys. Character 1931 131 818 518 532 10.1098/rspa.1931.0069 · DOI
- Watson P, Nicholls S (1992) ARIMA modelling in short data sets: some Monte Carlo results. Soc. Econ. Stud. 41(4):53–75. URL http://www.jstor.org/stable/27865115
- Young L On randomness in ordered sequences Ann. Math. Stat. 1941 12 3 293 300 10.1214/aoms/1177731711 · DOI
- Yule GU On a method of investigating periodicities in disturbed series, with special reference to Wolfer’s sunspot numbers Philos. Trans. R. Soc. Lon. Ser. A Contain. Pap. Math. Phys. Character 1927 226 267 298 10.1098/rsta.1927.0007 · DOI
- Zhang Z Nesselroade JR Bayesian estimation of categorical dynamic factor models Multivar. Behav. Res. 2007 42 4 729 756 10.1080/00273170701715998 · DOI
Cited by
Sorted by citations
The gendered experience with respect to health-seeking behaviour in an urban slum of Kolkata, India
Das, M., Angeli, F., Krumeich, A. J. S. M., & van Schayck, O. C. P. (2018) · International Journal for Equity in Health · doi:10.1186/s12939-018-0738-8 · Cited by 125 · see citing works
Views of psycho-oncologists, physicians, and nurses on cancer care—A qualitative study
Steven, B., Lange, L., Schulz, H., & Bleich, C. (2019) · PLOS ONE · doi:10.1371/journal.pone.0210325 · Cited by 45 · see citing works
- Authors
- Krone, T., Albers, C. J., & Timmerman, M. E.
- Affiliations
- University of Groningen (NL)
- Corresponding author
- Krone, Tanja
- Venue
- Quality & Quantity
- Published
- 2015-12-09
- Volume
- 51
- Issue
- 1
- Pages
- 1-21
- ISSN
- 0033-5177 (ISSN-L)
- 1573-7845
- PMC
- PMC5227053
- OpenAlex
- W2190246721
- Cited by
- 39
- References
- 0
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 3 · 2023: 5 · 2022: 2 · 2021: 3 · 2020: 7 · 2019: 3 · 2018: 5 · 2017: 2 · 2016: 1
- FWCI
- 2.19
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- Quality & Quantity (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- University of Groningen research database (University of Groningen / Centre for Information Technology) (publishedVersion, cc-by)
- RePEc: Research Papers in Economics (submittedVersion)
- University of Groningen research database (University of Groningen / Centre for Information Technology) (submittedVersion, cc-by)
- Funders
- NWO (406-11-018)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Mathematics › Applied Mathematics › Statistical and numerical algorithms
- Keywords
- AR(1) model, autoregressive coefficient estimation, short time series, autocorrelation estimation, prior distributions, flat prior, maximum likelihood estimator, ordinary least squares estimator, concordance index, model misspecification, ARMA(1,1), robustness, simulation study
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
