Factor recovery by principal axis factoring and maximum likelihood factor analysis as a function of factor pattern and sample size
Principal axis factoring (PAF) and maximum likelihood factor analysis (MLFA) are two of the most popular estimation methods in exploratory factor analysis. It is known that PAF is better able to recover weak factors and that the maximum likelihood estimator is asymptotically efficient. However, ther...
Gespeichert in:
| Veröffentlicht in: | Journal of applied statistics 2012-04, Vol.39 (4), p.695-710 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 710 |
|---|---|
| container_issue | 4 |
| container_start_page | 695 |
| container_title | Journal of applied statistics |
| container_volume | 39 |
| creator | de Winter, J. C.F. Dodou, D. |
| description | Principal axis factoring (PAF) and maximum likelihood factor analysis (MLFA) are two of the most popular estimation methods in exploratory factor analysis. It is known that PAF is better able to recover weak factors and that the maximum likelihood estimator is asymptotically efficient. However, there is almost no evidence regarding which method should be preferred for different types of factor patterns and sample sizes. Simulations were conducted to investigate factor recovery by PAF and MLFA for distortions of ideal simple structure and sample sizes between 25 and 5000. Results showed that PAF is preferred for population solutions with few indicators per factor and for overextraction. MLFA outperformed PAF in cases of unequal loadings within factors and for underextraction. It was further shown that PAF and MLFA do not always converge with increasing sample size. The simulation findings were confirmed by an empirical study as well as by a classic plasmode, Thurstone's box problem. The present results are of practical value for factor analysts. |
| doi_str_mv | 10.1080/02664763.2011.610445 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1283717583</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1283717583</sourcerecordid><originalsourceid>FETCH-LOGICAL-c467t-2e1d338ed087f21dab84ac92b5566606e8f2f108d27fbe8f8e1332c05d28da253</originalsourceid><addsrcrecordid>eNqFkc1u1DAUhSMEEkPhDVhYrNjM1P9xVghVFIoqsYG1dcexqYckDnbSEpY8OXcmLQsWIPnasv2dY-ueqnrJ6I5RQ88p11rWWuw4ZWynGZVSPao2TGi6pUrwx9XmiGyPzNPqWSkHSqlhSmyqX5fgppRJ9i7d-ryQ_ULGHAcXR-gI_IiFhBMRh68Ehpb0eNbPPeniN9_Fm5TaewBvoVsKCgAHCfPgppgGksIDMMI0-TycbAr0Y-dJiT_98-pJgK74F_frWfXl8t3niw_b60_vry7eXm-d1PW05Z61QhjfUlMHzlrYGwmu4XultNZUexN4wHa0vA573BjPhOCOqpabFrgSZ9Xr1XfM6fvsy2T7WJzvOhh8motlWnLeaG7E_1GEalarE_rqL_SQ5oytKLbhhkqhZI2QXCGXUynZB4s97iEvllF7jNA-RGiPEdo1QpR9XGXZj9790UwQDjCWCeytFSAanBYsVHJcIpbEGrF0o2yNT9xMPZq9Wc3iEFLu4S7lrkWvpUs5ZMDEixX__M5vMf28gQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>928043547</pqid></control><display><type>article</type><title>Factor recovery by principal axis factoring and maximum likelihood factor analysis as a function of factor pattern and sample size</title><source>RePEc</source><source>EBSCOhost Business Source Complete</source><creator>de Winter, J. C.F. ; Dodou, D.</creator><creatorcontrib>de Winter, J. C.F. ; Dodou, D.</creatorcontrib><description>Principal axis factoring (PAF) and maximum likelihood factor analysis (MLFA) are two of the most popular estimation methods in exploratory factor analysis. It is known that PAF is better able to recover weak factors and that the maximum likelihood estimator is asymptotically efficient. However, there is almost no evidence regarding which method should be preferred for different types of factor patterns and sample sizes. Simulations were conducted to investigate factor recovery by PAF and MLFA for distortions of ideal simple structure and sample sizes between 25 and 5000. Results showed that PAF is preferred for population solutions with few indicators per factor and for overextraction. MLFA outperformed PAF in cases of unequal loadings within factors and for underextraction. It was further shown that PAF and MLFA do not always converge with increasing sample size. The simulation findings were confirmed by an empirical study as well as by a classic plasmode, Thurstone's box problem. The present results are of practical value for factor analysts.</description><identifier>ISSN: 0266-4763</identifier><identifier>EISSN: 1360-0532</identifier><identifier>DOI: 10.1080/02664763.2011.610445</identifier><language>eng</language><publisher>Abingdon: Taylor & Francis</publisher><subject>Asymptotic properties ; Discriminant analysis ; Distortion ; empirical data ; Estimating techniques ; exploratory factor analysis ; Factor analysis ; maximum likelihood factor analysis ; Maximum likelihood method ; parameter estimation ; plasmode ; principal axis factoring ; Recovery ; Sample size ; Samples ; Simulation ; simulations ; Statistical analysis ; Statistical methods ; Studies</subject><ispartof>Journal of applied statistics, 2012-04, Vol.39 (4), p.695-710</ispartof><rights>Copyright Taylor & Francis Group, LLC 2012</rights><rights>Copyright Taylor & Francis Ltd. 2012</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c467t-2e1d338ed087f21dab84ac92b5566606e8f2f108d27fbe8f8e1332c05d28da253</citedby><cites>FETCH-LOGICAL-c467t-2e1d338ed087f21dab84ac92b5566606e8f2f108d27fbe8f8e1332c05d28da253</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,3994,27901,27902</link.rule.ids><backlink>$$Uhttp://econpapers.repec.org/article/tafjapsta/v_3a39_3ay_3a2012_3ai_3a4_3ap_3a695-710.htm$$DView record in RePEc$$Hfree_for_read</backlink></links><search><creatorcontrib>de Winter, J. C.F.</creatorcontrib><creatorcontrib>Dodou, D.</creatorcontrib><title>Factor recovery by principal axis factoring and maximum likelihood factor analysis as a function of factor pattern and sample size</title><title>Journal of applied statistics</title><description>Principal axis factoring (PAF) and maximum likelihood factor analysis (MLFA) are two of the most popular estimation methods in exploratory factor analysis. It is known that PAF is better able to recover weak factors and that the maximum likelihood estimator is asymptotically efficient. However, there is almost no evidence regarding which method should be preferred for different types of factor patterns and sample sizes. Simulations were conducted to investigate factor recovery by PAF and MLFA for distortions of ideal simple structure and sample sizes between 25 and 5000. Results showed that PAF is preferred for population solutions with few indicators per factor and for overextraction. MLFA outperformed PAF in cases of unequal loadings within factors and for underextraction. It was further shown that PAF and MLFA do not always converge with increasing sample size. The simulation findings were confirmed by an empirical study as well as by a classic plasmode, Thurstone's box problem. The present results are of practical value for factor analysts.</description><subject>Asymptotic properties</subject><subject>Discriminant analysis</subject><subject>Distortion</subject><subject>empirical data</subject><subject>Estimating techniques</subject><subject>exploratory factor analysis</subject><subject>Factor analysis</subject><subject>maximum likelihood factor analysis</subject><subject>Maximum likelihood method</subject><subject>parameter estimation</subject><subject>plasmode</subject><subject>principal axis factoring</subject><subject>Recovery</subject><subject>Sample size</subject><subject>Samples</subject><subject>Simulation</subject><subject>simulations</subject><subject>Statistical analysis</subject><subject>Statistical methods</subject><subject>Studies</subject><issn>0266-4763</issn><issn>1360-0532</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2012</creationdate><recordtype>article</recordtype><sourceid>X2L</sourceid><recordid>eNqFkc1u1DAUhSMEEkPhDVhYrNjM1P9xVghVFIoqsYG1dcexqYckDnbSEpY8OXcmLQsWIPnasv2dY-ueqnrJ6I5RQ88p11rWWuw4ZWynGZVSPao2TGi6pUrwx9XmiGyPzNPqWSkHSqlhSmyqX5fgppRJ9i7d-ryQ_ULGHAcXR-gI_IiFhBMRh68Ehpb0eNbPPeniN9_Fm5TaewBvoVsKCgAHCfPgppgGksIDMMI0-TycbAr0Y-dJiT_98-pJgK74F_frWfXl8t3niw_b60_vry7eXm-d1PW05Z61QhjfUlMHzlrYGwmu4XultNZUexN4wHa0vA573BjPhOCOqpabFrgSZ9Xr1XfM6fvsy2T7WJzvOhh8motlWnLeaG7E_1GEalarE_rqL_SQ5oytKLbhhkqhZI2QXCGXUynZB4s97iEvllF7jNA-RGiPEdo1QpR9XGXZj9790UwQDjCWCeytFSAanBYsVHJcIpbEGrF0o2yNT9xMPZq9Wc3iEFLu4S7lrkWvpUs5ZMDEixX__M5vMf28gQ</recordid><startdate>201204</startdate><enddate>201204</enddate><creator>de Winter, J. C.F.</creator><creator>Dodou, D.</creator><general>Taylor & Francis</general><general>Taylor and Francis Journals</general><general>Taylor & Francis Ltd</general><scope>DKI</scope><scope>X2L</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>H8D</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>C1K</scope><scope>F1W</scope><scope>H95</scope><scope>H97</scope><scope>L.G</scope></search><sort><creationdate>201204</creationdate><title>Factor recovery by principal axis factoring and maximum likelihood factor analysis as a function of factor pattern and sample size</title><author>de Winter, J. C.F. ; Dodou, D.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c467t-2e1d338ed087f21dab84ac92b5566606e8f2f108d27fbe8f8e1332c05d28da253</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Asymptotic properties</topic><topic>Discriminant analysis</topic><topic>Distortion</topic><topic>empirical data</topic><topic>Estimating techniques</topic><topic>exploratory factor analysis</topic><topic>Factor analysis</topic><topic>maximum likelihood factor analysis</topic><topic>Maximum likelihood method</topic><topic>parameter estimation</topic><topic>plasmode</topic><topic>principal axis factoring</topic><topic>Recovery</topic><topic>Sample size</topic><topic>Samples</topic><topic>Simulation</topic><topic>simulations</topic><topic>Statistical analysis</topic><topic>Statistical methods</topic><topic>Studies</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>de Winter, J. C.F.</creatorcontrib><creatorcontrib>Dodou, D.</creatorcontrib><collection>RePEc IDEAS</collection><collection>RePEc</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>Aerospace Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) 1: Biological Sciences & Living Resources</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) 3: Aquatic Pollution & Environmental Quality</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><jtitle>Journal of applied statistics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>de Winter, J. C.F.</au><au>Dodou, D.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Factor recovery by principal axis factoring and maximum likelihood factor analysis as a function of factor pattern and sample size</atitle><jtitle>Journal of applied statistics</jtitle><date>2012-04</date><risdate>2012</risdate><volume>39</volume><issue>4</issue><spage>695</spage><epage>710</epage><pages>695-710</pages><issn>0266-4763</issn><eissn>1360-0532</eissn><abstract>Principal axis factoring (PAF) and maximum likelihood factor analysis (MLFA) are two of the most popular estimation methods in exploratory factor analysis. It is known that PAF is better able to recover weak factors and that the maximum likelihood estimator is asymptotically efficient. However, there is almost no evidence regarding which method should be preferred for different types of factor patterns and sample sizes. Simulations were conducted to investigate factor recovery by PAF and MLFA for distortions of ideal simple structure and sample sizes between 25 and 5000. Results showed that PAF is preferred for population solutions with few indicators per factor and for overextraction. MLFA outperformed PAF in cases of unequal loadings within factors and for underextraction. It was further shown that PAF and MLFA do not always converge with increasing sample size. The simulation findings were confirmed by an empirical study as well as by a classic plasmode, Thurstone's box problem. The present results are of practical value for factor analysts.</abstract><cop>Abingdon</cop><pub>Taylor & Francis</pub><doi>10.1080/02664763.2011.610445</doi><tpages>16</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0266-4763 |
| ispartof | Journal of applied statistics, 2012-04, Vol.39 (4), p.695-710 |
| issn | 0266-4763 1360-0532 |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1283717583 |
| source | RePEc; EBSCOhost Business Source Complete |
| subjects | Asymptotic properties Discriminant analysis Distortion empirical data Estimating techniques exploratory factor analysis Factor analysis maximum likelihood factor analysis Maximum likelihood method parameter estimation plasmode principal axis factoring Recovery Sample size Samples Simulation simulations Statistical analysis Statistical methods Studies |
| title | Factor recovery by principal axis factoring and maximum likelihood factor analysis as a function of factor pattern and sample size |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-21T16%3A51%3A21IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Factor%20recovery%20by%20principal%20axis%20factoring%20and%20maximum%20likelihood%20factor%20analysis%20as%20a%20function%20of%20factor%20pattern%20and%20sample%20size&rft.jtitle=Journal%20of%20applied%20statistics&rft.au=de%20Winter,%20J.%20C.F.&rft.date=2012-04&rft.volume=39&rft.issue=4&rft.spage=695&rft.epage=710&rft.pages=695-710&rft.issn=0266-4763&rft.eissn=1360-0532&rft_id=info:doi/10.1080/02664763.2011.610445&rft_dat=%3Cproquest_cross%3E1283717583%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=928043547&rft_id=info:pmid/&rfr_iscdi=true |