Fitting latent growth models with small sample sizes and non-normal missing data
This study investigates the performance of robust maximum likelihood (ML) estimators when fitting and evaluating small sample latent growth models with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very smal...
Saved in:
| Published in | International journal of behavioral development Vol. 45; no. 2; pp. 179 - 192 |
|---|---|
| Main Authors | , , , , |
| Format | Journal Article |
| Language | English |
| Published |
London, England
SAGE Publications
01.03.2021
SAGE PUBLICATIONS, INC |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0165-0254 1464-0651 |
| DOI | 10.1177/0165025420979365 |
Cover
Loading…
| Abstract | This study investigates the performance of robust maximum likelihood (ML) estimators when fitting and evaluating small sample latent growth models with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., N < 100). Among the robust ML estimators, “MLR” was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice “MLMV” produced the most accurate p values for the χ2 test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., comparative fit index, root mean square error of approximation, and standardized root mean square residual) exhibited worse fit. When the sample size was very small (e.g., N < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population. |
|---|---|
| AbstractList | This study investigates the performance of robust maximum likelihood (ML) estimators when fitting and evaluating small sample latent growth models with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., N < 100). Among the robust ML estimators, “MLR” was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice “MLMV” produced the most accurate p values for the χ 2 test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., comparative fit index, root mean square error of approximation, and standardized root mean square residual) exhibited worse fit. When the sample size was very small (e.g., N < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population. This study investigates the performance of robust ML estimators when fitting and evaluating small sample latent growth models (LGM) with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., < 100). Among the robust ML estimators, "MLR" was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice "MLMV" produced the most accurate values for the Chi-square test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., CFI, RMSEA, and SRMR) exhibited worse fit. When the sample size was very small (e.g., < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population. This study investigates the performance of robust ML estimators when fitting and evaluating small sample latent growth models (LGM) with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., N < 100). Among the robust ML estimators, “MLR” was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice “MLMV” produced the most accurate p values for the Chi-square test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., CFI, RMSEA, and SRMR) exhibited worse fit. When the sample size was very small (e.g., N < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population. This study investigates the performance of robust maximum likelihood (ML) estimators when fitting and evaluating small sample latent growth models with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., N < 100). Among the robust ML estimators, “MLR” was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice “MLMV” produced the most accurate p values for the χ2 test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., comparative fit index, root mean square error of approximation, and standardized root mean square residual) exhibited worse fit. When the sample size was very small (e.g., N < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population. This study investigates the performance of robust ML estimators when fitting and evaluating small sample latent growth models (LGM) with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., N < 100). Among the robust ML estimators, "MLR" was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice "MLMV" produced the most accurate p values for the Chi-square test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., CFI, RMSEA, and SRMR) exhibited worse fit. When the sample size was very small (e.g., N < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population.This study investigates the performance of robust ML estimators when fitting and evaluating small sample latent growth models (LGM) with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., N < 100). Among the robust ML estimators, "MLR" was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice "MLMV" produced the most accurate p values for the Chi-square test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., CFI, RMSEA, and SRMR) exhibited worse fit. When the sample size was very small (e.g., N < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population. This study investigates the performance of robust maximum likelihood (ML) estimators when fitting and evaluating small sample latent growth models with non-normal missing data. Results showed that the robust ML methods could be used to account for non-normality even when the sample size is very small (e.g., N < 100). Among the robust ML estimators, "MLR" was the optimal choice, as it was found to be robust to both non-normality and missing data while also yielding more accurate standard error estimates and growth parameter coverage. However, the choice "MLMV" produced the most accurate p values for the X[superscript 2] test statistic under conditions studied. Regarding the goodness of fit indices, as sample size decreased, all three fit indices studied (i.e., comparative fit index, root mean square error of approximation, and standardized root mean square residual) exhibited worse fit. When the sample size was very small (e.g., N < 60), the fit indices would imply that a proposed model fit poorly, when this might not be actually the case in the population. |
| Author | Zheng, Xiaying Jiang, Zhehan DiStefano, Christine Liu, Ren Shi, Dexin |
| Author_xml | – sequence: 1 givenname: Dexin orcidid: 0000-0002-4120-6756 surname: Shi fullname: Shi, Dexin email: shid@mailbox.sc.edu – sequence: 2 givenname: Christine surname: DiStefano fullname: DiStefano, Christine – sequence: 3 givenname: Xiaying surname: Zheng fullname: Zheng, Xiaying – sequence: 4 givenname: Ren surname: Liu fullname: Liu, Ren – sequence: 5 givenname: Zhehan surname: Jiang fullname: Jiang, Zhehan email: jiangzhehan@gmail.com |
| BackLink | http://eric.ed.gov/ERICWebPortal/detail?accno=EJ1283707$$DView record in ERIC https://www.ncbi.nlm.nih.gov/pubmed/33664535$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9UT1vFDEQtVAQuQR6GpAlGpoF2-uPdYMURQkJihQKqK2J13dx5LUP20cEvx4vlwRyErgZS-_Nm_dmDtBeTNEh9JKSd5Qq9Z5QKQgTnBGtdC_FE7SgXPKOSEH30GKGuxnfRwel3JD2ekWeof2-l5KLXizQ51Nfq48rHKC6WPEqp9t6jac0ulDwrW__MkEIuMC0Dg4X_9MVDHHEzUoXU24gnnwps8YIFZ6jp0sIxb24q4fo6-nJl-Oz7uLy4_nx0UVn-cBrpzQbBgEjc9Ite0tlq6IHQth4tSSWSQtq0BKYHgSXbgCptRWgnOtHqlqOQ_Rhq7veXE1utM18hmDW2U-Qf5gE3jxGor82q_TdzJM5G5rA2zuBnL5tXKmmxbAuBIgubYphXA9cU_ab-maHepM2ObZ4jTXItm3d68Z6_bejByv3y26EV1uCy94-wCefaBuhiGq43OI2p1KyWxrrK1Sf5gA-GErMfHWze_XWSHYa78X_09JtWwqs3J84_-T_Amg-uP0 |
| CitedBy_id | crossref_primary_10_1111_jopy_12742 crossref_primary_10_1016_j_ijhm_2024_103748 crossref_primary_10_1016_j_infbeh_2022_101801 crossref_primary_10_1371_journal_pone_0265480 crossref_primary_10_1123_jsep_2024_0109 crossref_primary_10_1016_j_heliyon_2023_e21321 crossref_primary_10_1016_j_mhp_2023_200295 crossref_primary_10_1016_j_jvb_2022_103809 crossref_primary_10_52380_ijcer_2023_10_2_308 crossref_primary_10_1007_s41542_024_00206_x crossref_primary_10_1007_s11121_024_01749_9 crossref_primary_10_1111_jora_12823 crossref_primary_10_1016_j_lindif_2024_102408 crossref_primary_10_1177_00131644211010234 crossref_primary_10_1016_j_bone_2025_117428 crossref_primary_10_1080_10705511_2022_2032078 crossref_primary_10_1186_s13561_023_00472_5 crossref_primary_10_1007_s10459_023_10279_y crossref_primary_10_1080_1750399X_2025_2453349 crossref_primary_10_1136_bmjopen_2024_092724 crossref_primary_10_1007_s10803_021_05373_2 crossref_primary_10_1016_j_jpeds_2022_09_047 crossref_primary_10_1007_s12144_024_06437_z crossref_primary_10_1080_29933021_2025_2469036 crossref_primary_10_1080_21642850_2022_2104724 crossref_primary_10_1111_hex_14176 crossref_primary_10_1080_10615806_2023_2290667 crossref_primary_10_1080_09500693_2024_2394706 crossref_primary_10_1016_j_ejon_2024_102687 crossref_primary_10_1002_gps_5893 crossref_primary_10_1080_10640266_2024_2357942 crossref_primary_10_1186_s40359_024_01692_y crossref_primary_10_3390_psycholint6020029 crossref_primary_10_1007_s11482_024_10397_8 crossref_primary_10_1007_s10802_023_01140_2 crossref_primary_10_1016_j_jpain_2024_02_005 crossref_primary_10_1177_00131644231158854 crossref_primary_10_5964_ps_7237 crossref_primary_10_1111_jan_16068 crossref_primary_10_1080_10705511_2021_1931870 crossref_primary_10_1007_s13178_024_01038_8 crossref_primary_10_1080_10705511_2023_2264514 crossref_primary_10_1080_14616734_2023_2286228 |
| Cites_doi | 10.1037/0033-2909.107.2.238 10.1080/10705511.2020.1717957 10.1080/03610918.2014.983648 10.1093/biomet/63.3.581 10.1080/10705511.2013.824793 10.1080/10705511.2017.1369088 10.1037/1082-989X.1.1.16 10.1002/ajmg.a.31286 10.1037/a0015858 10.1027/1614-2241.4.1.22 10.1080/00273171.2014.933697 10.1007/BF02294746 10.1080/10705511.2019.1637741 10.1177/0013164414548894 10.1177/0049124198026003003 10.1080/00273171.2016.1167008 10.1007/BF02293687 10.1080/10705511.2012.634724 10.3758/s13428-017-0976-5 10.1207/S15328007SEM0904_8 10.32614/CRAN.package.simsem 10.1002/9781118619179 10.1177/0013164419845039 10.1177/0013164418783530 10.1037/a0015808 10.1080/00273171.2015.1133274 10.1111/j.2044-8317.1978.tb00581.x 10.1080/10705519809540104 10.1177/0013164416661824 10.1007/s10648-014-9287-x 10.1080/00273171.2018.1455142 10.1080/10705511.2016.1269606 10.1080/00273171.2012.715252 10.1037/0033-2909.105.1.156 10.1037/1082-989X.8.3.338 10.1037/a0020143 10.1080/10705519909540118 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2021 |
| Copyright_xml | – notice: The Author(s) 2021 |
| DBID | AAYXX CITATION 7SW BJH BNH BNI BNJ BNO ERI PET REK WWN NPM 7QJ AHOVV 7X8 5PM |
| DOI | 10.1177/0165025420979365 |
| DatabaseName | CrossRef ERIC ERIC (Ovid) ERIC ERIC ERIC (Legacy Platform) ERIC( SilverPlatter ) ERIC ERIC PlusText (Legacy Platform) Education Resources Information Center (ERIC) ERIC PubMed Applied Social Sciences Index & Abstracts (ASSIA) Education Research Index MEDLINE - Academic PubMed Central (Full Participant titles) |
| DatabaseTitle | CrossRef ERIC PubMed Applied Social Sciences Index and Abstracts (ASSIA) MEDLINE - Academic |
| DatabaseTitleList | CrossRef PubMed Applied Social Sciences Index and Abstracts (ASSIA) MEDLINE - Academic ERIC |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: ERI name: ERIC url: https://eric.ed.gov/ sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Psychology |
| EISSN | 1464-0651 |
| ERIC | EJ1283707 |
| EndPage | 192 |
| ExternalDocumentID | PMC7928428 33664535 EJ1283707 10_1177_0165025420979365 10.1177_0165025420979365 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: National Institutes of Health grantid: R21DC017252 funderid: https://doi.org/10.13039/100000002 – fundername: university of south carolina grantid: 13580-17-44758 funderid: https://doi.org/10.13039/100008899 – fundername: NIMH NIH HHS grantid: K23 MH120476 – fundername: NIDCD NIH HHS grantid: R21 DC017252 |
| GroupedDBID | --- --Z -ET -TM -W8 -~X .2G .2J .2L .2N .GO 01A 09Z 0R~ 1~K 29J 31S 31U 31V 31W 31X 31Y 31Z 4.4 41~ 53G 56W 5GY 5VS AABMB AABOD AACKU AACMV AACTG AADIR AADUE AAEWN AAGGD AAGLT AAHSB AAJIQ AAJOX AAJPV AAKTJ AAMFR AANSI AAPEO AAQDB AAQXH AAQXI AARDL AARIX AATAA AATBZ AAWLO AAYTG ABAWP ABCCA ABCJG ABDBF ABDWY ABEIX ABFWQ ABFXH ABHKI ABHQH ABIDT ABIVO ABJNI ABKRH ABLUO ABOPQ ABPGX ABPNF ABQKF ABQPY ABQXT ABRHV ABRLO ABUJY ABVFX ABYTW ACABN ACAEP ACARO ACDSZ ACDXX ACFEJ ACFMA ACFUR ACFZE ACGBL ACGEJ ACGFS ACGZU ACHQT ACJER ACLHI ACLZU ACOFE ACOXC ACROE ACRPL ACSIQ ACUAV ACUFS ACUHS ACUIR ACXKE ACXMB ADBBV ADCVX ADDLC ADEBD ADEIA ADMHG ADNMO ADNON ADPEE ADRRZ ADSTG ADTBJ ADTOS ADUKL ADVBO ADXPE ADYCS AECGH AECVZ AEDTQ AEDXQ AEOBU AEONT AEPTA AEQLS AERKM AESMA AESZF AEUHG AEVPJ AEWDL AEWHI AEXNY AFEET AFFNX AFKBI AFKRG AFMOU AFQAA AFUIA AFWMB AGDVU AGKLV AGNHF AGNWV AGQPQ AGWFA AGWNL AHDMH AHHFK AHOJL AHWHD AJEFB AJMMQ AJUZI AJWEG AJXAJ ALKWR ALMA_UNASSIGNED_HOLDINGS AMCVQ ANDLU ARTOV ASPBG AUTPY AUVAJ AVWKF AWYRJ AYAKG AYPQM AZFZN B0M B8O B8R B8S B8T B8Z B93 B94 BBRGL BDDNI BDZRT BKIIM BMVBW BPACV BSEHC BYIEH CAG CBRKF CCGJY CEADM CFDXU COF CORYS CQQTX CS3 DC- DC. DD- DD0 DD~ DE- DF0 DG~ DO- DOPDO DU5 DV7 DV8 D~Y EAP EAS EBS EDJ EJD EMK EPS ESO ESX F5P FEDTE FHBDP GROUPED_SAGE_PREMIER_JOURNAL_COLLECTION H13 HF~ HVGLF HZ~ J8X K.F K.J M4Z N9A O9- OHT OVD P.B P2P Q1R Q7K Q7L Q7O Q7P Q7X Q82 Q83 RIG ROL S01 SASJQ SAUOL SBI SCNPE SDB SFB SFC SFK SFT SFX SFY SGA SGP SGR SGU SGV SGX SGZ SHB SHF SHG SHM SNB SPJ SPP SPV SQCSI SSDHQ STM TDBHL TEORI TFW TN5 UPT WH7 ZGI ZONMY ZPLXX ZPPRI ZRKOI ~32 ~8M AAYXX ACCVC AJGYC AMNSR CITATION 7SW AAEJI AAPII AJHME AJVBE BJH BNH BNI BNJ BNO ERI PET REK WWN NPM 7QJ AHOVV 7X8 5PM |
| ID | FETCH-LOGICAL-c484t-792885ad2e6ef3c16e6e53a002dbf0c26ca7896a298546e8a699c5a7ee3d17003 |
| ISSN | 0165-0254 |
| IngestDate | Thu Aug 21 18:27:38 EDT 2025 Wed Jul 30 11:24:41 EDT 2025 Thu Aug 14 00:04:15 EDT 2025 Mon Jul 21 06:01:52 EDT 2025 Tue Sep 02 19:14:43 EDT 2025 Tue Jul 01 05:26:40 EDT 2025 Thu Apr 24 22:59:30 EDT 2025 Tue Jun 17 22:29:12 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Keywords | Latent growth models non-normality missing data small sample latent growth models |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c484t-792885ad2e6ef3c16e6e53a002dbf0c26ca7896a298546e8a699c5a7ee3d17003 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0002-4120-6756 |
| OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/7928428 |
| PMID | 33664535 |
| PQID | 2486065939 |
| PQPubID | 2033251 |
| PageCount | 14 |
| ParticipantIDs | pubmedcentral_primary_oai_pubmedcentral_nih_gov_7928428 proquest_miscellaneous_2498491228 proquest_journals_2486065939 pubmed_primary_33664535 eric_primary_EJ1283707 crossref_citationtrail_10_1177_0165025420979365 crossref_primary_10_1177_0165025420979365 sage_journals_10_1177_0165025420979365 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2021-03-01 |
| PublicationDateYYYYMMDD | 2021-03-01 |
| PublicationDate_xml | – month: 03 year: 2021 text: 2021-03-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | London, England |
| PublicationPlace_xml | – name: London, England – name: England – name: Amsterdam |
| PublicationTitle | International journal of behavioral development |
| PublicationTitleAlternate | Int J Behav Dev |
| PublicationYear | 2021 |
| Publisher | SAGE Publications SAGE PUBLICATIONS, INC |
| Publisher_xml | – name: SAGE Publications – name: SAGE PUBLICATIONS, INC |
| References | Savalei 2010; 15 Ferguson 2009; 40 Rubin 1976; 63 McNeish, Stapleton 2016; 51 Meredith, Tisak 1990; 55 Pavlov, Shi, Maydeu-Olivares 2020; 27 Shi, Lee, Terry 2018; 25 McNeish, Matta 2018; 50 Curran, West, Finch 1996; 1 Moshagen 2012; 19 Shi, Lee, Maydeu-Olivares 2019; 79 Hatton, Sideris, Skinner, Mankowski, Bailey, Roberts, Mirrett 2006; 140 Gao, Shi, Maydeu-Olivares 2020; 27 Micceri 1989; 105 Boomsma, Jöreskog, Wold 1982 McNeish, Harring 2017; 46 Muthén, Muthén 2002; 9 Bauer, Curran 2003; 8 Bentler 1990; 107 McNeish, Stapleton 2016; 28 Ferrer, Balluerka, Widaman 2008; 4 Bradley 1978; 31 Brosseau-Liard, Savalei 2014; 49 Foldnes, Olsson 2016; 51 Savalei 2018; 53 Savalei 2014; 21 Wu, West, Taylor 2009; 14 Hu, Bentler 1999; 6 Maydeu-Olivares 2017; 24 Olvera Astivia, Zumbo 2015; 75 Brosseau-Liard, Savalei, Li 2012; 47 McNeish 2017; 86 Shi, Lee, Fairchild, Maydeu-Olivares 2019; 80 Chou, Bentler, Pentz 1998; 5 McNeish, Harring 2017; 77 Vale, Maurelli 1983; 48 Hoogland, Boomsma 1998; 26 bibr39-0165025420979365 bibr38-0165025420979365 Jöreskog K. G. (bibr23-0165025420979365) 1988 bibr13-0165025420979365 bibr21-0165025420979365 bibr8-0165025420979365 bibr47-0165025420979365 bibr30-0165025420979365 bibr11-0165025420979365 bibr54-0165025420979365 bibr29-0165025420979365 bibr7-0165025420979365 Zheng X. (bibr55-0165025420979365) 2017 Enders C. K. (bibr12-0165025420979365) 2010 bibr46-0165025420979365 bibr28-0165025420979365 bibr36-0165025420979365 bibr10-0165025420979365 Boomsma A. (bibr6-0165025420979365) 1982 Grimm K. J. (bibr18-0165025420979365) 2017 bibr49-0165025420979365 Nunnally J. C. (bibr37-0165025420979365) 1967; 226 Finney S. (bibr15-0165025420979365) 2013 Hedeker D. (bibr20-0165025420979365) 2006 bibr52-0165025420979365 Steiger J. (bibr51-0165025420979365) 1980 Ross C. A. (bibr42-0165025420979365) 1997 McNeish D. (bibr25-0165025420979365) 2017; 86 Meredith W. (bibr31-0165025420979365) 1984 bibr4-0165025420979365 bibr50-0165025420979365 bibr26-0165025420979365 bibr34-0165025420979365 bibr43-0165025420979365 bibr17-0165025420979365 bibr16-0165025420979365 R Development Core Team (bibr41-0165025420979365) 2015 bibr2-0165025420979365 bibr3-0165025420979365 bibr24-0165025420979365 bibr33-0165025420979365 Bollen K. A. (bibr5-0165025420979365) 2006; 467 Asparouhov T. (bibr202-0165025420979365) 2010 bibr1-0165025420979365 bibr19-0165025420979365 bibr45-0165025420979365 Asparouhov T. (bibr201-0165025420979365) 2005 bibr32-0165025420979365 Muthén L. K. (bibr35-0165025420979365) 1998 bibr48-0165025420979365 Satorra A. (bibr44-0165025420979365) 1994 bibr22-0165025420979365 bibr27-0165025420979365 bibr9-0165025420979365 bibr40-0165025420979365 bibr14-0165025420979365 |
| References_xml | – volume: 49 start-page: 460 issue: 5 year: 2014 end-page: 470 article-title: Adjusting incremental fit indices for nonnormality publication-title: Multivariate Behavioral Research – volume: 27 start-page: 192 issue: 2 year: 2020 end-page: 201 article-title: Estimating the maximum likelihood root mean square error of approximation (RMSEA) with non-normal data: A Monte-Carlo study publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 107 start-page: 238 issue: 2 year: 1990 end-page: 246 article-title: Comparative fit indexes in structural models publication-title: Psychological Bulletin – volume: 140 start-page: 1804 issue: 17 year: 2006 end-page: 1813 article-title: Autistic behavior in children with fragile X syndrome: Prevalence, stability, and the impact of FMRP publication-title: American Journal of Medical Genetics Part A – volume: 19 start-page: 86 issue: 1 year: 2012 end-page: 98 article-title: The model size effect in SEM: Inflated goodness-of-fit statistics are due to the size of the covariance matrix publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 77 start-page: 990 issue: 6 year: 2017 end-page: 1018 article-title: Correcting model fit criteria for small sample latent growth models with incomplete data publication-title: Educational and Psychological Measurement – volume: 75 start-page: 541 issue: 4 year: 2015 end-page: 567 article-title: A cautionary note on the use of the Vale and Maurelli method to generate multivariate, nonnormal data for simulation purposes publication-title: Educational and Psychological Measurement – volume: 14 start-page: 183 issue: 3 year: 2009 article-title: Evaluating model fit for growth curve models: Integration of fit indices from SEM and MLM frameworks publication-title: Psychological Methods – volume: 31 start-page: 144 issue: 2 year: 1978 end-page: 152 article-title: Robustness? publication-title: British Journal of Mathematical and Statistical Psychology – volume: 86 start-page: 1 issue: 4 year: 2017 end-page: 12 article-title: Brief research report: Growth models with small samples and missing data publication-title: The Journal of Experimental Education – volume: 51 start-page: 207 issue: 2-3 year: 2016 end-page: 219 article-title: A simple simulation technique for nonnormal data with prespecified skewness, kurtosis, and covariance matrix publication-title: Multivariate Behavioral Research – volume: 21 start-page: 149 issue: 1 year: 2014 end-page: 160 article-title: Understanding robust corrections in structural equation modeling publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 79 start-page: 310 issue: 2 year: 2019 end-page: 334 article-title: Understanding the model size effect on SEM fit indices publication-title: Educational and Psychological Measurement – volume: 40 start-page: 532 year: 2009 end-page: 538 article-title: An effect size primer: A guide for clinicians and researchers publication-title: Professional Psychology: Research and Practice – volume: 8 start-page: 338 issue: 3 year: 2003 end-page: 363 article-title: Distributional assumptions of growth mixture models: Implications for overextraction of latent trajectory classes publication-title: Psychological Methods – volume: 47 start-page: 904 issue: 6 year: 2012 end-page: 930 article-title: An investigation of the sample performance of two nonnormality corrections for RMSEA publication-title: Multivariate Behavioral Research – volume: 48 start-page: 465 issue: 3 year: 1983 end-page: 471 article-title: Simulating multivariate nonnormal distributions publication-title: Psychometrika – volume: 53 start-page: 419 issue: 3 year: 2018 end-page: 429 article-title: On the computation of the RMSEA and CFI from the mean-and-variance corrected test statistic with nonnormal data in SEM publication-title: Multivariate Behavioral Research – volume: 28 start-page: 295 issue: 2 year: 2016 end-page: 314 article-title: The effect of small sample size on two-level model estimates: A review and illustration publication-title: Educational Psychology Review – volume: 46 start-page: 855 issue: 2 year: 2017 end-page: 869 article-title: Clustered data with small sample sizes: Comparing the performance of model-based and design-based approaches publication-title: Communications in Statistics-Simulation and Computation – volume: 25 start-page: 21 issue: 1 year: 2018 end-page: 40 article-title: Revisiting the model size effect in structural equation modeling publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 51 start-page: 495 issue: 4 year: 2016 end-page: 518 article-title: Modeling clustered data with very few clusters publication-title: Multivariate Behavioral Research – volume: 15 start-page: 352 year: 2010 end-page: 367 article-title: Expected versus observed information in SEM with incomplete normal and nonnormal data publication-title: Psychological Methods – volume: 55 start-page: 107 issue: 1 year: 1990 end-page: 122 article-title: Latent curve analysis publication-title: Psychometrika – volume: 105 start-page: 156 issue: 1 year: 1989 end-page: 166 article-title: The unicorn, the normal curve, and other improbable creatures publication-title: Psychological Bulletin – volume: 1 start-page: 16 issue: 1 year: 1996 article-title: The robustness of test statistics to nonnormality and specification error in confirmatory factor analysis publication-title: Psychological Methods – volume: 24 start-page: 383 issue: 3 year: 2017 end-page: 394 article-title: Maximum likelihood estimation of structural equation models for continuous data: Standard errors and goodness of fit publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 5 start-page: 247 issue: 3 year: 1998 end-page: 266 article-title: Comparisons of two statistical approaches to study growth curves: The multilevel model and the latent curve analysis publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 80 start-page: 41 issue: 1 year: 2019 end-page: 66 article-title: Fitting ordinal factor analysis models with missing data: A comparison between pairwise deletion and multiple imputation publication-title: Educational and Psychological Measurement – volume: 50 start-page: 1398 issue: 4 year: 2018 end-page: 1414 article-title: Differentiating between mixed-effects and latent-curve approaches to growth modeling publication-title: Behavior Research Methods – volume: 27 start-page: 908 issue: 6 year: 2020 end-page: 917 article-title: Chi-square difference tests for comparing nested models: An evaluation with non-normal data publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 9 start-page: 599 issue: 4 year: 2002 end-page: 620 article-title: How to use a Monte Carlo study to decide on sample size and determine power publication-title: Structural Equation Modeling – volume: 26 start-page: 329 issue: 3 year: 1998 end-page: 367 article-title: Robustness studies in covariance structure modeling: An overview and a meta-analysis publication-title: Sociological Methods & Research – volume: 6 start-page: 1 issue: 1 year: 1999 end-page: 55 article-title: Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternatives publication-title: Structural Equation Modeling: A Multidisciplinary Journal – volume: 63 start-page: 581 issue: 3 year: 1976 end-page: 592 article-title: Inference and missing data publication-title: Biometrika – start-page: 149 year: 1982 end-page: 173 article-title: The robustness of LISREL against small sample sizes in factor analysis models publication-title: Systems under indirect observation: Causality, structure, prediction – volume: 4 start-page: 22 issue: 1 year: 2008 article-title: Factorial invariance and the specification of second-order latent growth models publication-title: Methodology: European Journal of Research Methods for the Behavioral and Social Sciences – ident: bibr3-0165025420979365 doi: 10.1037/0033-2909.107.2.238 – ident: bibr39-0165025420979365 doi: 10.1080/10705511.2020.1717957 – start-page: 399 volume-title: Latent variable analysis. Applications for developmental research year: 1994 ident: bibr44-0165025420979365 – ident: bibr29-0165025420979365 doi: 10.1080/03610918.2014.983648 – ident: bibr43-0165025420979365 doi: 10.1093/biomet/63.3.581 – ident: bibr46-0165025420979365 doi: 10.1080/10705511.2013.824793 – ident: bibr50-0165025420979365 doi: 10.1080/10705511.2017.1369088 – ident: bibr11-0165025420979365 doi: 10.1037/1082-989X.1.1.16 – ident: bibr19-0165025420979365 doi: 10.1002/ajmg.a.31286 – volume-title: Longitudinal data analysis year: 2006 ident: bibr20-0165025420979365 – ident: bibr54-0165025420979365 doi: 10.1037/a0015858 – ident: bibr14-0165025420979365 doi: 10.1027/1614-2241.4.1.22 – ident: bibr8-0165025420979365 doi: 10.1080/00273171.2014.933697 – volume-title: R: A Language and environment for statistical computing year: 2015 ident: bibr41-0165025420979365 – volume-title: LISREL 7: A guide to the program and applications year: 1988 ident: bibr23-0165025420979365 – volume-title: Simple second order chi-square correction scaled chi-square statistics (Technical appendix) year: 2010 ident: bibr202-0165025420979365 – ident: bibr32-0165025420979365 doi: 10.1007/BF02294746 – ident: bibr17-0165025420979365 doi: 10.1080/10705511.2019.1637741 – volume-title: Proceedings of the Federal Committee on Statistical Methodology (FCSM) Research Conference year: 2005 ident: bibr201-0165025420979365 – ident: bibr38-0165025420979365 doi: 10.1177/0013164414548894 – ident: bibr21-0165025420979365 doi: 10.1177/0049124198026003003 – ident: bibr28-0165025420979365 doi: 10.1080/00273171.2016.1167008 – ident: bibr52-0165025420979365 doi: 10.1007/BF02293687 – ident: bibr34-0165025420979365 doi: 10.1080/10705511.2012.634724 – volume-title: Latent growth curve analysis with item response data: Model specification, estimation, and panel attrition year: 2017 ident: bibr55-0165025420979365 – ident: bibr27-0165025420979365 doi: 10.3758/s13428-017-0976-5 – ident: bibr36-0165025420979365 doi: 10.1207/S15328007SEM0904_8 – start-page: 439 volume-title: Structural equation modeling: A second course year: 2013 ident: bibr15-0165025420979365 – volume-title: Dissociative identity disorder: Diagnosis, clinical features, and treatment of multiple personality year: 1997 ident: bibr42-0165025420979365 – ident: bibr40-0165025420979365 doi: 10.32614/CRAN.package.simsem – volume: 467 volume-title: Latent curve models: A structural equation perspective year: 2006 ident: bibr5-0165025420979365 – start-page: 149 year: 1982 ident: bibr6-0165025420979365 publication-title: Systems under indirect observation: Causality, structure, prediction – ident: bibr4-0165025420979365 doi: 10.1002/9781118619179 – volume-title: Applied missing data analysis year: 2010 ident: bibr12-0165025420979365 – ident: bibr48-0165025420979365 doi: 10.1177/0013164419845039 – volume: 226 volume-title: Psychometric theory year: 1967 ident: bibr37-0165025420979365 – ident: bibr49-0165025420979365 doi: 10.1177/0013164418783530 – ident: bibr13-0165025420979365 doi: 10.1037/a0015808 – ident: bibr16-0165025420979365 doi: 10.1080/00273171.2015.1133274 – ident: bibr7-0165025420979365 doi: 10.1111/j.2044-8317.1978.tb00581.x – ident: bibr10-0165025420979365 doi: 10.1080/10705519809540104 – ident: bibr1-0165025420979365 – volume-title: Paper presented at the annual meeting of the annual spring meeting of the psychometric society year: 1980 ident: bibr51-0165025420979365 – ident: bibr26-0165025420979365 doi: 10.1177/0013164416661824 – volume: 86 start-page: 1 issue: 4 year: 2017 ident: bibr25-0165025420979365 publication-title: The Journal of Experimental Education – ident: bibr30-0165025420979365 doi: 10.1007/s10648-014-9287-x – ident: bibr47-0165025420979365 doi: 10.1080/00273171.2018.1455142 – ident: bibr24-0165025420979365 doi: 10.1080/10705511.2016.1269606 – volume-title: Growth modeling: Structural equation and multilevel modeling approaches year: 2017 ident: bibr18-0165025420979365 – volume-title: Paper presented at the meeting of the psychometric society year: 1984 ident: bibr31-0165025420979365 – ident: bibr9-0165025420979365 doi: 10.1080/00273171.2012.715252 – ident: bibr33-0165025420979365 doi: 10.1037/0033-2909.105.1.156 – ident: bibr2-0165025420979365 doi: 10.1037/1082-989X.8.3.338 – volume-title: Mplus user’s guide year: 1998 ident: bibr35-0165025420979365 – ident: bibr45-0165025420979365 doi: 10.1037/a0020143 – ident: bibr22-0165025420979365 doi: 10.1080/10705519909540118 |
| SSID | ssj0000370 |
| Score | 2.5091045 |
| Snippet | This study investigates the performance of robust maximum likelihood (ML) estimators when fitting and evaluating small sample latent growth models with... This study investigates the performance of robust ML estimators when fitting and evaluating small sample latent growth models (LGM) with non-normal missing... |
| SourceID | pubmedcentral proquest pubmed eric crossref sage |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 179 |
| SubjectTerms | Error of Measurement Factor Analysis Goodness of Fit Growth Models Indexes Maximum Likelihood Statistics Missing data Normality Research Problems Robustness (Statistics) Sample Size |
| Title | Fitting latent growth models with small sample sizes and non-normal missing data |
| URI | https://journals.sagepub.com/doi/full/10.1177/0165025420979365 http://eric.ed.gov/ERICWebPortal/detail?accno=EJ1283707 https://www.ncbi.nlm.nih.gov/pubmed/33664535 https://www.proquest.com/docview/2486065939 https://www.proquest.com/docview/2498491228 https://pubmed.ncbi.nlm.nih.gov/PMC7928428 |
| Volume | 45 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1ba9swFBZZCyMvY7eu3rqiwRiM4TaWZFl6LL1QylIy2kK2lyDLMjEkTtkctvY_7D9PF1-UdBtbX5xgK1Ks8-noSDrnOwC8ZYYwJZIkFIKgkMRZFDIsaSgHecpUnueDxMQOD8_p6RU5G8fjXu-n57W0rNI9efvbuJL7SFXf03I1UbL_Idm2Un1Df9fy1VctYX39JxmfFM5r-aM2GMvK7CN9r6Y2vdmsjlq7mNujZzG3PoPFrXKUzOeLMiyNtTr7MNQ9b-o4ckFqraW6ulXoEUx4gf1Z53HU7tRMXeS6-lG0sDsqLiqVi3LRsRl4p_lfpsrpm3EhbpqJ1LgIFUsn_9LfmUCea1azWUlN9Lcjid5TTsESSkJt9kS-BnaEkjXSkKdOI5dopp6ZI5c1767St8fOpjXTGBpwrXNcAgoPA9dzCwKMKSWxY0hZI9oeDQ8TrmdrxB6ATaRXHVrPbx58Hn0adlM7ttkH2xfrzr3315vvg4dNWysmz6pXvbecueuV67kWWmvn8jF4VC9T4IHD3BPQU-VT0G9ny5tnYFSDDzrwQQc-6MAHDfigBR904IMWfFCDD3bggzX4oAHfc3B1cnx5eBrW6TlCSRipQtNZLBYZUlTlWEZUf8ZY6Ck2S_OBRFSKhHEqEGcxoYoJyrmMRaIUzgwrJN4CG-WiVNsAMjnAmRK6D2VKJIl5mmaCM0UlznJGswDsNz04kTV3vUmhMptEDV39WvcH4H37i2vH2_KXsltGKG2547PIckIlAdhpxDSpx9m3CTJp22jMMQ_Am_axVsrmpE2UarE0ZTgjPEKIBeCFk2pbe4OKACQr8m4LGML31SdlMbXE7zU8A_DOIKP7S396sZf3buIV6HcjegdsVF-X6rW2vqt0tx4Tu3an6RcZDNYZ |
| linkProvider | SAGE Publications |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEB7B9kAv5VkIFDASQuKQNvEr9rFCXS2lWxWplQqXyHEcuiJNEcke6K_Hk02yu61AiFMOHj_GHttj-8s3AG8VEqbElofGcBpykcehYlaGNioy5YqiiBL8d3h6LCdn_PBcnK-E-up6sN5FWJVvUbtYD7MbmZJi71P4Uw2NtDctKe7ChkI_fAQb-19OPk-XyzBrI8WhfIgZlm-Ut8pY25PWYc8r_uZt2OQK9qvdjsb34WuvyAKF8n133ngdrm9wPP6Xpg9gq3NSyf7Cqh7CHVc9gs1hrfz1GE7GsxYwTUrvq1YN-eZP880FaePq1AQvd0l9acqS1Abph0k9u3Y1MVVOqqsqrNBRLok3MbypIIhSfQJn44PTD5OwC84QWq54EyaaKiVMTp10BbOx9F_BjF9g86yILJXWJEpLQ7USXDplpNZWmMQ5liMnINuGka_RPQOibMRyZ7y-NuOWC51ludHKScvyQsk8gL1-eFLbMZdjAI0yjXuy8htdFcD7IcePBWvHX2S3ccQHuYPDuGUESgLY6W0g7QcrpRi0SwrNdABvhmTfX_jOYip3NUcZrbiOKVUBPF2YzFA6Y1JywXytyZoxDQJI972eUs0uWtpv7HGOZb5Di1k26U-KPf9Xwddwb3I6PUqPPh5_egGbFFE7LcpuB0bNz7l76d2uJnvVTbDfktAfDg |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwELaglVAvvFsCbTESQuLgbuJX7GMFXZVCq0WiUjlFju3QFSGtSPZAfz0ebzbbbQVCnHLw-DH22J7Yn79B6LUCwpTMcmIMp4QLlxHFrCQ2rUrlq6pKc3g7fHwiD0_50Zk467E58Bam78F2D2BVoUVxsYbZfemqUX_HOIInOPCKm6Y6mJcUd9F62KdomJfr-18nn4-XSzGL0eJAnkCG5T3lrTJW9qVV6PM1n_M2dPIa_ituSeMH87irbWQyBCTK971ZF_S4usHz-N_aPkT3e2cV78-t6xG645vHaGNYM389QZPxNAKncR181qbD38JffXeOY3ydFsMhL25_mLrGrQEaYtxOr3yLTeNwc9GQBhzmGgdTgxMLDGjVp-h0fPDl3SHpgzQQyxXvSK6pUsI46qWvmM1k-ApmwkLryiq1VFqTKy0N1Upw6ZWRWlthcu-ZA25AtonWQo3-GcLKpsx5E_S1Jbdc6LJ0RisvLXOVki5Bo8UQFbZnMIdAGnWRLUjLb3RVgt4OOS7n7B1_kd2EUR_kDo6yyAyUJ2h7YQfFYsAKCsG7pNBMJ-jVkBz6C-5bTOMvZiCjFdfBMFWCtuZmM5TOmJRcsFBrvmJQgwDQfq-mNNPzSP8NPc6hzDdgNcsm_Umx5_8q-BLdm7wfF58-nHx8gTYogHci2G4brXU_Z34neF9dudvPsd_hyyGD |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Fitting+Latent+Growth+Models+with+Small+Sample+Sizes+and+Non-normal+Missing+Data&rft.jtitle=International+journal+of+behavioral+development&rft.au=Shi%2C+Dexin&rft.au=DiStefano%2C+Christine&rft.au=Zheng%2C+Xiaying&rft.au=Liu%2C+Ren&rft.date=2021-03-01&rft.issn=0165-0254&rft.eissn=1464-0651&rft.volume=45&rft.issue=2&rft.spage=179&rft.epage=192&rft_id=info:doi/10.1177%2F0165025420979365&rft_id=info%3Apmid%2F33664535&rft.externalDocID=PMC7928428 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0165-0254&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0165-0254&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0165-0254&client=summon |