Radioastrometry at different frequencies

Very long baseline interferometry (VLBI) technique allows us to determine positions of thousands of radio sources using the absolute astrometry approach. I have investigated the impact of a selection of observing frequencies in a range from 2 to 43 GHz in single-band, dual-band, and quad-band observing modes on astrometric results. I processed seven datasets in a range of 72 thousands to 6.9 million observations, estimated source positions, and compared them. I found that source positions derived from dual-band, quad-band, and 23.6 GHz single-band data agree at a level below 0.2 mas. Comparison of independent datasets allowed me to assess the error level of individual catalogues: 0.05-0.07 mas per position component. Further comparison showed that individual catalogues have systematic errors at the same level. Positions from 23.6 GHz single-band data show systematic errors related to the residual ionosphere contribution. Analysis of source positions differences revealed systematic errors along the jet direction at a level of 0.09 mas. Network related systematic errors affect all the data regardless of frequency. Comparison of position estimates allowed me to derive the stochastic error model that closes the error budget. Based on collected evidence, I made a conclusion that development of frequency-dependent reference frames of the entire sky is not warranted. In most cases dual-band, quad-band, and single-band data at frequency 22 GHz and higher can be used interchangeably, which allows us to exploit the strength of a specific frequency setup for given objects. Mixing observations at different frequencies causes errors not exceeding 0.07 mas.