Missing value in hydrological studies is an unexceptional riddle that has long been discussed by researchers. There are various patterns and mechanisms of “missingness” that can occur and this may have an impact on how the researcher should treat the missingness before analyzing the data. Supposing the consequence of missing value is disregarded, the outcomes of the statistical analysis will be influenced and the range of variability in the data will not be appropriately projected. The aim of this paper is to brief the patterns and mechanism of missing data, reviews several infilling techniques that are convenient to time series analyses in streamflow and deliberates some advantages and drawback of these approaches practically. Simplest infilling approaches along with more developed techniques, such as model-based deterministic imputation method and machine learning method, were discussed. We conclude that attention should be given to the method chosen to handle the gaps in hydrological aspects since missing data always result in misinterpretation of the resulting statistics.