Doctor Philosophiae (PhD) is the highest globally recognized academic qualification available in any field of research. A PhD degree can only be awarded by a university once the applicant has completed a wide-ranging and novel research project. The holder of a PhD degree can teach at universities, start independent scientific research, and also receives a higher salary as better paid positions are reserved to those with a PhD degree. For example, in Hungary only the two most basic academic (assistant lecturer) and scientific (assistant research fellow) positions can be filled by those without a PhD degree. Notably, the effect of education on wages was also sizeable in an Italian study [1], and over-education even had a negative impact [2]. The number of PhD graduates grows rapidly in all continents of the world–in some countries like China by 5% a year [3].

Commonly, the PhD student is assisted by a supervisor and the training requires 3–6 years of full-time investment. As cornerstones, completing the studying requirements, passing the doctoral examination, and the successful defense of the PhD dissertation is needed to obtain the degree. The so-called doctoral dissertation proves that the researcher can independently solve a scientific task, with which it broadens our knowledge with new, previously undiscovered results in the field [4]. The significance of the work made by PhD fellows is supported by the fact that about one third of research publications comes from a doctoral student in universities [5].

The exact conditions for obtaining the degree vary from country to country. In the UK, a PhD is awarded as part of a three-year course including specific and general subjects. Students’ dissertations are reviewed by external reviewers and an oral defense is delivered to show the candidates’ proficiency. In Australia, training with a scholarship lasts for 3–4 years [6] and publications accepted before the application can also form the basis of the doctoral thesis in certain disciplines [7]. Oral presentation for defending the dissertation is not mandatory. The United States has the longest PhD program with 4–11 years for graduates depending on subject areas. In Germany, most doctoral candidates work as employees in universities and training decisions are left to supervisors and doctoral students [8]. In Hungary, a two-year study period ending with a final exam is extended by a three-year research period, and the defense of the doctoral dissertation finishes the training.

A number of indicators are available to measure the quality and quantity of scientific output. Available bibliometric indicators include among others the total number of publications, the cumulative impact factor of all publications, the total number of citations, the number of articles with at least one citation, the number of highly cited articles, the average number of citations per article, the number of citations per year, and the H-index [9–11]. Derived bibliometric indicators have also been developed to measure researcher productivity [12]. There are no international standards for the publication requirements for obtaining a PhD [13]. The minimal requirements are mostly determined by the program, the lead tutors, and by the university. In Australia, 2–5 first or co-authored articles are required to get PhD degree [7]. There is no regulation in the United States and in Canada, although publication is strongly recommended before obtaining a PhD [13]. Peer-reviewed publication is not required in Germany. In Hungary, a discipline-specific number of publications with or without an impact factor threshold are needed to apply for a degree [14].

The scientific outcome of a doctoral training is determined by several factors in addition to the personal abilities of the doctoral student: the doctoral program, relevance, novelty, working environment, access to other experts, feasibility, and supervision [15]. The theoretical conditions of a good doctoral dissertation are also established [16]. Generally, a PhD is said to be strong in case the number of publications of the candidate is high, the total impact factor of these articles is high, and the doctoral student fulfills the training conditions in a shorter time.

To what extent does PhD training influence postdoctoral publication performance? Here, we aimed to correlate independently calculated pre- and post- PhD scientific output for a large cohort of Hungarian researchers spanning all scientific disciplines. In addition to different publication metrics we also aimed to include the age of the doctoral student to determine which features have the highest influence on a researcher’s subsequent career.

Publishing during PhD training has an impact on later careers, reputation, and collaborations [17]. Here, we partially reproduced the results of Horta and Santos, but by accounting for different scientific disciplines and assessing the effects for each disciplinary area. Thus, our results not only build on and validate the previous results [17] but also significantly extend the knowledge in this field.

Early career publications are seen as a requirement to enter an academic career [18]. Along with the excellent educational and professional activity, writing strong articles is an essential condition for promotion in a scientific career [19]. However, the question remains whether scientific publication output during the PhD adequately reflects future academic performance independently of the research environment [6]? Although Horta and Santos partially responded to this question, here we performed a more in-depth analysis including different scientific disciplines. We scrutinized Hungarian researchers whether the scientific performance before the PhD influences postdoctoral scientific output. We examined three bibliometric parameters in the year of obtaining the PhD and ten years later: the number of first, last- or corresponding authored manuscripts accepted in Q1-ranked journals, the H-index, and the total number of independent citations received by the researcher in the given year. In almost all settings each of the metrics measured at the time of obtaining the PhD was positively correlated with the values measured 10 years after the PhD award. These observations are in line with our previous study analyzing publication performance of Momentum grant holders before and after grant award [9] and reinforces the validity of the Matthew effect in this setting as well.

When looking on different scientific field-specific variances, we observed the weakest correlations in Medicine, Biology, and Physics sections for all three parameters compared to other sections. Most probably, the daily routine work of physicians in patient treatment often discourages publication activity [20]. On the other hand, bibliometric indicators achieved at the year of obtaining PhD are outstanding in Medicine, as confirmed by previous other studies as well [21]. Of all scientific sections, Mathematics, Engineering, and Philosophy and History had the highest correlations between pre- and post-PhD scientific output for all three investigated indicators. These observations can be partly explained by the fact that the highest salaries for PhD holders are available in engineering, business and science fields in the United States and in Hungary which can increase compliance and engagement during PhD studies.

We obtained a strong negative correlation between age at obtaining a PhD and subsequent scientific output in all disciplines. Younger age at PhD results in significantly better postdoctoral publications with higher impact. Our results are little bit astonishing, as we have evaluated pre-PhD and postdoctoral publications completely independently. Thus, the scientometric parameters ten years after PhD only reflect the H-index, citation, and publication count of publications printed after finishing the PhD studies. Because of this separation, those who obtain a PhD at a younger age had no advantage in terms of additional years to collect citations to increase their H-index over those who acquired their PhD later.

Publication metrics are not the only indicators of the performance of an individual, but also of an institution [22], and can be used to pave the way for access to external funding sources. Therefore, a main goal of universities worldwide is to maximize research output. Different tactics can be executed to intensify publication activity: writing courses, writing support groups, and writing coaches can significantly increase the number of publications of the research participants according to a study summarizing 17 studies [23]. Reviews also help to grasp available methods for scientific writing [24]. Other options include the continuous mentoring even after the competition of the PhD [25]. Overall, the requirement to publish is a constant high pressure for employees working in academic institutions [26].

Here, we did not examine personal factors such as periods of motherhood, in which case publication activity may be paused for years. The reason for this is the lack of available data regarding maternity leaves for PhD students. Although executed in a different country, a study involving 8,544 researchers from the United States found no effect of personal circumstances including marriage, number of children, and care for aging parents on publication productivity [27]. More important factors seemed to be academic rank, salary, commitment to research, and desire for recognition, which we could not examine due to the lack of available data. The availability of funding resources can also influence publication efficiency. Reputation and experience of the supervisor [6] or of the group leader [28] also impacts the productivity of a researcher. The country-specificity of these effects should be evaluated in a future study.

We have to note a few limitations of our study. In the analysis we did not have any explanatory variable for the PhD training itself. In other words, one does not know how the PhD was trained by the supervisors, if there was co-supervision or not, if one was included in a large or small research group, if one had access to resources to do research, etc. Second, one may publish during the PhD even if the training was not focused on publication. Sometimes it all depends on the earlier training of the students, and the ability of the students. In addition, we included only Hungarian researchers. The reason for this is the utilization of the MTMT database, which only comprises data for Hungarian researchers. A main advantage of MTMT is the differentiation between dependent and independent citations. Other repositories (like Google Scholar or Scopus) either do not have this information or there is no open access. Finally, we included only Q1 articles as our focus was on research excellence and not on research quantity. One might note that lower ranked publications might still have value as scientific results. We have to note however that the majority of all publications of the investigated researchers were published in a Q1 ranked journal.

In the future, a similar study with additional data can bring more light into this field. For example, the association between time to degree, available funding, and accomplished publications during the PhD may be relevant in order to understand how funding can influence the ability to publish or not during the PhD. Conversely, funding during the PhD can affect the research performance later on.

In summary, a major novelty of our analysis is the independent analysis of pre-PhD and post-PhD scientometric parameters. Therefore, in our analysis pre-PhD publications do not directly influence the number of post-PhD citation counts and H-index. Our results are most relevant to early stage pre-PhD researchers and emphasize the importance of building a publication track record. We show that a PhD obtained at a younger age is an outstanding advantage in the later scientific career prognosticating not only more abundant publications but also higher impact of these as measured by citation counts. Post-PhD research output shows a strong correlation to the number of publications and their impact during PhD studies in all scientific disciplines. Our results emphasize the need for pre-doctoral training programs having an emphasis on regular publications. The listed scientific discipline-specific values of scientometric parameters at the time of obtaining the PhD can help to select the most suitable applicants for postdoctoral grants and positions.