Statistical analysis of single-copy assays when some observations are zero
Observational and interventional studies for HIV cure research often use single-copy assays to quantify rare entities in blood or tissue samples. Statistical analysis of such measurements presents challenges due to tissue sampling variability and frequent findings of 0 copies in the sample analysed....
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-07-01
|
| Series: | Journal of Virus Eradication |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2055664020300479 |
| _version_ | 1819295839667879936 |
|---|---|
| author | Peter Bacchetti Ronald J. Bosch Eileen P. Scully Xutao Deng Michael P. Busch Steven G. Deeks Sharon R. Lewin |
| author_facet | Peter Bacchetti Ronald J. Bosch Eileen P. Scully Xutao Deng Michael P. Busch Steven G. Deeks Sharon R. Lewin |
| author_sort | Peter Bacchetti |
| collection | DOAJ |
| description | Observational and interventional studies for HIV cure research often use single-copy assays to quantify rare entities in blood or tissue samples. Statistical analysis of such measurements presents challenges due to tissue sampling variability and frequent findings of 0 copies in the sample analysed. We examined four approaches to analysing such studies, reflecting different ways of handling observations of 0 copies: (A) replace observations of 0 copies with 1 copy; (B) add 1 to all observed numbers of copies; (C) treat observations of 0 copies as left-censored at 1 copy; and (D) leave the data unaltered and apply a method for count data, negative binomial regression. Because research seeks to estimate general patterns rather than individuals’ values, we argue that unaltered use of 0 copies is suitable for research purposes and that altering those observations can introduce bias. When applied to a simulated study comparing preintervention to postintervention measurements within 12 participants, methods A–C showed more attenuation than method D in the estimated intervention effect, less chance of finding P < 0.05 for the intervention effect and a lower chance of including the true intervention effect within the 95% confidence interval. Application of the methods to actual data from a study comparing multiply-spliced HIV RNA among men and women estimated smaller differences by methods A–C than by method D. We recommend that negative binomial regression, which is readily available in many statistical software packages, be considered for analysis of studies of rare entities that are measured by single-copy assays. |
| first_indexed | 2024-12-24T04:48:36Z |
| format | Article |
| id | doaj.art-45874b23dd1f4e00b368f4f1834cabe6 |
| institution | Directory Open Access Journal |
| issn | 2055-6640 |
| language | English |
| last_indexed | 2024-12-24T04:48:36Z |
| publishDate | 2019-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Virus Eradication |
| spelling | doaj.art-45874b23dd1f4e00b368f4f1834cabe62022-12-21T17:14:36ZengElsevierJournal of Virus Eradication2055-66402019-07-0153167173Statistical analysis of single-copy assays when some observations are zeroPeter Bacchetti0Ronald J. Bosch1Eileen P. Scully2Xutao Deng3Michael P. Busch4Steven G. Deeks5Sharon R. Lewin6Department of Epidemiology and Biostatistics, University of California, San Francisco, CA, USA; Corresponding author: Peter Bacchetti, 5984 Stone Bridge Rd, Santa Rosa, CA95409, USACenter for Biostatistics in AIDS Research, Harvard T. H. Chan School of Public Health, Boston, MA, USADivision of Infectious Diseases, Department of Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USAVitalant Research Institute, San Francisco, CA, USAVitalant Research Institute, San Francisco, CA, USA; Department of Laboratory Medicine, University of California, San Francisco, San Francisco, CA, USAUniversity of California San Francisco, Department of Medicine, San Francisco, CA, USAThe Peter Doherty Institute for Infection and Immunity, The University of Melbourne and Royal Melbourne Hospital, Melbourne, Australia; Department of Infectious Diseases, Monash University and Alfred Hospital, Melbourne, AustraliaObservational and interventional studies for HIV cure research often use single-copy assays to quantify rare entities in blood or tissue samples. Statistical analysis of such measurements presents challenges due to tissue sampling variability and frequent findings of 0 copies in the sample analysed. We examined four approaches to analysing such studies, reflecting different ways of handling observations of 0 copies: (A) replace observations of 0 copies with 1 copy; (B) add 1 to all observed numbers of copies; (C) treat observations of 0 copies as left-censored at 1 copy; and (D) leave the data unaltered and apply a method for count data, negative binomial regression. Because research seeks to estimate general patterns rather than individuals’ values, we argue that unaltered use of 0 copies is suitable for research purposes and that altering those observations can introduce bias. When applied to a simulated study comparing preintervention to postintervention measurements within 12 participants, methods A–C showed more attenuation than method D in the estimated intervention effect, less chance of finding P < 0.05 for the intervention effect and a lower chance of including the true intervention effect within the 95% confidence interval. Application of the methods to actual data from a study comparing multiply-spliced HIV RNA among men and women estimated smaller differences by methods A–C than by method D. We recommend that negative binomial regression, which is readily available in many statistical software packages, be considered for analysis of studies of rare entities that are measured by single-copy assays.http://www.sciencedirect.com/science/article/pii/S2055664020300479HIVlatent reservoirrare entitiesstatistical bias |
| spellingShingle | Peter Bacchetti Ronald J. Bosch Eileen P. Scully Xutao Deng Michael P. Busch Steven G. Deeks Sharon R. Lewin Statistical analysis of single-copy assays when some observations are zero Journal of Virus Eradication HIV latent reservoir rare entities statistical bias |
| title | Statistical analysis of single-copy assays when some observations are zero |
| title_full | Statistical analysis of single-copy assays when some observations are zero |
| title_fullStr | Statistical analysis of single-copy assays when some observations are zero |
| title_full_unstemmed | Statistical analysis of single-copy assays when some observations are zero |
| title_short | Statistical analysis of single-copy assays when some observations are zero |
| title_sort | statistical analysis of single copy assays when some observations are zero |
| topic | HIV latent reservoir rare entities statistical bias |
| url | http://www.sciencedirect.com/science/article/pii/S2055664020300479 |
| work_keys_str_mv | AT peterbacchetti statisticalanalysisofsinglecopyassayswhensomeobservationsarezero AT ronaldjbosch statisticalanalysisofsinglecopyassayswhensomeobservationsarezero AT eileenpscully statisticalanalysisofsinglecopyassayswhensomeobservationsarezero AT xutaodeng statisticalanalysisofsinglecopyassayswhensomeobservationsarezero AT michaelpbusch statisticalanalysisofsinglecopyassayswhensomeobservationsarezero AT stevengdeeks statisticalanalysisofsinglecopyassayswhensomeobservationsarezero AT sharonrlewin statisticalanalysisofsinglecopyassayswhensomeobservationsarezero |